default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSearch dblp for Publications
export results for "Xizhou Zhu"
download as .bib file
@inproceedings{DBLP:conf/cvpr/ChenWW0CXZZZLLL24,
author = {Zhe Chen and
Jiannan Wu and
Wenhai Wang and
Weijie Su and
Guo Chen and
Sen Xing and
Muyan Zhong and
Qinglong Zhang and
Xizhou Zhu and
Lewei Lu and
Bin Li and
Ping Luo and
Tong Lu and
Yu Qiao and
Jifeng Dai},
title = {Intern {VL:} Scaling up Vision Foundation Models and Aligning for
Generic Visual-Linguistic Tasks},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2024, Seattle, WA, USA, June 16-22, 2024},
pages = {24185--24198},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/CVPR52733.2024.02283},
doi = {10.1109/CVPR52733.2024.02283},
timestamp = {Mon, 07 Oct 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/ChenWW0CXZZZLLL24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/Li0WZZQWLLD24,
author = {Hao Li and
Xue Yang and
Zhaokai Wang and
Xizhou Zhu and
Jie Zhou and
Yu Qiao and
Xiaogang Wang and
Hongsheng Li and
Lewei Lu and
Jifeng Dai},
title = {Auto MC-Reward: Automated Dense Reward Design with Large Language
Models for Minecraft},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2024, Seattle, WA, USA, June 16-22, 2024},
pages = {16426--16435},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/CVPR52733.2024.01554},
doi = {10.1109/CVPR52733.2024.01554},
timestamp = {Mon, 07 Oct 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/Li0WZZQWLLD24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/XiongLCWZLWL00L24,
author = {Yuwen Xiong and
Zhiqi Li and
Yuntao Chen and
Feng Wang and
Xizhou Zhu and
Jiapeng Luo and
Wenhai Wang and
Tong Lu and
Hongsheng Li and
Yu Qiao and
Lewei Lu and
Jie Zhou and
Jifeng Dai},
title = {Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator
for Vision Applications},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2024, Seattle, WA, USA, June 16-22, 2024},
pages = {5652--5661},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/CVPR52733.2024.00540},
doi = {10.1109/CVPR52733.2024.00540},
timestamp = {Fri, 04 Oct 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/XiongLCWZLWL00L24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/TianTD0LL00HZ24,
author = {Changyao Tian and
Chenxin Tao and
Jifeng Dai and
Hao Li and
Ziheng Li and
Lewei Lu and
Xiaogang Wang and
Hongsheng Li and
Gao Huang and
Xizhou Zhu},
title = {{ADDP:} Learning General Representations for Image Recognition and
Generation with Alternating Denoising Diffusion Process},
booktitle = {The Twelfth International Conference on Learning Representations,
{ICLR} 2024, Vienna, Austria, May 7-11, 2024},
publisher = {OpenReview.net},
year = {2024},
url = {https://openreview.net/forum?id=cMPm8YFXZe},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/TianTD0LL00HZ24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/Wang0LWHXCLZ0CL24,
author = {Weiyun Wang and
Min Shi and
Qingyun Li and
Wenhai Wang and
Zhenhang Huang and
Linjie Xing and
Zhe Chen and
Hao Li and
Xizhou Zhu and
Zhiguo Cao and
Yushi Chen and
Tong Lu and
Jifeng Dai and
Yu Qiao},
title = {The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding
of the Open World},
booktitle = {The Twelfth International Conference on Learning Representations,
{ICLR} 2024, Vienna, Austria, May 7-11, 2024},
publisher = {OpenReview.net},
year = {2024},
url = {https://openreview.net/forum?id=c2R7ajodcI},
timestamp = {Thu, 08 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/Wang0LWHXCLZ0CL24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-06197,
author = {Yuwen Xiong and
Zhiqi Li and
Yuntao Chen and
Feng Wang and
Xizhou Zhu and
Jiapeng Luo and
Wenhai Wang and
Tong Lu and
Hongsheng Li and
Yu Qiao and
Lewei Lu and
Jie Zhou and
Jifeng Dai},
title = {Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator
for Vision Applications},
journal = {CoRR},
volume = {abs/2401.06197},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.06197},
doi = {10.48550/ARXIV.2401.06197},
eprinttype = {arXiv},
eprint = {2401.06197},
timestamp = {Thu, 25 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-06197.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-08232,
author = {Chongzhi Zhang and
Mingyuan Zhang and
Zhiyang Teng and
Jiayi Li and
Xizhou Zhu and
Lewei Lu and
Ziwei Liu and
Aixin Sun},
title = {Multi-scale 2D Temporal Map Diffusion Models for Natural Language
Video Localization},
journal = {CoRR},
volume = {abs/2401.08232},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.08232},
doi = {10.48550/ARXIV.2401.08232},
eprinttype = {arXiv},
eprint = {2401.08232},
timestamp = {Thu, 01 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-08232.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-10208,
author = {Changyao Tian and
Xizhou Zhu and
Yuwen Xiong and
Weiyun Wang and
Zhe Chen and
Wenhai Wang and
Yuntao Chen and
Lewei Lu and
Tong Lu and
Jie Zhou and
Hongsheng Li and
Yu Qiao and
Jifeng Dai},
title = {MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal
Feature Synchronizer},
journal = {CoRR},
volume = {abs/2401.10208},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.10208},
doi = {10.48550/ARXIV.2401.10208},
eprinttype = {arXiv},
eprint = {2401.10208},
timestamp = {Sun, 21 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-10208.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-19474,
author = {Weiyun Wang and
Yiming Ren and
Haowen Luo and
Tiantong Li and
Chenxiang Yan and
Zhe Chen and
Wenhai Wang and
Qingyun Li and
Lewei Lu and
Xizhou Zhu and
Yu Qiao and
Jifeng Dai},
title = {The All-Seeing Project {V2:} Towards General Relation Comprehension
of the Open World},
journal = {CoRR},
volume = {abs/2402.19474},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.19474},
doi = {10.48550/ARXIV.2402.19474},
eprinttype = {arXiv},
eprint = {2402.19474},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-19474.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2403-02308,
author = {Yuchen Duan and
Weiyun Wang and
Zhe Chen and
Xizhou Zhu and
Lewei Lu and
Tong Lu and
Yu Qiao and
Hongsheng Li and
Jifeng Dai and
Wenhai Wang},
title = {Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like
Architectures},
journal = {CoRR},
volume = {abs/2403.02308},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2403.02308},
doi = {10.48550/ARXIV.2403.02308},
eprinttype = {arXiv},
eprint = {2403.02308},
timestamp = {Fri, 19 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2403-02308.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2404-16821,
author = {Zhe Chen and
Weiyun Wang and
Hao Tian and
Shenglong Ye and
Zhangwei Gao and
Erfei Cui and
Wenwen Tong and
Kongzhi Hu and
Jiapeng Luo and
Zheng Ma and
Ji Ma and
Jiaqi Wang and
Xiaoyi Dong and
Hang Yan and
Hewei Guo and
Conghui He and
Botian Shi and
Zhenjiang Jin and
Chao Xu and
Bin Wang and
Xingjian Wei and
Wei Li and
Wenjian Zhang and
Bo Zhang and
Pinlong Cai and
Licheng Wen and
Xiangchao Yan and
Min Dou and
Lewei Lu and
Xizhou Zhu and
Tong Lu and
Dahua Lin and
Yu Qiao and
Jifeng Dai and
Wenhai Wang},
title = {How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal
Models with Open-Source Suites},
journal = {CoRR},
volume = {abs/2404.16821},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2404.16821},
doi = {10.48550/ARXIV.2404.16821},
eprinttype = {arXiv},
eprint = {2404.16821},
timestamp = {Sat, 17 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2404-16821.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-04330,
author = {Xizhou Zhu and
Xue Yang and
Zhaokai Wang and
Hao Li and
Wenhan Dou and
Junqi Ge and
Lewei Lu and
Yu Qiao and
Jifeng Dai},
title = {Parameter-Inverted Image Pyramid Networks},
journal = {CoRR},
volume = {abs/2406.04330},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2406.04330},
doi = {10.48550/ARXIV.2406.04330},
eprinttype = {arXiv},
eprint = {2406.04330},
timestamp = {Tue, 06 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2406-04330.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-04342,
author = {Chenxin Tao and
Xizhou Zhu and
Shiqian Su and
Lewei Lu and
Changyao Tian and
Xuan Luo and
Gao Huang and
Hongsheng Li and
Yu Qiao and
Jie Zhou and
Jifeng Dai},
title = {Learning 1D Causal Visual Representation with De-focus Attention Networks},
journal = {CoRR},
volume = {abs/2406.04342},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2406.04342},
doi = {10.48550/ARXIV.2406.04342},
eprinttype = {arXiv},
eprint = {2406.04342},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2406-04342.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-07230,
author = {Weiyun Wang and
Shuibo Zhang and
Yiming Ren and
Yuchen Duan and
Tiantong Li and
Shuo Liu and
Mengkang Hu and
Zhe Chen and
Kaipeng Zhang and
Lewei Lu and
Xizhou Zhu and
Ping Luo and
Yu Qiao and
Jifeng Dai and
Wenqi Shao and
Wenhai Wang},
title = {Needle In {A} Multimodal Haystack},
journal = {CoRR},
volume = {abs/2406.07230},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2406.07230},
doi = {10.48550/ARXIV.2406.07230},
eprinttype = {arXiv},
eprint = {2406.07230},
timestamp = {Mon, 22 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2406-07230.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-07543,
author = {Chenyu Yang and
Xizhou Zhu and
Jinguo Zhu and
Weijie Su and
Junjie Wang and
Xuan Dong and
Wenhai Wang and
Lewei Lu and
Bin Li and
Jie Zhou and
Yu Qiao and
Jifeng Dai},
title = {Vision Model Pre-training on Interleaved Image-Text Data via Latent
Compression Learning},
journal = {CoRR},
volume = {abs/2406.07543},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2406.07543},
doi = {10.48550/ARXIV.2406.07543},
eprinttype = {arXiv},
eprint = {2406.07543},
timestamp = {Mon, 29 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2406-07543.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-08394,
author = {Jiannan Wu and
Muyan Zhong and
Sen Xing and
Zeqiang Lai and
Zhaoyang Liu and
Wenhai Wang and
Zhe Chen and
Xizhou Zhu and
Lewei Lu and
Tong Lu and
Ping Luo and
Yu Qiao and
Jifeng Dai},
title = {VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model
for Hundreds of Vision-Language Tasks},
journal = {CoRR},
volume = {abs/2406.08394},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2406.08394},
doi = {10.48550/ARXIV.2406.08394},
eprinttype = {arXiv},
eprint = {2406.08394},
timestamp = {Tue, 23 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2406-08394.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-08418,
author = {Qingyun Li and
Zhe Chen and
Weiyun Wang and
Wenhai Wang and
Shenglong Ye and
Zhenjiang Jin and
Guanzhou Chen and
Yinan He and
Zhangwei Gao and
Erfei Cui and
Jiashuo Yu and
Hao Tian and
Jiasheng Zhou and
Chao Xu and
Bin Wang and
Xingjian Wei and
Wei Li and
Wenjian Zhang and
Bo Zhang and
Pinlong Cai and
Licheng Wen and
Xiangchao Yan and
Zhenxiang Li and
Pei Chu and
Yi Wang and
Min Dou and
Changyao Tian and
Xizhou Zhu and
Lewei Lu and
Yushi Chen and
Junjun He and
Zhongying Tu and
Tong Lu and
Yali Wang and
Limin Wang and
Dahua Lin and
Yu Qiao and
Botian Shi and
Conghui He and
Jifeng Dai},
title = {OmniCorpus: {A} Unified Multimodal Corpus of 10 Billion-Level Images
Interleaved with Text},
journal = {CoRR},
volume = {abs/2406.08418},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2406.08418},
doi = {10.48550/ARXIV.2406.08418},
eprinttype = {arXiv},
eprint = {2406.08418},
timestamp = {Mon, 02 Sep 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2406-08418.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2407-06597,
author = {Renjie Liang and
Li Li and
Chongzhi Zhang and
Jing Wang and
Xizhou Zhu and
Aixin Sun},
title = {TVR-Ranking: {A} Dataset for Ranked Video Moment Retrieval with Imprecise
Queries},
journal = {CoRR},
volume = {abs/2407.06597},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2407.06597},
doi = {10.48550/ARXIV.2407.06597},
eprinttype = {arXiv},
eprint = {2407.06597},
timestamp = {Sun, 18 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2407-06597.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2407-15838,
author = {Yangzhou Liu and
Yue Cao and
Zhangwei Gao and
Weiyun Wang and
Zhe Chen and
Wenhai Wang and
Hao Tian and
Lewei Lu and
Xizhou Zhu and
Tong Lu and
Yu Qiao and
Jifeng Dai},
title = {MMInstruct: {A} High-Quality Multi-Modal Instruction Tuning Dataset
with Extensive Diversity},
journal = {CoRR},
volume = {abs/2407.15838},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2407.15838},
doi = {10.48550/ARXIV.2407.15838},
eprinttype = {arXiv},
eprint = {2407.15838},
timestamp = {Mon, 19 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2407-15838.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2408-02718,
author = {Fanqing Meng and
Jin Wang and
Chuanhao Li and
Quanfeng Lu and
Hao Tian and
Jiaqi Liao and
Xizhou Zhu and
Jifeng Dai and
Yu Qiao and
Ping Luo and
Kaipeng Zhang and
Wenqi Shao},
title = {{MMIU:} Multimodal Multi-image Understanding for Evaluating Large
Vision-Language Models},
journal = {CoRR},
volume = {abs/2408.02718},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2408.02718},
doi = {10.48550/ARXIV.2408.02718},
eprinttype = {arXiv},
eprint = {2408.02718},
timestamp = {Thu, 12 Sep 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2408-02718.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/0002ZTLLHQWZD23,
author = {Weijie Su and
Xizhou Zhu and
Chenxin Tao and
Lewei Lu and
Bin Li and
Gao Huang and
Yu Qiao and
Xiaogang Wang and
Jie Zhou and
Jifeng Dai},
title = {Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual
Information},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023},
pages = {15888--15899},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CVPR52729.2023.01525},
doi = {10.1109/CVPR52729.2023.01525},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/0002ZTLLHQWZD23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/HuYCLSZCDLWLJLD23,
author = {Yihan Hu and
Jiazhi Yang and
Li Chen and
Keyu Li and
Chonghao Sima and
Xizhou Zhu and
Siqi Chai and
Senyao Du and
Tianwei Lin and
Wenhai Wang and
Lewei Lu and
Xiaosong Jia and
Qiang Liu and
Jifeng Dai and
Yu Qiao and
Hongyang Li},
title = {Planning-oriented Autonomous Driving},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023},
pages = {17853--17862},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CVPR52729.2023.01712},
doi = {10.1109/CVPR52729.2023.01712},
timestamp = {Tue, 13 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/HuYCLSZCDLWLJLD23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/LiZJZLYWQWWD23,
author = {Hao Li and
Jinguo Zhu and
Xiaohu Jiang and
Xizhou Zhu and
Hongsheng Li and
Chun Yuan and
Xiaohua Wang and
Yu Qiao and
Xiaogang Wang and
Wenhai Wang and
Jifeng Dai},
title = {Uni-Perceiver v2: {A} Generalist Model for Large-Scale Vision and
Vision-Language Tasks},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023},
pages = {2691--2700},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CVPR52729.2023.00264},
doi = {10.1109/CVPR52729.2023.00264},
timestamp = {Sun, 04 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/LiZJZLYWQWWD23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/TaoZ0HLZ00D23,
author = {Chenxin Tao and
Xizhou Zhu and
Weijie Su and
Gao Huang and
Bin Li and
Jie Zhou and
Yu Qiao and
Xiaogang Wang and
Jifeng Dai},
title = {Siamese Image Modeling for Self-Supervised Vision Representation Learning},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023},
pages = {2132--2141},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CVPR52729.2023.00212},
doi = {10.1109/CVPR52729.2023.00212},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/TaoZ0HLZ00D23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/WangDCHLZHLLLWQ23,
author = {Wenhai Wang and
Jifeng Dai and
Zhe Chen and
Zhenhang Huang and
Zhiqi Li and
Xizhou Zhu and
Xiaowei Hu and
Tong Lu and
Lewei Lu and
Hongsheng Li and
Xiaogang Wang and
Yu Qiao},
title = {InternImage: Exploring Large-Scale Vision Foundation Models with Deformable
Convolutions},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023},
pages = {14408--14419},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CVPR52729.2023.01385},
doi = {10.1109/CVPR52729.2023.01385},
timestamp = {Sun, 04 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/WangDCHLZHLLLWQ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/YangCTTZZHLQLZD23,
author = {Chenyu Yang and
Yuntao Chen and
Hao Tian and
Chenxin Tao and
Xizhou Zhu and
Zhaoxiang Zhang and
Gao Huang and
Hongyang Li and
Yu Qiao and
Lewei Lu and
Jie Zhou and
Jifeng Dai},
title = {BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition
via Perspective Supervision},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2023, Vancouver, BC, Canada, June 17-24, 2023},
pages = {17830--17839},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CVPR52729.2023.01710},
doi = {10.1109/CVPR52729.2023.01710},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/YangCTTZZHLQLZD23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WangCCWZZLLZQD23,
author = {Wenhai Wang and
Zhe Chen and
Xiaokang Chen and
Jiannan Wu and
Xizhou Zhu and
Gang Zeng and
Ping Luo and
Tong Lu and
Jie Zhou and
Yu Qiao and
Jifeng Dai},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {VisionLLM: Large Language Model is also an Open-Ended Decoder for
Vision-Centric Tasks},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/c1f7b1ed763e9c75e4db74b49b76db5f-Abstract-Conference.html},
timestamp = {Thu, 25 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/WangCCWZZLLZQD23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-05662,
author = {Zhaoyang Liu and
Yinan He and
Wenhai Wang and
Weiyun Wang and
Yi Wang and
Shoufa Chen and
Qinglong Zhang and
Zeqiang Lai and
Yang Yang and
Qingyun Li and
Jiashuo Yu and
Kunchang Li and
Zhe Chen and
Xue Yang and
Xizhou Zhu and
Yali Wang and
Limin Wang and
Ping Luo and
Jifeng Dai and
Yu Qiao},
title = {InternGPT: Solving Vision-Centric Tasks by Interacting with Chatbots
Beyond Language},
journal = {CoRR},
volume = {abs/2305.05662},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.05662},
doi = {10.48550/ARXIV.2305.05662},
eprinttype = {arXiv},
eprint = {2305.05662},
timestamp = {Mon, 02 Sep 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-05662.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-11175,
author = {Wenhai Wang and
Zhe Chen and
Xiaokang Chen and
Jiannan Wu and
Xizhou Zhu and
Gang Zeng and
Ping Luo and
Tong Lu and
Jie Zhou and
Yu Qiao and
Jifeng Dai},
title = {VisionLLM: Large Language Model is also an Open-Ended Decoder for
Vision-Centric Tasks},
journal = {CoRR},
volume = {abs/2305.11175},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.11175},
doi = {10.48550/ARXIV.2305.11175},
eprinttype = {arXiv},
eprint = {2305.11175},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-11175.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-17144,
author = {Xizhou Zhu and
Yuntao Chen and
Hao Tian and
Chenxin Tao and
Weijie Su and
Chenyu Yang and
Gao Huang and
Bin Li and
Lewei Lu and
Xiaogang Wang and
Yu Qiao and
Zhaoxiang Zhang and
Jifeng Dai},
title = {Ghost in the Minecraft: Generally Capable Agents for Open-World Environments
via Large Language Models with Text-based Knowledge and Memory},
journal = {CoRR},
volume = {abs/2305.17144},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.17144},
doi = {10.48550/ARXIV.2305.17144},
eprinttype = {arXiv},
eprint = {2305.17144},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-17144.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-05423,
author = {Changyao Tian and
Chenxin Tao and
Jifeng Dai and
Hao Li and
Ziheng Li and
Lewei Lu and
Xiaogang Wang and
Hongsheng Li and
Gao Huang and
Xizhou Zhu},
title = {{ADDP:} Learning General Representations for Image Recognition and
Generation with Alternating Denoising Diffusion Process},
journal = {CoRR},
volume = {abs/2306.05423},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.05423},
doi = {10.48550/ARXIV.2306.05423},
eprinttype = {arXiv},
eprint = {2306.05423},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-05423.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-01907,
author = {Weiyun Wang and
Min Shi and
Qingyun Li and
Wenhai Wang and
Zhenhang Huang and
Linjie Xing and
Zhe Chen and
Hao Li and
Xizhou Zhu and
Zhiguo Cao and
Yushi Chen and
Tong Lu and
Jifeng Dai and
Yu Qiao},
title = {The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding
of the Open World},
journal = {CoRR},
volume = {abs/2308.01907},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.01907},
doi = {10.48550/ARXIV.2308.01907},
eprinttype = {arXiv},
eprint = {2308.01907},
timestamp = {Tue, 06 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-01907.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-07653,
author = {Zeqiang Lai and
Xizhou Zhu and
Jifeng Dai and
Yu Qiao and
Wenhai Wang},
title = {Mini-DALLE3: Interactive Text to Image by Prompting Large Language
Models},
journal = {CoRR},
volume = {abs/2310.07653},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.07653},
doi = {10.48550/ARXIV.2310.07653},
eprinttype = {arXiv},
eprint = {2310.07653},
timestamp = {Wed, 24 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-07653.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-17796,
author = {Zhaoyang Liu and
Zeqiang Lai and
Zhangwei Gao and
Erfei Cui and
Zhiheng Li and
Xizhou Zhu and
Lewei Lu and
Qifeng Chen and
Yu Qiao and
Jifeng Dai and
Wenhai Wang},
title = {ControlLLM: Augment Language Models with Tools by Searching on Graphs},
journal = {CoRR},
volume = {abs/2310.17796},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.17796},
doi = {10.48550/ARXIV.2310.17796},
eprinttype = {arXiv},
eprint = {2310.17796},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-17796.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-09238,
author = {Hao Li and
Xue Yang and
Zhaokai Wang and
Xizhou Zhu and
Jie Zhou and
Yu Qiao and
Xiaogang Wang and
Hongsheng Li and
Lewei Lu and
Jifeng Dai},
title = {Auto MC-Reward: Automated Dense Reward Design with Large Language
Models for Minecraft},
journal = {CoRR},
volume = {abs/2312.09238},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.09238},
doi = {10.48550/ARXIV.2312.09238},
eprinttype = {arXiv},
eprint = {2312.09238},
timestamp = {Tue, 06 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-09238.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-09245,
author = {Wenhai Wang and
Jiangwei Xie and
Chuanyang Hu and
Haoming Zou and
Jianan Fan and
Wenwen Tong and
Yang Wen and
Silei Wu and
Hanming Deng and
Zhiqi Li and
Hao Tian and
Lewei Lu and
Xizhou Zhu and
Xiaogang Wang and
Yu Qiao and
Jifeng Dai},
title = {DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral
Planning States for Autonomous Driving},
journal = {CoRR},
volume = {abs/2312.09245},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.09245},
doi = {10.48550/ARXIV.2312.09245},
eprinttype = {arXiv},
eprint = {2312.09245},
timestamp = {Wed, 24 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-09245.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-14238,
author = {Zhe Chen and
Jiannan Wu and
Wenhai Wang and
Weijie Su and
Guo Chen and
Sen Xing and
Muyan Zhong and
Qinglong Zhang and
Xizhou Zhu and
Lewei Lu and
Bin Li and
Ping Luo and
Tong Lu and
Yu Qiao and
Jifeng Dai},
title = {InternVL: Scaling up Vision Foundation Models and Aligning for Generic
Visual-Linguistic Tasks},
journal = {CoRR},
volume = {abs/2312.14238},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.14238},
doi = {10.48550/ARXIV.2312.14238},
eprinttype = {arXiv},
eprint = {2312.14238},
timestamp = {Thu, 25 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-14238.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/LiFDLHZ22,
author = {Hao Li and
Tianwen Fu and
Jifeng Dai and
Hongsheng Li and
Gao Huang and
Xizhou Zhu},
title = {AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2022, New Orleans, LA, USA, June 18-24, 2022},
pages = {999--1008},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/CVPR52688.2022.00108},
doi = {10.1109/CVPR52688.2022.00108},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/LiFDLHZ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/TaoWZDSHD22,
author = {Chenxin Tao and
Honghui Wang and
Xizhou Zhu and
Jiahua Dong and
Shiji Song and
Gao Huang and
Jifeng Dai},
title = {Exploring the Equivalence of Siamese Self-Supervised Learning via
{A} Unified Gradient Framework},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2022, New Orleans, LA, USA, June 18-24, 2022},
pages = {14411--14420},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/CVPR52688.2022.01403},
doi = {10.1109/CVPR52688.2022.01403},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/TaoWZDSHD22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/ZhuZLWLWD22,
author = {Xizhou Zhu and
Jinguo Zhu and
Hao Li and
Xiaoshi Wu and
Hongsheng Li and
Xiaohua Wang and
Jifeng Dai},
title = {Uni-Perceiver: Pre-training Unified Architecture for Generic Perception
for Zero-shot and Few-shot Tasks},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2022, New Orleans, LA, USA, June 18-24, 2022},
pages = {16783--16794},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/CVPR52688.2022.01630},
doi = {10.1109/CVPR52688.2022.01630},
timestamp = {Sun, 04 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/ZhuZLWLWD22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eccv/TianWZDQ22,
author = {Changyao Tian and
Wenhai Wang and
Xizhou Zhu and
Jifeng Dai and
Yu Qiao},
editor = {Shai Avidan and
Gabriel J. Brostow and
Moustapha Ciss{\'{e}} and
Giovanni Maria Farinella and
Tal Hassner},
title = {{VL-LTR:} Learning Class-wise Visual-Linguistic Representation for
Long-Tailed Visual Recognition},
booktitle = {Computer Vision - {ECCV} 2022 - 17th European Conference, Tel Aviv,
Israel, October 23-27, 2022, Proceedings, Part {XXV}},
series = {Lecture Notes in Computer Science},
volume = {13685},
pages = {73--91},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-3-031-19806-9\_5},
doi = {10.1007/978-3-031-19806-9\_5},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eccv/TianWZDQ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eccv/ZengJYGZDX22,
author = {Ailing Zeng and
Xuan Ju and
Lei Yang and
Ruiyuan Gao and
Xizhou Zhu and
Bo Dai and
Qiang Xu},
editor = {Shai Avidan and
Gabriel J. Brostow and
Moustapha Ciss{\'{e}} and
Giovanni Maria Farinella and
Tal Hassner},
title = {DeciWatch: {A} Simple Baseline for 10{\(^\times\)} Efficient 2D and
3D Pose Estimation},
booktitle = {Computer Vision - {ECCV} 2022 - 17th European Conference, Tel Aviv,
Israel, October 23-27, 2022, Proceedings, Part {V}},
series = {Lecture Notes in Computer Science},
volume = {13665},
pages = {607--624},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-3-031-20065-6\_35},
doi = {10.1007/978-3-031-20065-6\_35},
timestamp = {Tue, 04 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eccv/ZengJYGZDX22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZhuZWWLWD22,
author = {Jinguo Zhu and
Xizhou Zhu and
Wenhai Wang and
Xiaohua Wang and
Hongsheng Li and
Xiaogang Wang and
Jifeng Dai},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional
MoEs},
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/11fc8c98b46d4cbdfe8157267228f7d7-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ZhuZWWLWD22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-08713,
author = {Ailing Zeng and
Xuan Ju and
Lei Yang and
Ruiyuan Gao and
Xizhou Zhu and
Bo Dai and
Qiang Xu},
title = {DeciWatch: {A} Simple Baseline for 10x Efficient 2D and 3D Pose Estimation},
journal = {CoRR},
volume = {abs/2203.08713},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.08713},
doi = {10.48550/ARXIV.2203.08713},
eprinttype = {arXiv},
eprint = {2203.08713},
timestamp = {Tue, 04 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-08713.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-01204,
author = {Chenxin Tao and
Xizhou Zhu and
Gao Huang and
Yu Qiao and
Xiaogang Wang and
Jifeng Dai},
title = {Siamese Image Modeling for Self-Supervised Vision Representation Learning},
journal = {CoRR},
volume = {abs/2206.01204},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.01204},
doi = {10.48550/ARXIV.2206.01204},
eprinttype = {arXiv},
eprint = {2206.01204},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-01204.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-04674,
author = {Jinguo Zhu and
Xizhou Zhu and
Wenhai Wang and
Xiaohua Wang and
Hongsheng Li and
Xiaogang Wang and
Jifeng Dai},
title = {Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional
MoEs},
journal = {CoRR},
volume = {abs/2206.04674},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.04674},
doi = {10.48550/ARXIV.2206.04674},
eprinttype = {arXiv},
eprint = {2206.04674},
timestamp = {Fri, 03 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-04674.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-05324,
author = {Hongyang Li and
Chonghao Sima and
Jifeng Dai and
Wenhai Wang and
Lewei Lu and
Huijie Wang and
Enze Xie and
Zhiqi Li and
Hanming Deng and
Hao Tian and
Xizhou Zhu and
Li Chen and
Yulu Gao and
Xiangwei Geng and
Jia Zeng and
Yang Li and
Jiazhi Yang and
Xiaosong Jia and
Bohan Yu and
Yu Qiao and
Dahua Lin and
Si Liu and
Junchi Yan and
Jianping Shi and
Ping Luo},
title = {Delving into the Devils of Bird's-eye-view Perception: {A} Review,
Evaluation and Recipe},
journal = {CoRR},
volume = {abs/2209.05324},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.05324},
doi = {10.48550/ARXIV.2209.05324},
eprinttype = {arXiv},
eprint = {2209.05324},
timestamp = {Wed, 14 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-05324.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-05778,
author = {Wenhai Wang and
Jifeng Dai and
Zhe Chen and
Zhenhang Huang and
Zhiqi Li and
Xizhou Zhu and
Xiaowei Hu and
Tong Lu and
Lewei Lu and
Hongsheng Li and
Xiaogang Wang and
Yu Qiao},
title = {InternImage: Exploring Large-Scale Vision Foundation Models with Deformable
Convolutions},
journal = {CoRR},
volume = {abs/2211.05778},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.05778},
doi = {10.48550/ARXIV.2211.05778},
eprinttype = {arXiv},
eprint = {2211.05778},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-05778.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-05781,
author = {Jifeng Dai and
Min Shi and
Weiyun Wang and
Sitong Wu and
Linjie Xing and
Wenhai Wang and
Xizhou Zhu and
Lewei Lu and
Jie Zhou and
Xiaogang Wang and
Yu Qiao and
Xiaowei Hu},
title = {Demystify Transformers {\&} Convolutions in Modern Image Deep
Networks},
journal = {CoRR},
volume = {abs/2211.05781},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.05781},
doi = {10.48550/ARXIV.2211.05781},
eprinttype = {arXiv},
eprint = {2211.05781},
timestamp = {Mon, 29 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-05781.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-09807,
author = {Weijie Su and
Xizhou Zhu and
Chenxin Tao and
Lewei Lu and
Bin Li and
Gao Huang and
Yu Qiao and
Xiaogang Wang and
Jie Zhou and
Jifeng Dai},
title = {Towards All-in-one Pre-training via Maximizing Multi-modal Mutual
Information},
journal = {CoRR},
volume = {abs/2211.09807},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.09807},
doi = {10.48550/ARXIV.2211.09807},
eprinttype = {arXiv},
eprint = {2211.09807},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-09807.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-09808,
author = {Hao Li and
Jinguo Zhu and
Xiaohu Jiang and
Xizhou Zhu and
Hongsheng Li and
Chun Yuan and
Xiaohua Wang and
Yu Qiao and
Xiaogang Wang and
Wenhai Wang and
Jifeng Dai},
title = {Uni-Perceiver v2: {A} Generalist Model for Large-Scale Vision and
Vision-Language Tasks},
journal = {CoRR},
volume = {abs/2211.09808},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.09808},
doi = {10.48550/ARXIV.2211.09808},
eprinttype = {arXiv},
eprint = {2211.09808},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-09808.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-10439,
author = {Chenyu Yang and
Yuntao Chen and
Hao Tian and
Chenxin Tao and
Xizhou Zhu and
Zhaoxiang Zhang and
Gao Huang and
Hongyang Li and
Yu Qiao and
Lewei Lu and
Jie Zhou and
Jifeng Dai},
title = {BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition
via Perspective Supervision},
journal = {CoRR},
volume = {abs/2211.10439},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.10439},
doi = {10.48550/ARXIV.2211.10439},
eprinttype = {arXiv},
eprint = {2211.10439},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-10439.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-10156,
author = {Yihan Hu and
Jiazhi Yang and
Li Chen and
Keyu Li and
Chonghao Sima and
Xizhou Zhu and
Siqi Chai and
Senyao Du and
Tianwei Lin and
Wenhai Wang and
Lewei Lu and
Xiaosong Jia and
Qiang Liu and
Jifeng Dai and
Yu Qiao and
Hongyang Li},
title = {Goal-oriented Autonomous Driving},
journal = {CoRR},
volume = {abs/2212.10156},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.10156},
doi = {10.48550/ARXIV.2212.10156},
eprinttype = {arXiv},
eprint = {2212.10156},
timestamp = {Tue, 13 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-10156.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/TianCDZZ21,
author = {Hao Tian and
Yuntao Chen and
Jifeng Dai and
Zhaoxiang Zhang and
Xizhou Zhu},
title = {Unsupervised Object Detection With {LIDAR} Clues},
booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR}
2021, virtual, June 19-25, 2021},
pages = {5962--5972},
publisher = {Computer Vision Foundation / {IEEE}},
year = {2021},
url = {https://openaccess.thecvf.com/content/CVPR2021/html/Tian\_Unsupervised\_Object\_Detection\_With\_LIDAR\_Clues\_CVPR\_2021\_paper.html},
doi = {10.1109/CVPR46437.2021.00590},
timestamp = {Tue, 26 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cvpr/TianCDZZ21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/LiTZWHD21,
author = {Hao Li and
Chenxin Tao and
Xizhou Zhu and
Xiaogang Wang and
Gao Huang and
Jifeng Dai},
title = {Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation},
booktitle = {9th International Conference on Learning Representations, {ICLR} 2021,
Virtual Event, Austria, May 3-7, 2021},
publisher = {OpenReview.net},
year = {2021},
url = {https://openreview.net/forum?id=MJAqnaC2vO1},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/LiTZWHD21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/ZhuSLLWD21,
author = {Xizhou Zhu and
Weijie Su and
Lewei Lu and
Bin Li and
Xiaogang Wang and
Jifeng Dai},
title = {Deformable {DETR:} Deformable Transformers for End-to-End Object Detection},
booktitle = {9th International Conference on Learning Representations, {ICLR} 2021,
Virtual Event, Austria, May 3-7, 2021},
publisher = {OpenReview.net},
year = {2021},
url = {https://openreview.net/forum?id=gZ9hCDWe6ke},
timestamp = {Tue, 15 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iclr/ZhuSLLWD21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/TaoLZHLD21,
author = {Chenxin Tao and
Zizhang Li and
Xizhou Zhu and
Gao Huang and
Yong Liu and
Jifeng Dai},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Searching Parameterized {AP} Loss for Object Detection},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {22021--22033},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/b9009beb804fa097c04d226a8ba5102e-Abstract.html},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/TaoLZHLD21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-14026,
author = {Hao Li and
Tianwen Fu and
Jifeng Dai and
Hongsheng Li and
Gao Huang and
Xizhou Zhu},
title = {AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks},
journal = {CoRR},
volume = {abs/2103.14026},
year = {2021},
url = {https://arxiv.org/abs/2103.14026},
eprinttype = {arXiv},
eprint = {2103.14026},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-14026.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-01151,
author = {Haiyang Wang and
Wenguan Wang and
Xizhou Zhu and
Jifeng Dai and
Liwei Wang},
title = {Collaborative Visual Navigation},
journal = {CoRR},
volume = {abs/2107.01151},
year = {2021},
url = {https://arxiv.org/abs/2107.01151},
eprinttype = {arXiv},
eprint = {2107.01151},
timestamp = {Tue, 12 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-01151.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-13579,
author = {Changyao Tian and
Wenhai Wang and
Xizhou Zhu and
Xiaogang Wang and
Jifeng Dai and
Yu Qiao},
title = {{VL-LTR:} Learning Class-wise Visual-Linguistic Representation for
Long-Tailed Visual Recognition},
journal = {CoRR},
volume = {abs/2111.13579},
year = {2021},
url = {https://arxiv.org/abs/2111.13579},
eprinttype = {arXiv},
eprint = {2111.13579},
timestamp = {Mon, 03 Jun 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-13579.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-01522,
author = {Xizhou Zhu and
Jinguo Zhu and
Hao Li and
Xiaoshi Wu and
Xiaogang Wang and
Hongsheng Li and
Xiaohua Wang and
Jifeng Dai},
title = {Uni-Perceiver: Pre-training Unified Architecture for Generic Perception
for Zero-shot and Few-shot Tasks},
journal = {CoRR},
volume = {abs/2112.01522},
year = {2021},
url = {https://arxiv.org/abs/2112.01522},
eprinttype = {arXiv},
eprint = {2112.01522},
timestamp = {Tue, 06 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-01522.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-05138,
author = {Chenxin Tao and
Zizhang Li and
Xizhou Zhu and
Gao Huang and
Yong Liu and
Jifeng Dai},
title = {Searching Parameterized {AP} Loss for Object Detection},
journal = {CoRR},
volume = {abs/2112.05138},
year = {2021},
url = {https://arxiv.org/abs/2112.05138},
eprinttype = {arXiv},
eprint = {2112.05138},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-05138.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-05141,
author = {Chenxin Tao and
Honghui Wang and
Xizhou Zhu and
Jiahua Dong and
Shiji Song and
Gao Huang and
Jifeng Dai},
title = {Exploring the Equivalence of Siamese Self-Supervised Learning via
{A} Unified Gradient Framework},
journal = {CoRR},
volume = {abs/2112.05141},
year = {2021},
url = {https://arxiv.org/abs/2112.05141},
eprinttype = {arXiv},
eprint = {2112.05141},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-05141.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eccv/XieZZHL20,
author = {Zhenda Xie and
Zheng Zhang and
Xizhou Zhu and
Gao Huang and
Stephen Lin},
editor = {Andrea Vedaldi and
Horst Bischof and
Thomas Brox and
Jan{-}Michael Frahm},
title = {Spatially Adaptive Inference with Stochastic Feature Sampling and
Interpolation},
booktitle = {Computer Vision - {ECCV} 2020 - 16th European Conference, Glasgow,
UK, August 23-28, 2020, Proceedings, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {12346},
pages = {531--548},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-3-030-58452-8\_31},
doi = {10.1007/978-3-030-58452-8\_31},
timestamp = {Thu, 22 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eccv/XieZZHL20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/GaoZLD20,
author = {Hang Gao and
Xizhou Zhu and
Stephen Lin and
Jifeng Dai},
title = {Deformable Kernels: Adapting Effective Receptive Fields for Object
Deformation},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=SkxSv6VFvS},
timestamp = {Thu, 19 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/GaoZLD20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/SuZCLLWD20,
author = {Weijie Su and
Xizhou Zhu and
Yue Cao and
Bin Li and
Lewei Lu and
Furu Wei and
Jifeng Dai},
title = {{VL-BERT:} Pre-training of Generic Visual-Linguistic Representations},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=SygXPaEYvH},
timestamp = {Tue, 12 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/SuZCLLWD20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-08866,
author = {Zhenda Xie and
Zheng Zhang and
Xizhou Zhu and
Gao Huang and
Stephen Lin},
title = {Spatially Adaptive Inference with Stochastic Feature Sampling and
Interpolation},
journal = {CoRR},
volume = {abs/2003.08866},
year = {2020},
url = {https://arxiv.org/abs/2003.08866},
eprinttype = {arXiv},
eprint = {2003.08866},
timestamp = {Thu, 22 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-08866.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-04159,
author = {Xizhou Zhu and
Weijie Su and
Lewei Lu and
Bin Li and
Xiaogang Wang and
Jifeng Dai},
title = {Deformable {DETR:} Deformable Transformers for End-to-End Object Detection},
journal = {CoRR},
volume = {abs/2010.04159},
year = {2020},
url = {https://arxiv.org/abs/2010.04159},
eprinttype = {arXiv},
eprint = {2010.04159},
timestamp = {Tue, 15 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-04159.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-07930,
author = {Hao Li and
Chenxin Tao and
Xizhou Zhu and
Xiaogang Wang and
Gao Huang and
Jifeng Dai},
title = {Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation},
journal = {CoRR},
volume = {abs/2010.07930},
year = {2020},
url = {https://arxiv.org/abs/2010.07930},
eprinttype = {arXiv},
eprint = {2010.07930},
timestamp = {Tue, 20 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-07930.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-12953,
author = {Hao Tian and
Yuntao Chen and
Jifeng Dai and
Zhaoxiang Zhang and
Xizhou Zhu},
title = {Unsupervised Object Detection with LiDAR Clues},
journal = {CoRR},
volume = {abs/2011.12953},
year = {2020},
url = {https://arxiv.org/abs/2011.12953},
eprinttype = {arXiv},
eprint = {2011.12953},
timestamp = {Tue, 26 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-12953.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/ZhuHLD19,
author = {Xizhou Zhu and
Han Hu and
Stephen Lin and
Jifeng Dai},
title = {Deformable ConvNets {V2:} More Deformable, Better Results},
booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR}
2019, Long Beach, CA, USA, June 16-20, 2019},
pages = {9308--9316},
publisher = {Computer Vision Foundation / {IEEE}},
year = {2019},
url = {http://openaccess.thecvf.com/content\_CVPR\_2019/html/Zhu\_Deformable\_ConvNets\_V2\_More\_Deformable\_Better\_Results\_CVPR\_2019\_paper.html},
doi = {10.1109/CVPR.2019.00953},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/ZhuHLD19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccv/ZhuCZLD19,
author = {Xizhou Zhu and
Dazhi Cheng and
Zheng Zhang and
Stephen Lin and
Jifeng Dai},
title = {An Empirical Study of Spatial Attention Mechanisms in Deep Networks},
booktitle = {2019 {IEEE/CVF} International Conference on Computer Vision, {ICCV}
2019, Seoul, Korea (South), October 27 - November 2, 2019},
pages = {6687--6696},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICCV.2019.00679},
doi = {10.1109/ICCV.2019.00679},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iccv/ZhuCZLD19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-05873,
author = {Xizhou Zhu and
Dazhi Cheng and
Zheng Zhang and
Stephen Lin and
Jifeng Dai},
title = {An Empirical Study of Spatial Attention Mechanisms in Deep Networks},
journal = {CoRR},
volume = {abs/1904.05873},
year = {2019},
url = {http://arxiv.org/abs/1904.05873},
eprinttype = {arXiv},
eprint = {1904.05873},
timestamp = {Thu, 19 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-05873.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-08530,
author = {Weijie Su and
Xizhou Zhu and
Yue Cao and
Bin Li and
Lewei Lu and
Furu Wei and
Jifeng Dai},
title = {{VL-BERT:} Pre-training of Generic Visual-Linguistic Representations},
journal = {CoRR},
volume = {abs/1908.08530},
year = {2019},
url = {http://arxiv.org/abs/1908.08530},
eprinttype = {arXiv},
eprint = {1908.08530},
timestamp = {Tue, 12 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-08530.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-02940,
author = {Hang Gao and
Xizhou Zhu and
Steve Lin and
Jifeng Dai},
title = {Deformable Kernels: Adapting Effective Receptive Fields for Object
Deformation},
journal = {CoRR},
volume = {abs/1910.02940},
year = {2019},
url = {http://arxiv.org/abs/1910.02940},
eprinttype = {arXiv},
eprint = {1910.02940},
timestamp = {Fri, 06 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-02940.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/ZhuDYW18,
author = {Xizhou Zhu and
Jifeng Dai and
Lu Yuan and
Yichen Wei},
title = {Towards High Performance Video Object Detection},
booktitle = {2018 {IEEE} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2018, Salt Lake City, UT, USA, June 18-22, 2018},
pages = {7210--7218},
publisher = {Computer Vision Foundation / {IEEE} Computer Society},
year = {2018},
url = {http://openaccess.thecvf.com/content\_cvpr\_2018/html/Zhu\_Towards\_High\_Performance\_CVPR\_2018\_paper.html},
doi = {10.1109/CVPR.2018.00753},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/ZhuDYW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-05830,
author = {Xizhou Zhu and
Jifeng Dai and
Xingchi Zhu and
Yichen Wei and
Lu Yuan},
title = {Towards High Performance Video Object Detection for Mobiles},
journal = {CoRR},
volume = {abs/1804.05830},
year = {2018},
url = {http://arxiv.org/abs/1804.05830},
eprinttype = {arXiv},
eprint = {1804.05830},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-05830.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-11167,
author = {Zheng Zhang and
Dazhi Cheng and
Xizhou Zhu and
Stephen Lin and
Jifeng Dai},
title = {Integrated Object Detection and Tracking with Tracklet-Conditioned
Detection},
journal = {CoRR},
volume = {abs/1811.11167},
year = {2018},
url = {http://arxiv.org/abs/1811.11167},
eprinttype = {arXiv},
eprint = {1811.11167},
timestamp = {Thu, 19 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-11167.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-11168,
author = {Xizhou Zhu and
Han Hu and
Stephen Lin and
Jifeng Dai},
title = {Deformable ConvNets v2: More Deformable, Better Results},
journal = {CoRR},
volume = {abs/1811.11168},
year = {2018},
url = {http://arxiv.org/abs/1811.11168},
eprinttype = {arXiv},
eprint = {1811.11168},
timestamp = {Mon, 05 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-11168.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/ZhuXDYW17,
author = {Xizhou Zhu and
Yuwen Xiong and
Jifeng Dai and
Lu Yuan and
Yichen Wei},
title = {Deep Feature Flow for Video Recognition},
booktitle = {2017 {IEEE} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2017, Honolulu, HI, USA, July 21-26, 2017},
pages = {4141--4150},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.ieeecomputersociety.org/10.1109/CVPR.2017.441},
doi = {10.1109/CVPR.2017.441},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/ZhuXDYW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccv/ZhuWDYW17,
author = {Xizhou Zhu and
Yujie Wang and
Jifeng Dai and
Lu Yuan and
Yichen Wei},
title = {Flow-Guided Feature Aggregation for Video Object Detection},
booktitle = {{IEEE} International Conference on Computer Vision, {ICCV} 2017, Venice,
Italy, October 22-29, 2017},
pages = {408--417},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/ICCV.2017.52},
doi = {10.1109/ICCV.2017.52},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iccv/ZhuWDYW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhuWDYW17,
author = {Xizhou Zhu and
Yujie Wang and
Jifeng Dai and
Lu Yuan and
Yichen Wei},
title = {Flow-Guided Feature Aggregation for Video Object Detection},
journal = {CoRR},
volume = {abs/1703.10025},
year = {2017},
url = {http://arxiv.org/abs/1703.10025},
eprinttype = {arXiv},
eprint = {1703.10025},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhuWDYW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-11577,
author = {Xizhou Zhu and
Jifeng Dai and
Lu Yuan and
Yichen Wei},
title = {Towards High Performance Video Object Detection},
journal = {CoRR},
volume = {abs/1711.11577},
year = {2017},
url = {http://arxiv.org/abs/1711.11577},
eprinttype = {arXiv},
eprint = {1711.11577},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-11577.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tvcg/LiuLZLWP16,
author = {Mengchen Liu and
Shixia Liu and
Xizhou Zhu and
Qinying Liao and
Furu Wei and
Shimei Pan},
title = {An Uncertainty-Aware Approach for Exploratory Microblog Retrieval},
journal = {{IEEE} Trans. Vis. Comput. Graph.},
volume = {22},
number = {1},
pages = {250--259},
year = {2016},
url = {https://doi.org/10.1109/TVCG.2015.2467554},
doi = {10.1109/TVCG.2015.2467554},
timestamp = {Sun, 06 Oct 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tvcg/LiuLZLWP16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhuXDYW16,
author = {Xizhou Zhu and
Yuwen Xiong and
Jifeng Dai and
Lu Yuan and
Yichen Wei},
title = {Deep Feature Flow for Video Recognition},
journal = {CoRR},
volume = {abs/1611.07715},
year = {2016},
url = {http://arxiv.org/abs/1611.07715},
eprinttype = {arXiv},
eprint = {1611.07715},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhuXDYW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pcm/ChengZWHI15,
author = {Xina Cheng and
Xizhou Zhuang and
Yuan Wang and
Masaaki Honda and
Takeshi Ikenaga},
editor = {Yo{-}Sung Ho and
Jitao Sang and
Yong Man Ro and
Junmo Kim and
Fei Wu},
title = {Particle Filter with Ball Size Adaptive Tracking Window and Ball Feature
Likelihood Model for Ball's 3D Position Tracking in Volleyball Analysis},
booktitle = {Advances in Multimedia Information Processing - {PCM} 2015 - 16th
Pacific-Rim Conference on Multimedia, Gwangju, South Korea, September
16-18, 2015, Proceedings, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {9314},
pages = {203--211},
publisher = {Springer},
year = {2015},
url = {https://doi.org/10.1007/978-3-319-24075-6\_20},
doi = {10.1007/978-3-319-24075-6\_20},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/pcm/ChengZWHI15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pcm/ZhuangCHHI15,
author = {Xizhou Zhuang and
Xina Cheng and
Shu{-}Yi Huang and
Masaaki Honda and
Takeshi Ikenaga},
editor = {Yo{-}Sung Ho and
Jitao Sang and
Yong Man Ro and
Junmo Kim and
Fei Wu},
title = {Motion Vector and Players' Features Based Particle Filter for Volleyball
Players Tracking in 3D Space},
booktitle = {Advances in Multimedia Information Processing - {PCM} 2015 - 16th
Pacific-Rim Conference on Multimedia, Gwangju, South Korea, September
16-18, 2015, Proceedings, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {9314},
pages = {393--401},
publisher = {Springer},
year = {2015},
url = {https://doi.org/10.1007/978-3-319-24075-6\_38},
doi = {10.1007/978-3-319-24075-6\_38},
timestamp = {Sun, 21 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pcm/ZhuangCHHI15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiuLZLWP15,
author = {Mengchen Liu and
Shixia Liu and
Xizhou Zhu and
Qinying Liao and
Furu Wei and
Shimei Pan},
title = {An Uncertainty-Aware Approach for Exploratory Microblog Retrieval},
journal = {CoRR},
volume = {abs/1512.04038},
year = {2015},
url = {http://arxiv.org/abs/1512.04038},
eprinttype = {arXiv},
eprint = {1512.04038},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiuLZLWP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ChengSZI14,
author = {Xina Cheng and
Yuhi Shiina and
Xizhou Zhuang and
Takeshi Ikenaga},
title = {Player tracking using prediction after intersection based particle
filter for volleyball match video},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2014, Chiang Mai, Thailand, December
9-12, 2014},
pages = {1--4},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/APSIPA.2014.7041650},
doi = {10.1109/APSIPA.2014.7041650},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/ChengSZI14.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.
retrieved on 2024-10-09 02:41 CEST from data curated by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
