default search action
BibTeX records: Ishan Misra
@article{DBLP:journals/tmlr/OquabDMVSKFHMEA24, author = {Maxime Oquab and Timoth{\'{e}}e Darcet and Th{\'{e}}o Moutakanni and Huy V. Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El{-}Nouby and Mido Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po{-}Yao Huang and Shang{-}Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Herv{\'{e}} J{\'{e}}gou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski}, title = {DINOv2: Learning Robust Visual Features without Supervision}, journal = {Trans. Mach. Learn. Res.}, volume = {2024}, year = {2024}, url = {https://openreview.net/forum?id=a68SUt6zFt}, timestamp = {Thu, 08 Aug 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tmlr/OquabDMVSKFHMEA24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2402-03290, author = {Xudong Wang and Trevor Darrell and Sai Saketh Rambhatla and Rohit Girdhar and Ishan Misra}, title = {InstanceDiffusion: Instance-level Control for Image Generation}, journal = {CoRR}, volume = {abs/2402.03290}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.03290}, doi = {10.48550/ARXIV.2402.03290}, eprinttype = {arXiv}, eprint = {2402.03290}, timestamp = {Mon, 12 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-03290.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2407-21783, author = {Abhimanyu Dubey and Abhinav Jauhri and Abhinav Pandey and Abhishek Kadian and Ahmad Al{-}Dahle and Aiesha Letman and Akhil Mathur and Alan Schelten and Amy Yang and Angela Fan and Anirudh Goyal and Anthony Hartshorn and Aobo Yang and Archi Mitra and Archie Sravankumar and Artem Korenev and Arthur Hinsvark and Arun Rao and Aston Zhang and Aur{\'{e}}lien Rodriguez and Austen Gregerson and Ava Spataru and Baptiste Rozi{\`{e}}re and Bethany Biron and Binh Tang and Bobbie Chern and Charlotte Caucheteux and Chaya Nayak and Chloe Bi and Chris Marra and Chris McConnell and Christian Keller and Christophe Touret and Chunyang Wu and Corinne Wong and Cristian Canton Ferrer and Cyrus Nikolaidis and Damien Allonsius and Daniel Song and Danielle Pintz and Danny Livshits and David Esiobu and Dhruv Choudhary and Dhruv Mahajan and Diego Garcia{-}Olano and Diego Perino and Dieuwke Hupkes and Egor Lakomkin and Ehab AlBadawy and Elina Lobanova and Emily Dinan and Eric Michael Smith and Filip Radenovic and Frank Zhang and Gabriel Synnaeve and Gabrielle Lee and Georgia Lewis Anderson and Graeme Nail and Gr{\'{e}}goire Mialon and Guan Pang and Guillem Cucurell and Hailey Nguyen and Hannah Korevaar and Hu Xu and Hugo Touvron and Iliyan Zarov and Imanol Arrieta Ibarra and Isabel M. Kloumann and Ishan Misra and Ivan Evtimov and Jade Copet and Jaewon Lee and Jan Geffert and Jana Vranes and Jason Park and Jay Mahadeokar and Jeet Shah and Jelmer van der Linde and Jennifer Billock and Jenny Hong and Jenya Lee and Jeremy Fu and Jianfeng Chi and Jianyu Huang and Jiawen Liu and Jie Wang and Jiecao Yu and Joanna Bitton and Joe Spisak and Jongsoo Park and Joseph Rocca and Joshua Johnstun and Joshua Saxe and Junteng Jia and Kalyan Vasuden Alwala and Kartikeya Upasani and Kate Plawiak and Ke Li and Kenneth Heafield and Kevin Stone and et al.}, title = {The Llama 3 Herd of Models}, journal = {CoRR}, volume = {abs/2407.21783}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2407.21783}, doi = {10.48550/ARXIV.2407.21783}, eprinttype = {arXiv}, eprint = {2407.21783}, timestamp = {Mon, 26 Aug 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2407-21783.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/0007GYM23, author = {Xudong Wang and Rohit Girdhar and Stella X. Yu and Ishan Misra}, title = {Cut and Learn for Unsupervised Object Detection and Instance Segmentation}, booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023}, pages = {3124--3134}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/CVPR52729.2023.00305}, doi = {10.1109/CVPR52729.2023.00305}, timestamp = {Mon, 28 Aug 2023 16:14:07 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/0007GYM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/0006MKG23, author = {Yue Zhao and Ishan Misra and Philipp Kr{\"{a}}henb{\"{u}}hl and Rohit Girdhar}, title = {Learning Video Representations from Large Language Models}, booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023}, pages = {6586--6597}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/CVPR52729.2023.00637}, doi = {10.1109/CVPR52729.2023.00637}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/0006MKG23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/VazeCM23, author = {Sagar Vaze and Nicolas Carion and Ishan Misra}, title = {GeneCIS: {A} Benchmark for General Conditional Image Similarity}, booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023}, pages = {6862--6872}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/CVPR52729.2023.00663}, doi = {10.1109/CVPR52729.2023.00663}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/VazeCM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/GirdharESAJM23, author = {Rohit Girdhar and Alaaeldin El{-}Nouby and Mannat Singh and Kalyan Vasudev Alwala and Armand Joulin and Ishan Misra}, title = {OmniMAE: Single Model Masked Pretraining on Images and Videos}, booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023}, pages = {10406--10417}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/CVPR52729.2023.01003}, doi = {10.1109/CVPR52729.2023.01003}, timestamp = {Tue, 29 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/GirdharESAJM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/GirdharELSAJM23, author = {Rohit Girdhar and Alaaeldin El{-}Nouby and Zhuang Liu and Mannat Singh and Kalyan Vasudev Alwala and Armand Joulin and Ishan Misra}, title = {ImageBind One Embedding Space to Bind Them All}, booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023}, pages = {15180--15190}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/CVPR52729.2023.01457}, doi = {10.1109/CVPR52729.2023.01457}, timestamp = {Tue, 29 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/GirdharELSAJM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/AssranDMBVRLB23, author = {Mahmoud Assran and Quentin Duval and Ishan Misra and Piotr Bojanowski and Pascal Vincent and Michael G. Rabbat and Yann LeCun and Nicolas Ballas}, title = {Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture}, booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023}, pages = {15619--15629}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/CVPR52729.2023.01499}, doi = {10.1109/CVPR52729.2023.01499}, timestamp = {Tue, 29 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/AssranDMBVRLB23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/SinghDA0AAJDFGG23, author = {Mannat Singh and Quentin Duval and Kalyan Vasudev Alwala and Haoqi Fan and Vaibhav Aggarwal and Aaron Adcock and Armand Joulin and Piotr Doll{\'{a}}r and Christoph Feichtenhofer and Ross B. Girshick and Rohit Girdhar and Ishan Misra}, title = {The effectiveness of {MAE} pre-pretraining for billion-scale pretraining}, booktitle = {{IEEE/CVF} International Conference on Computer Vision, {ICCV} 2023, Paris, France, October 1-6, 2023}, pages = {5461--5471}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICCV51070.2023.00505}, doi = {10.1109/ICCV51070.2023.00505}, timestamp = {Mon, 22 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccv/SinghDA0AAJDFGG23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/RambhatlaMCS23, author = {Sai Saketh Rambhatla and Ishan Misra and Rama Chellappa and Abhinav Shrivastava}, title = {{MOST:} Multiple Object localization with Self-supervised Transformers for object discovery}, booktitle = {{IEEE/CVF} International Conference on Computer Vision, {ICCV} 2023, Paris, France, October 1-6, 2023}, pages = {15777--15788}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICCV51070.2023.01450}, doi = {10.1109/ICCV51070.2023.01450}, timestamp = {Mon, 22 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccv/RambhatlaMCS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccvw/HallGAMR23, author = {Melissa Hall and Laura Gustafson and Aaron Adcock and Ishan Misra and Candace Ross}, title = {Vision-Language Models Performing Zero-Shot Tasks Exhibit Disparities Between Gender Groups}, booktitle = {{IEEE/CVF} International Conference on Computer Vision, {ICCV} 2023 - Workshops, Paris, France, October 2-6, 2023}, pages = {2770--2777}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICCVW60793.2023.00294}, doi = {10.1109/ICCVW60793.2023.00294}, timestamp = {Wed, 10 Jan 2024 14:20:12 +0100}, biburl = {https://dblp.org/rec/conf/iccvw/HallGAMR23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/AssranBDBMBVRB23, author = {Mido Assran and Randall Balestriero and Quentin Duval and Florian Bordes and Ishan Misra and Piotr Bojanowski and Pascal Vincent and Michael G. Rabbat and Nicolas Ballas}, title = {The hidden uniform cluster prior in self-supervised learning}, booktitle = {The Eleventh International Conference on Learning Representations, {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023}, publisher = {OpenReview.net}, year = {2023}, url = {https://openreview.net/forum?id=04K3PMtMckp}, timestamp = {Wed, 24 Jul 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iclr/AssranBDBMBVRB23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/MoSMAMYB23, author = {Sangwoo Mo and Jong{-}Chyi Su and Chih{-}Yao Ma and Mido Assran and Ishan Misra and Licheng Yu and Sean Bell}, title = {RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data}, booktitle = {The Eleventh International Conference on Learning Representations, {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023}, publisher = {OpenReview.net}, year = {2023}, url = {https://openreview.net/forum?id=G1H4NSATlr}, timestamp = {Wed, 24 Jul 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iclr/MoSMAMYB23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/FuM023, author = {Yang Fu and Ishan Misra and Xiaolong Wang}, editor = {Andreas Krause and Emma Brunskill and Kyunghyun Cho and Barbara Engelhardt and Sivan Sabato and Jonathan Scarlett}, title = {MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Poses}, booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July 2023, Honolulu, Hawaii, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {202}, pages = {10392--10404}, publisher = {{PMLR}}, year = {2023}, url = {https://proceedings.mlr.press/v202/fu23b.html}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icml/FuM023.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2301-08243, author = {Mahmoud Assran and Quentin Duval and Ishan Misra and Piotr Bojanowski and Pascal Vincent and Michael G. Rabbat and Yann LeCun and Nicolas Ballas}, title = {Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture}, journal = {CoRR}, volume = {abs/2301.08243}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2301.08243}, doi = {10.48550/ARXIV.2301.08243}, eprinttype = {arXiv}, eprint = {2301.08243}, timestamp = {Thu, 26 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2301-08243.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2301-09451, author = {Quentin Duval and Ishan Misra and Nicolas Ballas}, title = {A Simple Recipe for Competitive Low-compute Self supervised Vision Models}, journal = {CoRR}, volume = {abs/2301.09451}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2301.09451}, doi = {10.48550/ARXIV.2301.09451}, eprinttype = {arXiv}, eprint = {2301.09451}, timestamp = {Thu, 26 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2301-09451.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2301-11100, author = {Melissa Hall and Laura Gustafson and Aaron Adcock and Ishan Misra and Candace Ross}, title = {Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based Disparities}, journal = {CoRR}, volume = {abs/2301.11100}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2301.11100}, doi = {10.48550/ARXIV.2301.11100}, eprinttype = {arXiv}, eprint = {2301.11100}, timestamp = {Tue, 31 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2301-11100.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2301-11320, author = {Xudong Wang and Rohit Girdhar and Stella X. Yu and Ishan Misra}, title = {Cut and Learn for Unsupervised Object Detection and Instance Segmentation}, journal = {CoRR}, volume = {abs/2301.11320}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2301.11320}, doi = {10.48550/ARXIV.2301.11320}, eprinttype = {arXiv}, eprint = {2301.11320}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2301-11320.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-14483, author = {Sangwoo Mo and Jong{-}Chyi Su and Chih{-}Yao Ma and Mido Assran and Ishan Misra and Licheng Yu and Sean Bell}, title = {RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data}, journal = {CoRR}, volume = {abs/2302.14483}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.14483}, doi = {10.48550/ARXIV.2302.14483}, eprinttype = {arXiv}, eprint = {2302.14483}, timestamp = {Thu, 02 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-14483.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2303-13496, author = {Mannat Singh and Quentin Duval and Kalyan Vasudev Alwala and Haoqi Fan and Vaibhav Aggarwal and Aaron Adcock and Armand Joulin and Piotr Doll{\'{a}}r and Christoph Feichtenhofer and Ross B. Girshick and Rohit Girdhar and Ishan Misra}, title = {The effectiveness of {MAE} pre-pretraining for billion-scale pretraining}, journal = {CoRR}, volume = {abs/2303.13496}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2303.13496}, doi = {10.48550/ARXIV.2303.13496}, eprinttype = {arXiv}, eprint = {2303.13496}, timestamp = {Thu, 13 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2303-13496.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2304-05387, author = {Sai Saketh Rambhatla and Ishan Misra and Rama Chellappa and Abhinav Shrivastava}, title = {{MOST:} Multiple Object localization with Self-supervised Transformers for object discovery}, journal = {CoRR}, volume = {abs/2304.05387}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2304.05387}, doi = {10.48550/ARXIV.2304.05387}, eprinttype = {arXiv}, eprint = {2304.05387}, timestamp = {Wed, 19 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2304-05387.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2304-07193, author = {Maxime Oquab and Timoth{\'{e}}e Darcet and Th{\'{e}}o Moutakanni and Huy V. Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El{-}Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po{-}Yao Huang and Shang{-}Wen Li and Ishan Misra and Michael G. Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Herv{\'{e}} J{\'{e}}gou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski}, title = {DINOv2: Learning Robust Visual Features without Supervision}, journal = {CoRR}, volume = {abs/2304.07193}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2304.07193}, doi = {10.48550/ARXIV.2304.07193}, eprinttype = {arXiv}, eprint = {2304.07193}, timestamp = {Thu, 08 Aug 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2304-07193.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-05665, author = {Rohit Girdhar and Alaaeldin El{-}Nouby and Zhuang Liu and Mannat Singh and Kalyan Vasudev Alwala and Armand Joulin and Ishan Misra}, title = {ImageBind: One Embedding Space To Bind Them All}, journal = {CoRR}, volume = {abs/2305.05665}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.05665}, doi = {10.48550/ARXIV.2305.05665}, eprinttype = {arXiv}, eprint = {2305.05665}, timestamp = {Mon, 15 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-05665.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-07969, author = {Sagar Vaze and Nicolas Carion and Ishan Misra}, title = {GeneCIS: {A} Benchmark for General Conditional Image Similarity}, journal = {CoRR}, volume = {abs/2306.07969}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.07969}, doi = {10.48550/ARXIV.2306.07969}, eprinttype = {arXiv}, eprint = {2306.07969}, timestamp = {Sun, 18 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-07969.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2308-14710, author = {Xudong Wang and Ishan Misra and Ziyun Zeng and Rohit Girdhar and Trevor Darrell}, title = {VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation}, journal = {CoRR}, volume = {abs/2308.14710}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2308.14710}, doi = {10.48550/ARXIV.2308.14710}, eprinttype = {arXiv}, eprint = {2308.14710}, timestamp = {Mon, 04 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2308-14710.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-10708, author = {Sai Saketh Rambhatla and Ishan Misra}, title = {SelfEval: Leveraging the discriminative nature of generative models for evaluation}, journal = {CoRR}, volume = {abs/2311.10708}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.10708}, doi = {10.48550/ARXIV.2311.10708}, eprinttype = {arXiv}, eprint = {2311.10708}, timestamp = {Wed, 22 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-10708.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-10709, author = {Rohit Girdhar and Mannat Singh and Andrew Brown and Quentin Duval and Samaneh Azadi and Sai Saketh Rambhatla and Akbar Shah and Xi Yin and Devi Parikh and Ishan Misra}, title = {Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning}, journal = {CoRR}, volume = {abs/2311.10709}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.10709}, doi = {10.48550/ARXIV.2311.10709}, eprinttype = {arXiv}, eprint = {2311.10709}, timestamp = {Wed, 22 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-10709.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-16098, author = {Nur Muhammad (Mahi) Shafiullah and Anant Rai and Haritheja Etukuru and Yiqian Liu and Ishan Misra and Soumith Chintala and Lerrel Pinto}, title = {On Bringing Robots Home}, journal = {CoRR}, volume = {abs/2311.16098}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.16098}, doi = {10.48550/ARXIV.2311.16098}, eprinttype = {arXiv}, eprint = {2311.16098}, timestamp = {Fri, 01 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-16098.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-04552, author = {Sachit Menon and Ishan Misra and Rohit Girdhar}, title = {Generating Illustrated Instructions}, journal = {CoRR}, volume = {abs/2312.04552}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.04552}, doi = {10.48550/ARXIV.2312.04552}, eprinttype = {arXiv}, eprint = {2312.04552}, timestamp = {Tue, 02 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-04552.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-17681, author = {Feng Liang and Bichen Wu and Jialiang Wang and Licheng Yu and Kunpeng Li and Yinan Zhao and Ishan Misra and Jia{-}Bin Huang and Peizhao Zhang and Peter Vajda and Diana Marculescu}, title = {FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis}, journal = {CoRR}, volume = {abs/2312.17681}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.17681}, doi = {10.48550/ARXIV.2312.17681}, eprinttype = {arXiv}, eprint = {2312.17681}, timestamp = {Fri, 19 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-17681.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/bmvc/DesaiM0M22, author = {Karan Desai and Ishan Misra and Justin Johnson and Laurens van der Maaten}, title = {Scaling up Instance Segmentation using Approximately Localized Phrases}, booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022}, pages = {648}, publisher = {{BMVA} Press}, year = {2022}, url = {https://bmvc2022.mpi-inf.mpg.de/648/}, timestamp = {Thu, 16 Feb 2023 16:15:04 +0100}, biburl = {https://dblp.org/rec/conf/bmvc/DesaiM0M22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/ChengMSKG22, author = {Bowen Cheng and Ishan Misra and Alexander G. Schwing and Alexander Kirillov and Rohit Girdhar}, title = {Masked-attention Mask Transformer for Universal Image Segmentation}, booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2022, New Orleans, LA, USA, June 18-24, 2022}, pages = {1280--1289}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/CVPR52688.2022.00135}, doi = {10.1109/CVPR52688.2022.00135}, timestamp = {Tue, 04 Oct 2022 15:11:56 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/ChengMSKG22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/GirdharSRMJM22, author = {Rohit Girdhar and Mannat Singh and Nikhila Ravi and Laurens van der Maaten and Armand Joulin and Ishan Misra}, title = {Omnivore: {A} Single Model for Many Visual Modalities}, booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2022, New Orleans, LA, USA, June 18-24, 2022}, pages = {16081--16091}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/CVPR52688.2022.01563}, doi = {10.1109/CVPR52688.2022.01563}, timestamp = {Wed, 05 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/GirdharSRMJM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eccv/ZhouGJKM22, author = {Xingyi Zhou and Rohit Girdhar and Armand Joulin and Philipp Kr{\"{a}}henb{\"{u}}hl and Ishan Misra}, editor = {Shai Avidan and Gabriel J. Brostow and Moustapha Ciss{\'{e}} and Giovanni Maria Farinella and Tal Hassner}, title = {Detecting Twenty-Thousand Classes Using Image-Level Supervision}, booktitle = {Computer Vision - {ECCV} 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part {IX}}, series = {Lecture Notes in Computer Science}, volume = {13669}, pages = {350--368}, publisher = {Springer}, year = {2022}, url = {https://doi.org/10.1007/978-3-031-20077-9\_21}, doi = {10.1007/978-3-031-20077-9\_21}, timestamp = {Thu, 10 Nov 2022 10:31:49 +0100}, biburl = {https://dblp.org/rec/conf/eccv/ZhouGJKM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eccv/AssranCMBBVJRB22, author = {Mahmoud Assran and Mathilde Caron and Ishan Misra and Piotr Bojanowski and Florian Bordes and Pascal Vincent and Armand Joulin and Mike Rabbat and Nicolas Ballas}, editor = {Shai Avidan and Gabriel J. Brostow and Moustapha Ciss{\'{e}} and Giovanni Maria Farinella and Tal Hassner}, title = {Masked Siamese Networks for Label-Efficient Learning}, booktitle = {Computer Vision - {ECCV} 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part {XXXI}}, series = {Lecture Notes in Computer Science}, volume = {13691}, pages = {456--473}, publisher = {Springer}, year = {2022}, url = {https://doi.org/10.1007/978-3-031-19821-2\_26}, doi = {10.1007/978-3-031-19821-2\_26}, timestamp = {Wed, 26 Oct 2022 09:56:23 +0200}, biburl = {https://dblp.org/rec/conf/eccv/AssranCMBBVJRB22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/PunyASMGBL22, author = {Omri Puny and Matan Atzmon and Edward J. Smith and Ishan Misra and Aditya Grover and Heli Ben{-}Hamu and Yaron Lipman}, title = {Frame Averaging for Invariant and Equivariant Network Design}, booktitle = {The Tenth International Conference on Learning Representations, {ICLR} 2022, Virtual Event, April 25-29, 2022}, publisher = {OpenReview.net}, year = {2022}, url = {https://openreview.net/forum?id=zIUyj55nXR}, timestamp = {Sat, 20 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iclr/PunyASMGBL22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/BalestrieroML22, author = {Randall Balestriero and Ishan Misra and Yann LeCun}, editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh}, title = {A Data-Augmentation Is Worth {A} Thousand Samples: Analytical Moments And Sampling-Free Training}, booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022}, year = {2022}, url = {http://papers.nips.cc/paper\_files/paper/2022/hash/7c080cab957edab671ac49ae11e51337-Abstract-Conference.html}, timestamp = {Mon, 08 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/BalestrieroML22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-02605, author = {Xingyi Zhou and Rohit Girdhar and Armand Joulin and Philipp Kr{\"{a}}henb{\"{u}}hl and Ishan Misra}, title = {Detecting Twenty-thousand Classes using Image-level Supervision}, journal = {CoRR}, volume = {abs/2201.02605}, year = {2022}, url = {https://arxiv.org/abs/2201.02605}, eprinttype = {arXiv}, eprint = {2201.02605}, timestamp = {Mon, 10 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-02605.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-08377, author = {Rohit Girdhar and Mannat Singh and Nikhila Ravi and Laurens van der Maaten and Armand Joulin and Ishan Misra}, title = {Omnivore: {A} Single Model for Many Visual Modalities}, journal = {CoRR}, volume = {abs/2201.08377}, year = {2022}, url = {https://arxiv.org/abs/2201.08377}, eprinttype = {arXiv}, eprint = {2201.08377}, timestamp = {Tue, 01 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-08377.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2202-08325, author = {Randall Balestriero and Ishan Misra and Yann LeCun}, title = {A Data-Augmentation Is Worth {A} Thousand Samples: Exact Quantification From Analytical Augmented Sample Moments}, journal = {CoRR}, volume = {abs/2202.08325}, year = {2022}, url = {https://arxiv.org/abs/2202.08325}, eprinttype = {arXiv}, eprint = {2202.08325}, timestamp = {Tue, 01 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2202-08325.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2202-08360, author = {Priya Goyal and Quentin Duval and Isaac Seessel and Mathilde Caron and Ishan Misra and Levent Sagun and Armand Joulin and Piotr Bojanowski}, title = {Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision}, journal = {CoRR}, volume = {abs/2202.08360}, year = {2022}, url = {https://arxiv.org/abs/2202.08360}, eprinttype = {arXiv}, eprint = {2202.08360}, timestamp = {Tue, 01 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2202-08360.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2204-07141, author = {Mahmoud Assran and Mathilde Caron and Ishan Misra and Piotr Bojanowski and Florian Bordes and Pascal Vincent and Armand Joulin and Michael G. Rabbat and Nicolas Ballas}, title = {Masked Siamese Networks for Label-Efficient Learning}, journal = {CoRR}, volume = {abs/2204.07141}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2204.07141}, doi = {10.48550/ARXIV.2204.07141}, eprinttype = {arXiv}, eprint = {2204.07141}, timestamp = {Tue, 19 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2204-07141.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-08356, author = {Rohit Girdhar and Alaaeldin El{-}Nouby and Mannat Singh and Kalyan Vasudev Alwala and Armand Joulin and Ishan Misra}, title = {OmniMAE: Single Model Masked Pretraining on Images and Videos}, journal = {CoRR}, volume = {abs/2206.08356}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.08356}, doi = {10.48550/ARXIV.2206.08356}, eprinttype = {arXiv}, eprint = {2206.08356}, timestamp = {Tue, 21 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-08356.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-07181, author = {Yang Fu and Ishan Misra and Xiaolong Wang}, title = {Multiplane NeRF-Supervised Disentanglement of Depth and Camera Pose from Videos}, journal = {CoRR}, volume = {abs/2210.07181}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.07181}, doi = {10.48550/ARXIV.2210.07181}, eprinttype = {arXiv}, eprint = {2210.07181}, timestamp = {Tue, 18 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-07181.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-07277, author = {Mahmoud Assran and Randall Balestriero and Quentin Duval and Florian Bordes and Ishan Misra and Piotr Bojanowski and Pascal Vincent and Michael G. Rabbat and Nicolas Ballas}, title = {The Hidden Uniform Cluster Prior in Self-Supervised Learning}, journal = {CoRR}, volume = {abs/2210.07277}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.07277}, doi = {10.48550/ARXIV.2210.07277}, eprinttype = {arXiv}, eprint = {2210.07277}, timestamp = {Tue, 18 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-07277.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2212-04501, author = {Yue Zhao and Ishan Misra and Philipp Kr{\"{a}}henb{\"{u}}hl and Rohit Girdhar}, title = {Learning Video Representations from Large Language Models}, journal = {CoRR}, volume = {abs/2212.04501}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2212.04501}, doi = {10.48550/ARXIV.2212.04501}, eprinttype = {arXiv}, eprint = {2212.04501}, timestamp = {Mon, 02 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2212-04501.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/0001VM21, author = {Pedro Morgado and Nuno Vasconcelos and Ishan Misra}, title = {Audio-Visual Instance Discrimination with Cross-Modal Agreement}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2021, virtual, June 19-25, 2021}, pages = {12475--12486}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2021}, url = {https://openaccess.thecvf.com/content/CVPR2021/html/Morgado\_Audio-Visual\_Instance\_Discrimination\_with\_Cross-Modal\_Agreement\_CVPR\_2021\_paper.html}, doi = {10.1109/CVPR46437.2021.01229}, timestamp = {Sun, 04 Aug 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/0001VM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/0001MV21, author = {Pedro Morgado and Ishan Misra and Nuno Vasconcelos}, title = {Robust Audio-Visual Instance Discrimination}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2021, virtual, June 19-25, 2021}, pages = {12934--12945}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2021}, url = {https://openaccess.thecvf.com/content/CVPR2021/html/Morgado\_Robust\_Audio-Visual\_Instance\_Discrimination\_CVPR\_2021\_paper.html}, doi = {10.1109/CVPR46437.2021.01274}, timestamp = {Sun, 04 Aug 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/0001MV21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/RenMSG21, author = {Zhongzheng Ren and Ishan Misra and Alexander G. Schwing and Rohit Girdhar}, title = {3D Spatial Recognition Without Spatially Labeled 3D}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2021, virtual, June 19-25, 2021}, pages = {13204--13213}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2021}, url = {https://openaccess.thecvf.com/content/CVPR2021/html/Ren\_3D\_Spatial\_Recognition\_Without\_Spatially\_Labeled\_3D\_CVPR\_2021\_paper.html}, doi = {10.1109/CVPR46437.2021.01300}, timestamp = {Mon, 18 Jul 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/RenMSG21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/KamathSLSMC21, author = {Aishwarya Kamath and Mannat Singh and Yann LeCun and Gabriel Synnaeve and Ishan Misra and Nicolas Carion}, title = {{MDETR} - Modulated Detection for End-to-End Multi-Modal Understanding}, booktitle = {2021 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2021, Montreal, QC, Canada, October 10-17, 2021}, pages = {1760--1770}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICCV48922.2021.00180}, doi = {10.1109/ICCV48922.2021.00180}, timestamp = {Fri, 11 Mar 2022 10:01:27 +0100}, biburl = {https://dblp.org/rec/conf/iccv/KamathSLSMC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/MisraGJ21, author = {Ishan Misra and Rohit Girdhar and Armand Joulin}, title = {An End-to-End Transformer Model for 3D Object Detection}, booktitle = {2021 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2021, Montreal, QC, Canada, October 10-17, 2021}, pages = {2886--2897}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICCV48922.2021.00290}, doi = {10.1109/ICCV48922.2021.00290}, timestamp = {Fri, 11 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccv/MisraGJ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/AssranCMBJBR21, author = {Mahmoud Assran and Mathilde Caron and Ishan Misra and Piotr Bojanowski and Armand Joulin and Nicolas Ballas and Michael G. Rabbat}, title = {Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples}, booktitle = {2021 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2021, Montreal, QC, Canada, October 10-17, 2021}, pages = {8423--8432}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICCV48922.2021.00833}, doi = {10.1109/ICCV48922.2021.00833}, timestamp = {Fri, 11 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccv/AssranCMBJBR21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/CaronTMJMBJ21, author = {Mathilde Caron and Hugo Touvron and Ishan Misra and Herv{\'{e}} J{\'{e}}gou and Julien Mairal and Piotr Bojanowski and Armand Joulin}, title = {Emerging Properties in Self-Supervised Vision Transformers}, booktitle = {2021 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2021, Montreal, QC, Canada, October 10-17, 2021}, pages = {9630--9640}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICCV48922.2021.00951}, doi = {10.1109/ICCV48922.2021.00951}, timestamp = {Fri, 11 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccv/CaronTMJMBJ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/ZhangGJM21, author = {Zaiwei Zhang and Rohit Girdhar and Armand Joulin and Ishan Misra}, title = {Self-Supervised Pretraining of 3D Features on any Point-Cloud}, booktitle = {2021 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2021, Montreal, QC, Canada, October 10-17, 2021}, pages = {10232--10243}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICCV48922.2021.01009}, doi = {10.1109/ICCV48922.2021.01009}, timestamp = {Fri, 11 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccv/ZhangGJM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/Patrick0MMVAH21, author = {Mandela Patrick and Po{-}Yao Huang and Ishan Misra and Florian Metze and Andrea Vedaldi and Yuki M. Asano and Jo{\~{a}}o F. Henriques}, title = {Space-Time Crop {\&} Attend: Improving Cross-modal Video Representation Learning}, booktitle = {2021 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2021, Montreal, QC, Canada, October 10-17, 2021}, pages = {10540--10552}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICCV48922.2021.01039}, doi = {10.1109/ICCV48922.2021.01039}, timestamp = {Fri, 11 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccv/Patrick0MMVAH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/ZbontarJMLD21, author = {Jure Zbontar and Li Jing and Ishan Misra and Yann LeCun and St{\'{e}}phane Deny}, editor = {Marina Meila and Tong Zhang}, title = {Barlow Twins: Self-Supervised Learning via Redundancy Reduction}, booktitle = {Proceedings of the 38th International Conference on Machine Learning, {ICML} 2021, 18-24 July 2021, Virtual Event}, series = {Proceedings of Machine Learning Research}, volume = {139}, pages = {12310--12320}, publisher = {{PMLR}}, year = {2021}, url = {http://proceedings.mlr.press/v139/zbontar21a.html}, timestamp = {Thu, 01 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icml/ZbontarJMLD21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/PatrickCAMMFVH21, author = {Mandela Patrick and Dylan Campbell and Yuki M. Asano and Ishan Misra and Florian Metze and Christoph Feichtenhofer and Andrea Vedaldi and Jo{\~{a}}o F. Henriques}, editor = {Marc'Aurelio Ranzato and Alina Beygelzimer and Yann N. Dauphin and Percy Liang and Jennifer Wortman Vaughan}, title = {Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers}, booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual}, pages = {12493--12506}, year = {2021}, url = {https://proceedings.neurips.cc/paper/2021/hash/67f7fb873eaf29526a11a9b7ac33bfac-Abstract.html}, timestamp = {Tue, 03 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/nips/PatrickCAMMFVH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2101-02691, author = {Zaiwei Zhang and Rohit Girdhar and Armand Joulin and Ishan Misra}, title = {Self-Supervised Pretraining of 3D Features on any Point-Cloud}, journal = {CoRR}, volume = {abs/2101.02691}, year = {2021}, url = {https://arxiv.org/abs/2101.02691}, eprinttype = {arXiv}, eprint = {2101.02691}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2101-02691.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-01988, author = {Priya Goyal and Mathilde Caron and Benjamin Lefaudeux and Min Xu and Pengchao Wang and Vivek Pai and Mannat Singh and Vitaliy Liptchinsky and Ishan Misra and Armand Joulin and Piotr Bojanowski}, title = {Self-supervised Pretraining of Visual Features in the Wild}, journal = {CoRR}, volume = {abs/2103.01988}, year = {2021}, url = {https://arxiv.org/abs/2103.01988}, eprinttype = {arXiv}, eprint = {2103.01988}, timestamp = {Thu, 04 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-01988.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-03230, author = {Jure Zbontar and Li Jing and Ishan Misra and Yann LeCun and St{\'{e}}phane Deny}, title = {Barlow Twins: Self-Supervised Learning via Redundancy Reduction}, journal = {CoRR}, volume = {abs/2103.03230}, year = {2021}, url = {https://arxiv.org/abs/2103.03230}, eprinttype = {arXiv}, eprint = {2103.03230}, timestamp = {Thu, 01 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-03230.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-10211, author = {Mandela Patrick and Yuki Markus Asano and Bernie Huang and Ishan Misra and Florian Metze and Jo{\~{a}}o F. Henriques and Andrea Vedaldi}, title = {Space-Time Crop {\&} Attend: Improving Cross-modal Video Representation Learning}, journal = {CoRR}, volume = {abs/2103.10211}, year = {2021}, url = {https://arxiv.org/abs/2103.10211}, eprinttype = {arXiv}, eprint = {2103.10211}, timestamp = {Wed, 24 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-10211.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-15916, author = {Pedro Morgado and Ishan Misra and Nuno Vasconcelos}, title = {Robust Audio-Visual Instance Discrimination}, journal = {CoRR}, volume = {abs/2103.15916}, year = {2021}, url = {https://arxiv.org/abs/2103.15916}, eprinttype = {arXiv}, eprint = {2103.15916}, timestamp = {Wed, 07 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-15916.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2104-12763, author = {Aishwarya Kamath and Mannat Singh and Yann LeCun and Ishan Misra and Gabriel Synnaeve and Nicolas Carion}, title = {{MDETR} - Modulated Detection for End-to-End Multi-Modal Understanding}, journal = {CoRR}, volume = {abs/2104.12763}, year = {2021}, url = {https://arxiv.org/abs/2104.12763}, eprinttype = {arXiv}, eprint = {2104.12763}, timestamp = {Mon, 03 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2104-12763.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2104-13963, author = {Mahmoud Assran and Mathilde Caron and Ishan Misra and Piotr Bojanowski and Armand Joulin and Nicolas Ballas and Michael G. Rabbat}, title = {Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples}, journal = {CoRR}, volume = {abs/2104.13963}, year = {2021}, url = {https://arxiv.org/abs/2104.13963}, eprinttype = {arXiv}, eprint = {2104.13963}, timestamp = {Tue, 04 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2104-13963.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2104-14294, author = {Mathilde Caron and Hugo Touvron and Ishan Misra and Herv{\'{e}} J{\'{e}}gou and Julien Mairal and Piotr Bojanowski and Armand Joulin}, title = {Emerging Properties in Self-Supervised Vision Transformers}, journal = {CoRR}, volume = {abs/2104.14294}, year = {2021}, url = {https://arxiv.org/abs/2104.14294}, eprinttype = {arXiv}, eprint = {2104.14294}, timestamp = {Tue, 04 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2104-14294.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2105-06461, author = {Zhongzheng Ren and Ishan Misra and Alexander G. Schwing and Rohit Girdhar}, title = {3D Spatial Recognition without Spatially Labeled 3D}, journal = {CoRR}, volume = {abs/2105.06461}, year = {2021}, url = {https://arxiv.org/abs/2105.06461}, eprinttype = {arXiv}, eprint = {2105.06461}, timestamp = {Tue, 18 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2105-06461.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2106-05392, author = {Mandela Patrick and Dylan Campbell and Yuki Markus Asano and Ishan Misra and Florian Metze and Christoph Feichtenhofer and Andrea Vedaldi and Jo{\~{a}}o F. Henriques}, title = {Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers}, journal = {CoRR}, volume = {abs/2106.05392}, year = {2021}, url = {https://arxiv.org/abs/2106.05392}, eprinttype = {arXiv}, eprint = {2106.05392}, timestamp = {Tue, 15 Jun 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2106-05392.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2109-08141, author = {Ishan Misra and Rohit Girdhar and Armand Joulin}, title = {An End-to-End Transformer Model for 3D Object Detection}, journal = {CoRR}, volume = {abs/2109.08141}, year = {2021}, url = {https://arxiv.org/abs/2109.08141}, eprinttype = {arXiv}, eprint = {2109.08141}, timestamp = {Wed, 22 Sep 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2109-08141.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-03336, author = {Omri Puny and Matan Atzmon and Heli Ben{-}Hamu and Edward J. Smith and Ishan Misra and Aditya Grover and Yaron Lipman}, title = {Frame Averaging for Invariant and Equivariant Network Design}, journal = {CoRR}, volume = {abs/2110.03336}, year = {2021}, url = {https://arxiv.org/abs/2110.03336}, eprinttype = {arXiv}, eprint = {2110.03336}, timestamp = {Thu, 21 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-03336.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2112-01527, author = {Bowen Cheng and Ishan Misra and Alexander G. Schwing and Alexander Kirillov and Rohit Girdhar}, title = {Masked-attention Mask Transformer for Universal Image Segmentation}, journal = {CoRR}, volume = {abs/2112.01527}, year = {2021}, url = {https://arxiv.org/abs/2112.01527}, eprinttype = {arXiv}, eprint = {2112.01527}, timestamp = {Tue, 07 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2112-01527.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2112-10764, author = {Bowen Cheng and Anwesa Choudhuri and Ishan Misra and Alexander Kirillov and Rohit Girdhar and Alexander G. Schwing}, title = {Mask2Former for Video Instance Segmentation}, journal = {CoRR}, volume = {abs/2112.10764}, year = {2021}, url = {https://arxiv.org/abs/2112.10764}, eprinttype = {arXiv}, eprint = {2112.10764}, timestamp = {Tue, 04 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2112-10764.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/YanM0GM20, author = {Xueting Yan and Ishan Misra and Abhinav Gupta and Deepti Ghadiyaram and Dhruv Mahajan}, title = {ClusterFit: Improving Generalization of Visual Representations}, booktitle = {2020 {IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2020, Seattle, WA, USA, June 13-19, 2020}, pages = {6508--6517}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2020}, url = {https://openaccess.thecvf.com/content\_CVPR\_2020/html/Yan\_ClusterFit\_Improving\_Generalization\_of\_Visual\_Representations\_CVPR\_2020\_paper.html}, doi = {10.1109/CVPR42600.2020.00654}, timestamp = {Tue, 31 Aug 2021 14:00:04 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/YanM0GM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/MisraM20, author = {Ishan Misra and Laurens van der Maaten}, title = {Self-Supervised Learning of Pretext-Invariant Representations}, booktitle = {2020 {IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2020, Seattle, WA, USA, June 13-19, 2020}, pages = {6706--6716}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2020}, url = {https://openaccess.thecvf.com/content\_CVPR\_2020/html/Misra\_Self-Supervised\_Learning\_of\_Pretext-Invariant\_Representations\_CVPR\_2020\_paper.html}, doi = {10.1109/CVPR42600.2020.00674}, timestamp = {Mon, 30 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/MisraM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/JiangMRLC20, author = {Huaizu Jiang and Ishan Misra and Marcus Rohrbach and Erik G. Learned{-}Miller and Xinlei Chen}, title = {In Defense of Grid Features for Visual Question Answering}, booktitle = {2020 {IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2020, Seattle, WA, USA, June 13-19, 2020}, pages = {10264--10273}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2020}, url = {https://openaccess.thecvf.com/content\_CVPR\_2020/html/Jiang\_In\_Defense\_of\_Grid\_Features\_for\_Visual\_Question\_Answering\_CVPR\_2020\_paper.html}, doi = {10.1109/CVPR42600.2020.01028}, timestamp = {Mon, 30 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/JiangMRLC20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/CaronMMGBJ20, author = {Mathilde Caron and Ishan Misra and Julien Mairal and Priya Goyal and Piotr Bojanowski and Armand Joulin}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, title = {Unsupervised Learning of Visual Features by Contrasting Cluster Assignments}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, year = {2020}, url = {https://proceedings.neurips.cc/paper/2020/hash/70feb62b69f16e0238f741fab228fec2-Abstract.html}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/CaronMMGBJ20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-03615, author = {Huaizu Jiang and Ishan Misra and Marcus Rohrbach and Erik G. Learned{-}Miller and Xinlei Chen}, title = {In Defense of Grid Features for Visual Question Answering}, journal = {CoRR}, volume = {abs/2001.03615}, year = {2020}, url = {https://arxiv.org/abs/2001.03615}, eprinttype = {arXiv}, eprint = {2001.03615}, timestamp = {Fri, 17 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-03615.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2004-12943, author = {Pedro Morgado and Nuno Vasconcelos and Ishan Misra}, title = {Audio-Visual Instance Discrimination with Cross-Modal Agreement}, journal = {CoRR}, volume = {abs/2004.12943}, year = {2020}, url = {https://arxiv.org/abs/2004.12943}, eprinttype = {arXiv}, eprint = {2004.12943}, timestamp = {Wed, 17 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2004-12943.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2006-09882, author = {Mathilde Caron and Ishan Misra and Julien Mairal and Priya Goyal and Piotr Bojanowski and Armand Joulin}, title = {Unsupervised Learning of Visual Features by Contrasting Cluster Assignments}, journal = {CoRR}, volume = {abs/2006.09882}, year = {2020}, url = {https://arxiv.org/abs/2006.09882}, eprinttype = {arXiv}, eprint = {2006.09882}, timestamp = {Tue, 23 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2006-09882.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2011-13046, author = {Yutong Bai and Haoqi Fan and Ishan Misra and Ganesh Venkatesh and Yongyi Lu and Yuyin Zhou and Qihang Yu and Vikas Chandra and Alan L. Yuille}, title = {Can Temporal Information Help with Contrastive Self-Supervised Learning?}, journal = {CoRR}, volume = {abs/2011.13046}, year = {2020}, url = {https://arxiv.org/abs/2011.13046}, eprinttype = {arXiv}, eprint = {2011.13046}, timestamp = {Mon, 07 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2011-13046.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/DeVriesMWM19, author = {Terrance DeVries and Ishan Misra and Changhan Wang and Laurens van der Maaten}, title = {Does Object Recognition Work for Everyone?}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition Workshops, {CVPR} Workshops 2019, Long Beach, CA, USA, June 16-20, 2019}, pages = {52--59}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2019}, url = {http://openaccess.thecvf.com/content\_CVPRW\_2019/html/cv4gc/de\_Vries\_Does\_Object\_Recognition\_Work\_for\_Everyone\_CVPRW\_2019\_paper.html}, timestamp = {Mon, 30 Aug 2021 17:04:30 +0200}, biburl = {https://dblp.org/rec/conf/cvpr/DeVriesMWM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/KulkarniMT019, author = {Nilesh Kulkarni and Ishan Misra and Shubham Tulsiani and Abhinav Gupta}, title = {3D-RelNet: Joint Object and Relational Network for 3D Prediction}, booktitle = {2019 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2019, Seoul, Korea (South), October 27 - November 2, 2019}, pages = {2212--2221}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICCV.2019.00230}, doi = {10.1109/ICCV.2019.00230}, timestamp = {Thu, 05 Mar 2020 10:01:04 +0100}, biburl = {https://dblp.org/rec/conf/iccv/KulkarniMT019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/GoyalM0M19, author = {Priya Goyal and Dhruv Mahajan and Abhinav Gupta and Ishan Misra}, title = {Scaling and Benchmarking Self-Supervised Visual Representation Learning}, booktitle = {2019 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2019, Seoul, Korea (South), October 27 - November 2, 2019}, pages = {6390--6399}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICCV.2019.00649}, doi = {10.1109/ICCV.2019.00649}, timestamp = {Mon, 28 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iccv/GoyalM0M19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccvw/HuMM19, author = {Hexiang Hu and Ishan Misra and Laurens van der Maaten}, title = {Evaluating Text-to-Image Matching using Binary Image Selection {(BISON)}}, booktitle = {2019 {IEEE/CVF} International Conference on Computer Vision Workshops, {ICCV} Workshops 2019, Seoul, Korea (South), October 27-28, 2019}, pages = {1887--1890}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICCVW.2019.00237}, doi = {10.1109/ICCVW.2019.00237}, timestamp = {Thu, 12 Mar 2020 10:53:35 +0100}, biburl = {https://dblp.org/rec/conf/iccvw/HuMM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1901-06595, author = {Hexiang Hu and Ishan Misra and Laurens van der Maaten}, title = {Binary Image Selection {(BISON):} Interpretable Evaluation of Visual Grounding}, journal = {CoRR}, volume = {abs/1901.06595}, year = {2019}, url = {http://arxiv.org/abs/1901.06595}, eprinttype = {arXiv}, eprint = {1901.06595}, timestamp = {Fri, 01 Feb 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1901-06595.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1905-01235, author = {Priya Goyal and Dhruv Mahajan and Abhinav Gupta and Ishan Misra}, title = {Scaling and Benchmarking Self-Supervised Visual Representation Learning}, journal = {CoRR}, volume = {abs/1905.01235}, year = {2019}, url = {http://arxiv.org/abs/1905.01235}, eprinttype = {arXiv}, eprint = {1905.01235}, timestamp = {Mon, 28 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1905-01235.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1906-02659, author = {Terrance DeVries and Ishan Misra and Changhan Wang and Laurens van der Maaten}, title = {Does Object Recognition Work for Everyone?}, journal = {CoRR}, volume = {abs/1906.02659}, year = {2019}, url = {http://arxiv.org/abs/1906.02659}, eprinttype = {arXiv}, eprint = {1906.02659}, timestamp = {Thu, 13 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1906-02659.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1906-02729, author = {Nilesh Kulkarni and Ishan Misra and Shubham Tulsiani and Abhinav Gupta}, title = {3D-RelNet: Joint Object and Relational Network for 3D Prediction}, journal = {CoRR}, volume = {abs/1906.02729}, year = {2019}, url = {http://arxiv.org/abs/1906.02729}, eprinttype = {arXiv}, eprint = {1906.02729}, timestamp = {Thu, 13 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1906-02729.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1912-01991, author = {Ishan Misra and Laurens van der Maaten}, title = {Self-Supervised Learning of Pretext-Invariant Representations}, journal = {CoRR}, volume = {abs/1912.01991}, year = {2019}, url = {http://arxiv.org/abs/1912.01991}, eprinttype = {arXiv}, eprint = {1912.01991}, timestamp = {Thu, 02 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1912-01991.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1912-03330, author = {Xueting Yan and Ishan Misra and Abhinav Gupta and Deepti Ghadiyaram and Dhruv Mahajan}, title = {ClusterFit: Improving Generalization of Visual Representations}, journal = {CoRR}, volume = {abs/1912.03330}, year = {2019}, url = {http://arxiv.org/abs/1912.03330}, eprinttype = {arXiv}, eprint = {1912.03330}, timestamp = {Mon, 28 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1912-03330.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/MisraGFHGM18, author = {Ishan Misra and Ross B. Girshick and Rob Fergus and Martial Hebert and Abhinav Gupta and Laurens van der Maaten}, title = {Learning by Asking Questions}, booktitle = {2018 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2018, Salt Lake City, UT, USA, June 18-22, 2018}, pages = {11--20}, publisher = {Computer Vision Foundation / {IEEE} Computer Society}, year = {2018}, url = {http://openaccess.thecvf.com/content\_cvpr\_2018/html/Misra\_Learning\_by\_Asking\_CVPR\_2018\_paper.html}, doi = {10.1109/CVPR.2018.00009}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/cvpr/MisraGFHGM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/usenix/JiangWCTMKKPAG18, author = {Angela H. Jiang and Daniel L.{-}K. Wong and Christopher Canel and Lilia Tang and Ishan Misra and Michael Kaminsky and Michael A. Kozuch and Padmanabhan Pillai and David G. Andersen and Gregory R. Ganger}, editor = {Haryadi S. Gunawi and Benjamin C. Reed}, title = {Mainstream: Dynamic Stem-Sharing for Multi-Tenant Video Processing}, booktitle = {Proceedings of the 2018 {USENIX} Annual Technical Conference, {USENIX} {ATC} 2018, Boston, MA, USA, July 11-13, 2018}, pages = {29--42}, publisher = {{USENIX} Association}, year = {2018}, url = {https://www.usenix.org/conference/atc18/presentation/jiang}, timestamp = {Tue, 16 Jul 2024 09:12:32 +0200}, biburl = {https://dblp.org/rec/conf/usenix/JiangWCTMKKPAG18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/MisraGH17, author = {Ishan Misra and Abhinav Gupta and Martial Hebert}, title = {From Red Wine to Red Tomato: Composition with Context}, booktitle = {2017 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2017, Honolulu, HI, USA, July 21-26, 2017}, pages = {1160--1169}, publisher = {{IEEE} Computer Society}, year = {2017}, url = {https://doi.org/10.1109/CVPR.2017.129}, doi = {10.1109/CVPR.2017.129}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/cvpr/MisraGH17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccv/DwibediMH17, author = {Debidatta Dwibedi and Ishan Misra and Martial Hebert}, title = {Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection}, booktitle = {{IEEE} International Conference on Computer Vision, {ICCV} 2017, Venice, Italy, October 22-29, 2017}, pages = {1310--1319}, publisher = {{IEEE} Computer Society}, year = {2017}, url = {https://doi.org/10.1109/ICCV.2017.146}, doi = {10.1109/ICCV.2017.146}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iccv/DwibediMH17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1708-01642, author = {Debidatta Dwibedi and Ishan Misra and Martial Hebert}, title = {Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection}, journal = {CoRR}, volume = {abs/1708.01642}, year = {2017}, url = {http://arxiv.org/abs/1708.01642}, eprinttype = {arXiv}, eprint = {1708.01642}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1708-01642.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1712-01238, author = {Ishan Misra and Ross B. Girshick and Rob Fergus and Martial Hebert and Abhinav Gupta and Laurens van der Maaten}, title = {Learning by Asking Questions}, journal = {CoRR}, volume = {abs/1712.01238}, year = {2017}, url = {http://arxiv.org/abs/1712.01238}, eprinttype = {arXiv}, eprint = {1712.01238}, timestamp = {Fri, 05 Apr 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1712-01238.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/acl/MostafazadehMDM16, author = {Nasrin Mostafazadeh and Ishan Misra and Jacob Devlin and Margaret Mitchell and Xiaodong He and Lucy Vanderwende}, title = {Generating Natural Questions About an Image}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, {ACL} 2016, August 7-12, 2016, Berlin, Germany, Volume 1: Long Papers}, publisher = {The Association for Computer Linguistics}, year = {2016}, url = {https://doi.org/10.18653/v1/p16-1170}, doi = {10.18653/V1/P16-1170}, timestamp = {Fri, 06 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/acl/MostafazadehMDM16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/MisraZMG16, author = {Ishan Misra and C. Lawrence Zitnick and Margaret Mitchell and Ross B. Girshick}, title = {Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels}, booktitle = {2016 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2016, Las Vegas, NV, USA, June 27-30, 2016}, pages = {2930--2939}, publisher = {{IEEE} Computer Society}, year = {2016}, url = {https://doi.org/10.1109/CVPR.2016.320}, doi = {10.1109/CVPR.2016.320}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/cvpr/MisraZMG16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/MisraSGH16, author = {Ishan Misra and Abhinav Shrivastava and Abhinav Gupta and Martial Hebert}, title = {Cross-Stitch Networks for Multi-task Learning}, booktitle = {2016 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2016, Las Vegas, NV, USA, June 27-30, 2016}, pages = {3994--4003}, publisher = {{IEEE} Computer Society}, year = {2016}, url = {https://doi.org/10.1109/CVPR.2016.433}, doi = {10.1109/CVPR.2016.433}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/cvpr/MisraSGH16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eccv/MisraZH16, author = {Ishan Misra and C. Lawrence Zitnick and Martial Hebert}, editor = {Bastian Leibe and Jiri Matas and Nicu Sebe and Max Welling}, title = {Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification}, booktitle = {Computer Vision - {ECCV} 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {9905}, pages = {527--544}, publisher = {Springer}, year = {2016}, url = {https://doi.org/10.1007/978-3-319-46448-0\_32}, doi = {10.1007/978-3-319-46448-0\_32}, timestamp = {Wed, 07 Dec 2022 23:10:23 +0100}, biburl = {https://dblp.org/rec/conf/eccv/MisraZH16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/naacl/HuangFMMADGHKBZ16, author = {Ting{-}Hao (Kenneth) Huang and Francis Ferraro and Nasrin Mostafazadeh and Ishan Misra and Aishwarya Agrawal and Jacob Devlin and Ross B. Girshick and Xiaodong He and Pushmeet Kohli and Dhruv Batra and C. Lawrence Zitnick and Devi Parikh and Lucy Vanderwende and Michel Galley and Margaret Mitchell}, editor = {Kevin Knight and Ani Nenkova and Owen Rambow}, title = {Visual Storytelling}, booktitle = {{NAACL} {HLT} 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego California, USA, June 12-17, 2016}, pages = {1233--1239}, publisher = {The Association for Computational Linguistics}, year = {2016}, url = {https://doi.org/10.18653/v1/n16-1147}, doi = {10.18653/V1/N16-1147}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/naacl/HuangFMMADGHKBZ16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/MostafazadehMDZ16, author = {Nasrin Mostafazadeh and Ishan Misra and Jacob Devlin and Larry Zitnick and Margaret Mitchell and Xiaodong He and Lucy Vanderwende}, title = {Generating Natural Questions About an Image}, journal = {CoRR}, volume = {abs/1603.06059}, year = {2016}, url = {http://arxiv.org/abs/1603.06059}, eprinttype = {arXiv}, eprint = {1603.06059}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/MostafazadehMDZ16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/MisraZH16, author = {Ishan Misra and C. Lawrence Zitnick and Martial Hebert}, title = {Unsupervised Learning using Sequential Verification for Action Recognition}, journal = {CoRR}, volume = {abs/1603.08561}, year = {2016}, url = {http://arxiv.org/abs/1603.08561}, eprinttype = {arXiv}, eprint = {1603.08561}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/MisraZH16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/MisraSGH16, author = {Ishan Misra and Abhinav Shrivastava and Abhinav Gupta and Martial Hebert}, title = {Cross-stitch Networks for Multi-task Learning}, journal = {CoRR}, volume = {abs/1604.03539}, year = {2016}, url = {http://arxiv.org/abs/1604.03539}, eprinttype = {arXiv}, eprint = {1604.03539}, timestamp = {Fri, 05 Apr 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/MisraSGH16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/HuangFMMADGHKBZ16, author = {Ting{-}Hao (Kenneth) Huang and Francis Ferraro and Nasrin Mostafazadeh and Ishan Misra and Aishwarya Agrawal and Jacob Devlin and Ross B. Girshick and Xiaodong He and Pushmeet Kohli and Dhruv Batra and C. Lawrence Zitnick and Devi Parikh and Lucy Vanderwende and Michel Galley and Margaret Mitchell}, title = {Visual Storytelling}, journal = {CoRR}, volume = {abs/1604.03968}, year = {2016}, url = {http://arxiv.org/abs/1604.03968}, eprinttype = {arXiv}, eprint = {1604.03968}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/HuangFMMADGHKBZ16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ficn/AminoffTSCMGT15, author = {Elissa Michele Aminoff and Mariya Toneva and Abhinav Shrivastava and Xinlei Chen and Ishan Misra and Abhinav Gupta and Michael J. Tarr}, title = {Applying artificial vision models to human scene understanding}, journal = {Frontiers Comput. Neurosci.}, volume = {9}, pages = {8}, year = {2015}, url = {https://doi.org/10.3389/fncom.2015.00008}, doi = {10.3389/FNCOM.2015.00008}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ficn/AminoffTSCMGT15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/MisraSH15, author = {Ishan Misra and Abhinav Shrivastava and Martial Hebert}, title = {Watch and learn: Semi-supervised learning of object detectors from videos}, booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2015, Boston, MA, USA, June 7-12, 2015}, pages = {3593--3602}, publisher = {{IEEE} Computer Society}, year = {2015}, url = {https://doi.org/10.1109/CVPR.2015.7298982}, doi = {10.1109/CVPR.2015.7298982}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/cvpr/MisraSH15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/MisraSH15, author = {Ishan Misra and Abhinav Shrivastava and Martial Hebert}, title = {Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos}, journal = {CoRR}, volume = {abs/1505.05769}, year = {2015}, url = {http://arxiv.org/abs/1505.05769}, eprinttype = {arXiv}, eprint = {1505.05769}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/MisraSH15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/MisraZMG15, author = {Ishan Misra and C. Lawrence Zitnick and Margaret Mitchell and Ross B. Girshick}, title = {Learning Visual Classifiers using Human-centric Annotations}, journal = {CoRR}, volume = {abs/1512.06974}, year = {2015}, url = {http://arxiv.org/abs/1512.06974}, eprinttype = {arXiv}, eprint = {1512.06974}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/MisraZMG15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/wacv/MisraSH14, author = {Ishan Misra and Abhinav Shrivastava and Martial Hebert}, title = {Data-driven exemplar model selection}, booktitle = {{IEEE} Winter Conference on Applications of Computer Vision, Steamboat Springs, CO, USA, March 24-26, 2014}, pages = {339--346}, publisher = {{IEEE} Computer Society}, year = {2014}, url = {https://doi.org/10.1109/WACV.2014.6836080}, doi = {10.1109/WACV.2014.6836080}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/wacv/MisraSH14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1303-2171, author = {Kishore Kothapalli and Dip Sankar Banerjee and P. J. Narayanan and Surinder Sood and Aman Kumar Bahl and Shashank Sharma and Shrenik Lad and Krishna Kumar Singh and Kiran Kumar Matam and Sivaramakrishna Bharadwaj and Rohit Nigam and Parikshit Sakurikar and Aditya Deshpande and Ishan Misra and Siddharth Choudhary and Shubham Gupta}, title = {{CPU} and/or {GPU:} Revisiting the {GPU} Vs. {CPU} Myth}, journal = {CoRR}, volume = {abs/1303.2171}, year = {2013}, url = {http://arxiv.org/abs/1303.2171}, eprinttype = {arXiv}, eprint = {1303.2171}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1303-2171.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hipc/DeshpandeMN11, author = {Aditya Deshpande and Ishan Misra and P. J. Narayanan}, title = {Hybrid implementation of error diffusion dithering}, booktitle = {18th International Conference on High Performance Computing, HiPC 2011, Bengaluru, India, December 18-21, 2011}, pages = {1--10}, publisher = {{IEEE} Computer Society}, year = {2011}, url = {https://doi.org/10.1109/HiPC.2011.6152714}, doi = {10.1109/HIPC.2011.6152714}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/hipc/DeshpandeMN11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.