default search action
Atsuto Maki
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [i19]Hiroki Azuma, Yusuke Matsui, Atsuto Maki:
ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer. CoRR abs/2403.13652 (2024) - [i18]Xiaomeng Zhu, Talha Bilal, Pär Mårtensson, Lars Hanson, Mårten Björkman, Atsuto Maki:
Towards Sim-to-Real Industrial Parts Classification with Synthetic Dataset. CoRR abs/2404.08778 (2024) - 2023
- [j25]Kazuhiro Fukui, Naoya Sogi, Takumi Kobayashi, Jing-Hao Xue, Atsuto Maki:
Discriminant Feature Extraction by Generalized Difference Subspace. IEEE Trans. Pattern Anal. Mach. Intell. 45(2): 1618-1635 (2023) - [c54]Xiaomeng Zhu, Talha Bilal, Pär Mårtensson, Lars Hanson, Mårten Björkman, Atsuto Maki:
Towards Sim-to-Real Industrial Parts Classification with Synthetic Dataset. CVPR Workshops 2023: 4454-4463 - [c53]Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki:
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks. NLDL 2023 - [c52]Daniel Sabel, Torbjörn Westin, Atsuto Maki:
3D Point Cloud Registration for GNSS-denied Aerial Localization over Forests. SCIA (1) 2023: 396-411 - [i17]Takumi Kanai, Naoya Sogi, Atsuto Maki, Kazuhiro Fukui:
Time-series Anomaly Detection based on Difference Subspace between Signal Subspaces. CoRR abs/2303.17802 (2023) - [i16]Marcus Nordström, Henrik Hult, Atsuto Maki, Fredrik Löfman:
Noisy Image Segmentation With Soft-Dice. CoRR abs/2304.00801 (2023) - [i15]Marcus Nordström, Henrik Hult, Atsuto Maki:
Marginal Thresholding in Noisy Image Segmentation. CoRR abs/2304.04116 (2023) - 2022
- [j24]Atsuto Maki, Danica Kragic, Hedvig Kjellström, Hossein Azizpour, Josephine Sullivan, Mårten Björkman, Patric Jensfelt, Stefan Carlsson, Tony Lindeberg, Yngve Sundblad:
In Memoriam: Jan-Olof Eklundh. IEEE Trans. Pattern Anal. Mach. Intell. 44(9): 4488-4489 (2022) - [j23]Louise Rixon Fuchs, Atsuto Maki, Andreas Gällström:
Optimization Method for Wide Beam Sonar Transmit Beamforming. Sensors 22(19): 7526 (2022) - [c51]Miquel Martí, Sebastian Bujwid, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki:
An analysis of over-sampling labeled data in semi-supervised learning with FixMatch. NLDL 2022 - [i14]Miquel Martí i Rabadán, Sebastian Bujwid, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki:
An analysis of over-sampling labeled data in semi-supervised learning with FixMatch. CoRR abs/2201.00604 (2022) - [i13]Vladimir Li, Atsuto Maki:
Towards a Unified View of Affinity-Based Knowledge Distillation. CoRR abs/2209.15555 (2022) - [i12]Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki:
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks. CoRR abs/2210.09919 (2022) - 2020
- [j22]Atsuto Maki:
Foreword. IEICE Trans. Inf. Syst. 103-D(6): 1208 (2020) - [c50]Yang Zhong, Atsuto Maki:
Regularizing CNN Transfer Learning With Randomised Regression. CVPR 2020: 13634-13643 - [c49]Luca Marson, Vladimir Li, Atsuto Maki:
Boundary Optimised Samples Training for Detecting Out-of-Distribution Images. ICPR 2020: 10486-10492 - [c48]Marcus Nordström, Han Bao, Fredrik Löfman, Henrik Hult, Atsuto Maki, Masashi Sugiyama:
Calibrated Surrogate Maximization of Dice. MICCAI (4) 2020: 269-278
2010 – 2019
- 2019
- [j21]Atsuto Maki:
Toward principled regularization of deep networks - From weight decay to feature contraction. Sci. Robotics 4(30) (2019) - [c47]Di Feng, Xiao Wei, Lars Rosenbaum, Atsuto Maki, Klaus Dietmayer:
Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector. IV 2019: 667-674 - [i11]Di Feng, Xiao Wei, Lars Rosenbaum, Atsuto Maki, Klaus Dietmayer:
Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector. CoRR abs/1901.10609 (2019) - [i10]Yang Zhong, Atsuto Maki:
Pseudo-task Regularization for ConvNet Transfer Learning. CoRR abs/1908.05997 (2019) - [i9]Kazuhiro Fukui, Naoya Sogi, Takumi Kobayashi, Jing-Hao Xue, Atsuto Maki:
Discriminant analysis based on projection onto generalized difference subspace. CoRR abs/1910.13113 (2019) - 2018
- [j20]Mateusz Buda, Atsuto Maki, Maciej A. Mazurowski:
A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks 106: 249-259 (2018) - [c46]Vladimir Li, Atsuto Maki:
Feature Contraction: New ConvNet Regularization in Image Classification. BMVC 2018: 213 - [c45]Yang Zhong, Vladimir Li, Ryuzo Okada, Atsuto Maki:
Target Aware Network Adaptation for Efficient Representation Learning. ECCV Workshops (4) 2018: 450-467 - [i8]Yang Zhong, Vladimir Li, Ryuzo Okada, Atsuto Maki:
Target Aware Network Adaptation for Efficient Representation Learning. CoRR abs/1810.01104 (2018) - 2017
- [c44]Ali Ghadirzadeh, Atsuto Maki, Danica Kragic, Mårten Björkman:
Deep predictive policy training using reinforcement learning. IROS 2017: 2351-2358 - [i7]Ali Ghadirzadeh, Atsuto Maki, Danica Kragic, Mårten Björkman:
Deep Predictive Policy Training using Reinforcement Learning. CoRR abs/1703.00727 (2017) - [i6]Shinya Nawata, Atsuto Maki, Takashi Hikihara:
Power packet transferability via symbol propagation matrix. CoRR abs/1708.02676 (2017) - [i5]Mateusz Buda, Atsuto Maki, Maciej A. Mazurowski:
A systematic study of the class imbalance problem in convolutional neural networks. CoRR abs/1710.05381 (2017) - [i4]Miquel Martí, Atsuto Maki:
A multitask deep learning model for real-time deployment in embedded systems. CoRR abs/1711.00146 (2017) - 2016
- [j19]Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson:
Factors of Transferability for a Generic ConvNet Representation. IEEE Trans. Pattern Anal. Mach. Intell. 38(9): 1790-1802 (2016) - [j18]Virgile Hogman, Mårten Björkman, Atsuto Maki, Danica Kragic:
A Sensorimotor Learning Framework for Object Categorization. IEEE Trans. Cogn. Dev. Syst. 8(1): 15-25 (2016) - [c43]Johan Johansson, Martin Solli, Atsuto Maki:
An Evaluation of Local Feature Detectors and Descriptors for Infrared Images. ECCV Workshops (3) 2016: 711-723 - [c42]Ali Ghadirzadeh, Judith Bütepage, Atsuto Maki, Danica Kragic, Mårten Björkman:
A sensorimotor reinforcement learning framework for physical Human-Robot Interaction. IROS 2016: 2682-2688 - [i3]Ali Ghadirzadeh, Judith Bütepage, Atsuto Maki, Danica Kragic, Mårten Björkman:
A Sensorimotor Reinforcement Learning Framework for Physical Human-Robot Interaction. CoRR abs/1607.07939 (2016) - 2015
- [j17]Mikael Brudfors, Alexander Seitel, Abtin Rasoulian, Andras Lasso, Victoria A. Lessoway, Jill Osborn, Atsuto Maki, Robert N. Rohling, Purang Abolmaesumi:
Towards real-time, tracker-less 3D ultrasound guidance for spine anaesthesia. Int. J. Comput. Assist. Radiol. Surg. 10(6): 855-865 (2015) - [j16]Minh-Tri Pham, Oliver J. Woodford, Frank Perbet, Atsuto Maki, Riccardo Gherardi, Björn Stenger, Roberto Cipolla:
Distances and Means of Direct Similarities. Int. J. Comput. Vis. 112(3): 285-306 (2015) - [j15]Kazuhiro Fukui, Atsuto Maki:
Difference Subspace and Its Generalization for Subspace-Based Methods. IEEE Trans. Pattern Anal. Mach. Intell. 37(11): 2164-2177 (2015) - [c41]Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson:
From generic to specific deep representations for visual recognition. CVPR Workshops 2015: 36-45 - [c40]Ali Ghadirzadeh, Atsuto Maki, Mårten Björkman:
A sensorimotor approach for self-learning of hand-eye coordination. IROS 2015: 4969-4975 - [c39]Ali Sharif Razavian, Hossein Azizpour, Atsuto Maki, Josephine Sullivan, Carl Henrik Ek, Stefan Carlsson:
Persistent Evidence of Local Image Properties in Generic ConvNets. SCIA 2015: 249-262 - [c38]Rickard Norlander, Josef Grahn, Atsuto Maki:
Wooden Knot Detection Using ConvNet Transfer Learning. SCIA 2015: 263-274 - [c37]Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson:
Visual Instance Retrieval with Deep Convolutional Networks. ICLR (Workshop) 2015 - 2014
- [j14]Oliver J. Woodford, Minh-Tri Pham, Atsuto Maki, Frank Perbet, Björn Stenger:
Demisting the Hough Transform for 3D Shape Recognition and Registration. Int. J. Comput. Vis. 106(3): 332-341 (2014) - [c36]Ali Ghadirzadeh, Gert Kootstra, Atsuto Maki, Mårten Björkman:
Learning visual forward models to compensate for self-induced image motion. RO-MAN 2014: 1110-1115 - [i2]Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson:
From Generic to Specific Deep Representations for Visual Recognition. CoRR abs/1406.5774 (2014) - [i1]Ali Sharif Razavian, Hossein Azizpour, Atsuto Maki, Josephine Sullivan, Carl Henrik Ek, Stefan Carlsson:
Persistent Evidence of Local Image Properties in Generic ConvNets. CoRR abs/1411.6509 (2014) - 2013
- [j13]Atsuto Maki, Frank Perbet, Björn Stenger, Roberto Cipolla:
Detecting bipedal motion from correlated probabilistic trajectories. Pattern Recognit. Lett. 34(15): 1808-1818 (2013) - [p2]Minh-Tri Pham, Oliver J. Woodford, Frank Perbet, Atsuto Maki, Riccardo Gherardi, Björn Stenger, Roberto Cipolla:
Scale-Invariant Vote-Based 3D Recognition and Registration from Point Clouds. Machine Learning for Computer Vision 2013: 137-162 - 2012
- [j12]Frank Perbet, Björn Stenger, Atsuto Maki:
Homogeneous Superpixels from Markov Random Walks. IEICE Trans. Inf. Syst. 95-D(7): 1740-1748 (2012) - [c35]Oliver J. Woodford, Minh-Tri Pham, Atsuto Maki, Riccardo Gherardi, Frank Perbet, Björn Stenger:
Contraction Moves for Geometric Model Fitting. ECCV (7) 2012: 181-194 - [c34]Martin Peris, Sara Martull, Atsuto Maki, Yasuhiro Ohkawa, Kazuhiro Fukui:
Towards a simulation driven stereo vision system. ICPR 2012: 1038-1042 - [c33]Atsuto Maki, Riccardo Gherardi:
Conditional Variance of Differences: A Robust Similarity Measure for Matching and Registration. SSPR/SPR 2012: 657-665 - 2011
- [j11]Behzad Sajadi, Aditi Majumder, Kazuhiro Hiwada, Atsuto Maki, Ramesh Raskar:
Switchable primaries using shiftable layers of color filter arrays. ACM Trans. Graph. 30(4): 65 (2011) - [c32]Oliver J. Woodford, Minh-Tri Pham, Atsuto Maki, Frank Perbet, Björn Stenger:
Demisting the Hough Transform for 3D Shape Recognition and Registration. BMVC 2011: 1-11 - [c31]Minh-Tri Pham, Oliver J. Woodford, Frank Perbet, Atsuto Maki, Björn Stenger, Roberto Cipolla:
A new distance for scale-invariant 3D shape recognition and registration. ICCV 2011: 145-152 - [c30]Carlos Hernández, Frank Perbet, Minh-Tri Pham, George Vogiatzis, Oliver J. Woodford, Atsuto Maki, Björn Stenger, Roberto Cipolla:
Live 3D shape reconstruction, recognition and registration. ICCV Workshops 2011: 729 - [c29]Atsuto Maki, Akihito Seki, Tomoki Watanabe, Roberto Cipolla:
Co-occurrence flow for pedestrian detection. ICIP 2011: 1889-1892 - [c28]Frank Perbet, Atsuto Maki:
Homogeneous Superpixels from Random Walks. MVA 2011: 26-30 - 2010
- [c27]Hajime Mizuyama, Kayo Yamada, Atsuto Maki, Kazuto Tanaka:
A semiotic characterization of the process of teaching and learning a skilled motion taking wok handling as an example. IFAC HMS 2010: 448-453 - [p1]Takeshi Takai, Susumu Iino, Atsuto Maki, Takashi Matsuyama:
3-D Lighting Environment Estimation with Shading and Shadows. Image and Geometry Processing for 3-D Cinematography 2010: 239-257
2000 – 2009
- 2009
- [j10]Takeshi Takai, Atsuto Maki, Koichiro Niinuma, Takashi Matsuyama:
Difference sphere: An approach to near light source estimation. Comput. Vis. Image Underst. 113(9): 966-978 (2009) - [j9]Jonathan Starck, Atsuto Maki, Shohei Nobuhara, Adrian Hilton, Takashi Matsuyama:
The Multiple-Camera 3-D Production Studio. IEEE Trans. Circuits Syst. Video Technol. 19(6): 856-869 (2009) - [c26]Atsuto Maki, Roberto Cipolla:
Obtaining the Shape of a Moving Object with a Specular Surface. BMVC 2009: 1-10 - [c25]Frank Perbet, Björn Stenger, Atsuto Maki:
Random Forest Clustering and Application to Video Segmentation. BMVC 2009: 1-10 - [c24]Frank Perbet, Atsuto Maki, Björn Stenger:
Correlated probabilistic trajectories for pedestrian motion detection. ICCV 2009: 1647-1654 - 2008
- [c23]Tomoyuki Mukasa, Arata Miyamoto, Shohei Nobuhara, Atsuto Maki, Takashi Matsuyama:
Complex human motion estimation using visibility. FG 2008: 1-6 - [c22]Atsuto Maki, Yosuke Hatanaka, Takashi Matsuyama:
Tracking features on a moving object using local image bases. ICPR 2008: 1-5 - 2007
- [c21]Masaaki Nishino, Atsuto Maki, Takashi Matsuyama:
Phase-Based Feature Matching Under Illumination Variances. IEA/AIE 2007: 94-104 - 2006
- [c20]Tomoyuki Mukasa, Shohei Nobuhara, Atsuto Maki, Takashi Matsuyama:
Finding Articulated Body in Time-Series Volume Data. AMDO 2006: 395-404 - 2005
- [c19]Atsuto Maki:
3D Surface Reconstruction of a Moving Object in the Presence of Specular Reflection. ICIAP 2005: 867-875 - 2004
- [j8]Atsuto Maki:
Photometric subspace for multibody motion segmentation. Image Vis. Comput. 22(8): 655-662 (2004) - [j7]Atsuto Maki, Kazuhiro Fukui:
Ship identification in sequential ISAR imagery. Mach. Vis. Appl. 15(3): 149-155 (2004) - [j6]Atsuto Maki, Mutsumi Watanabe, Charles Wiles:
Geotensity constraint for 3D surface reconstruction. Syst. Comput. Jpn. 35(4): 72-83 (2004) - [c18]Takeshi Takai, Koichiro Niinuma, Atsuto Maki, Takashi Matsuyama:
Difference Sphere: An Approach to Near Light Source Estimation. CVPR (1) 2004: 98-105 - 2003
- [c17]Akiko Nakashima, Atsuto Maki:
Synthesizing pose and lighting variation from object motion. ICIP (3) 2003: 725-728 - [c16]Kazuhiro Hiwada, Atsuto Maki, Akiko Nakashima:
Mimicking video: real-time morphable 3D model fitting. VRST 2003: 132-139 - 2002
- [j5]Atsuto Maki, Mutsumi Watanabe, Charles Wiles:
Geotensity: Combining Motion and Lighting for 3D Surface Reconstruction. Int. J. Comput. Vis. 48(2): 75-90 (2002) - [c15]Akiko Nakashima, Atsuto Maki, Kazuhiro Fukui:
Constructing Illumination Image Basis from Object Motion. ECCV (3) 2002: 195-209 - [c14]Ryuzo Okada, Atsuto Maki, Yasuhiro Taniguchi, Kazunori Onoguchi:
Temporally Evaluated Optical Flow: Study on Accuracy. ICPR (1) 2002: 343-347 - 2001
- [j4]Charles Wiles, Atsuto Maki, Natsuko Matsuda:
Hyperpatches for 3D Model Acquisition and Tracking. IEEE Trans. Pattern Anal. Mach. Intell. 23(12): 1391-1403 (2001) - [c13]Atsuto Maki, Hiroshi Hattori:
Illumination Subspace for Multibody Motion Segmentation. CVPR (2) 2001: 11-17 - [c12]Atsuto Maki, Kazuhiro Fukui, Kazunori Onoguchi, Ken-ichi Maeda:
ISAR Image Analysis by Subspace Method: Automatic Extraction and Identification of Ship Profile. ICIAP 2001: 523-528 - 2000
- [j3]Atsuto Maki, Peter Nordlund, Jan-Olof Eklundh:
Attentional Scene Segmentation: Integrating Depth and Motion. Comput. Vis. Image Underst. 78(3): 351-373 (2000) - [j2]Atsuto Maki:
Estimation of illuminant direction and surface reconstruction by Geotensity constraint. Pattern Recognit. Lett. 21(13-14): 1115-1123 (2000) - [c11]Hiroshi Hattori, Atsuto Maki:
Stereo without Depth Search and Metric Calibration. CVPR 2000: 1177- - [c10]Atsuto Maki, Charles Wiles:
Geotensity Constraint for 3D Surface Reconstruction under Multiple Light Sources. ECCV (1) 2000: 725-741
1990 – 1999
- 1998
- [c9]Hiroshi Hattori, Atsuto Maki:
Stereo Matching with Direct Surface Orientation Recovery. BMVC 1998: 1-11 - [c8]Atsuto Maki, Mutsumi Watanabe, Charles Wiles:
Geotensity: Combining Motion and Lighting for 3D Surface Reconstruction. ICCV 1998: 1053-1060 - 1997
- [c7]Charles Wiles, Atsuto Maki, Natsuko Matsuda, Mutsumi Watanabe:
Hyper-patches for 3D model acquisition and tracking. CVPR 1997: 1074-1080 - 1996
- [c6]Atsuto Maki, Peter Nordlund, Jan-Olof Eklundh:
A computational model of depth-based attention. ICPR 1996: 734-739 - [c5]Atsuto Maki, Tomas Uhlin, Jan-Olof Eklundh:
A Direct Disparity Estimation Technique for Depth Segmentation. MVA 1996: 530-533 - 1995
- [j1]Atsuto Maki, Tomas Uhlin:
Disparity Selection in Binocular Pursuit. IEICE Trans. Inf. Syst. 78-D(12): 1591-1597 (1995) - [c4]Jan-Olof Eklundh, Tomas Uhlin, Peter Nordlund, Atsuto Maki:
Developing an Active Observer. ACCV 1995: 181-190 - [c3]Atsuto Maki, Lars Bretzner, Jan-Olof Eklundh:
Local Fourir Phase and Disparity Estimates: An Analytical Study. CAIP 1995: 868-873 - [c2]Tomas Uhlin, Peter Nordlund, Atsuto Maki, Jan-Olof Eklundh:
Towards an Active Visual Observer. ICCV 1995: 679-686 - 1994
- [c1]Atsuto Maki, Tomas Uhlin, Jan-Olof Eklundh:
Disparity Selection in Binocular Pursuit. MVA 1994: 182-185
Coauthor Index
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.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from , , and to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-07 22:10 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint