Pavel Tokmakov

71 papers A* 18A 1Misc 1Journal 40Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A careful examination of large behavior models for multitask dexterous manipulation. Sci. Robotics Jose A. Barreiros, Andrew Beaulieu, Aditya Bhat, Rick Cory, Eric Cousineau, Hongkai Dai, Ching-Hsin Fang, Kunimatsu Hashimoto, Muhammad Zubair Irshad, Masha Itkina, Naveen Kuppuswamy, Kuan-Hui Lee, Katherine Liu, Dale McConachie, Ian McMahon, Haruki Nishimura, Calder Phillips-Grafflin, Charles Richter, Paarth Shah, Krishnan Srinivasan, Blake Wulfe, Chen Xu, Mengchao Zhang, Alex Alspach, Maya Angeles, Kushal Arora, Vitor Campagnolo Guizilini, Alejandro M. Castro, Dian Chen, Ting-Sheng Chu, Sam Creasey, Sean Curtis, Richard Denitto, Emma Dixon, Eric Dusel, Matthew Ferreira, Aimee Goncalves, Grant Gould, Damrong Guoy, Swati Gupta, Xuchen Han, Kyle Hatch, Brendan Hathaway, Allison Henry, Hillel Hochsztein, Phoebe Horgan, Shun Iwase, Donovon Jackson, Siddharth Karamcheti, Sedrick Keh, Joseph Masterjohn, Masayuki Masuda, Jean Mercat, Patrick Tree Miller, Paul Mitiguy, Tony Nguyen, Jeremy Nimmer, Yuki Noguchi, Reko Ong, Aykut Özgün Önol, Owen Pfannenstiehl, Richard Poyner, Leticia Priebe Rocha, Gordon Richardson, Christopher Rodriguez, Derick Seale, Michael A. Sherman, Mariah Smith-Jones, David Tago, Pavel Tokmakov, Matthew Tran, Basile Van Hoorick, Igor Vasiljevic, Sergey Zakharov, Mark Zolotas, Rares Ambrus, Kerri Fetzer-Borelli, Benjamin Burchfiel, Hadas Kress-Gazit, Siyuan Feng, Stacie Ford, Russ Tedrake
2026	J	`jnl`	AnyView: Synthesizing Any Novel View in Dynamic Scenes. CoRR Basile Van Hoorick, Dian Chen, Shun Iwase, Pavel Tokmakov, Muhammad Zubair Irshad, Igor Vasiljevic, Swati Gupta, Fangzhou Cheng, Sergey Zakharov, Vitor Campagnolo Guizilini
2026	J	`jnl`	Capturing Visual Environment Structure Correlates with Control Performance. CoRR Jiahua Dong, Yunze Man, Pavel Tokmakov, Yu-Xiong Wang
2026	J	`jnl`	Walk through Paintings: Egocentric World Models from Internet Priors. CoRR Anurag Bagchi, Zhipeng Bao, Homanga Bharadhwaj, Yu-Xiong Wang, Pavel Tokmakov, Martial Hebert
2025	J	`jnl`	AllTracker: Efficient Dense Point Tracking at High Resolution. CoRR Adam W. Harley, Yang You, Xinglong Sun, Yang Zheng, Nikhil Raghuraman, Yunqi Gu, Sheldon Liang, Wen-Hsuan Chu, Achal Dave, Pavel Tokmakov, Suya You, Rares Ambrus, Katerina Fragkiadaki, Leonidas J. Guibas
2025	J	`jnl`	AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis. CoRR Junjie Ye, Rong Xue, Basile Van Hoorick, Pavel Tokmakov, Muhammad Zubair Irshad, Yue Wang, Vitor Guizilini
2025	—	`conf`	GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion. 3DV Vitor Guizilini, Pavel Tokmakov, Achal Dave, Rares Ambrus
2025	J	`jnl`	Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors. CoRR Wen-Hsuan Chu, Lei Ke, Jianmeng Liu, Mingxiao Huo, Pavel Tokmakov, Katerina Fragkiadaki
2025	A*	`conf`	Robust Multi-Object 4D Generation for In-the-wild Videos. CVPR Wen-Hsuan Chu, Lei Ke, Jianmeng Liu, Mingxiao Huo, Pavel Tokmakov, Katerina Fragkiadaki
2025	—	`conf`	The Third Visual Object Tracking Segmentation VOTS2025 Challenge Results. ICCVW Matei Kristan, Jirí Matas, Pavel Tokmakov, Alan Lukezic, Michael Felsberg, Luka Cehovin Zajc, Khanh-Tung Tran, Xuan-Son Vu, Johanna Björklund, Michal Neoral, Hyung Jin Chang, Gustavo Fernández, Minasadat Attari, Matteo Dunnhofer, Wei Feng, Zhenhua Feng, Jin Gao, Yameng Gu, Ruize Han, Jiawei He, Zhenyu He, Junhui Hou, Weiming Hu, Xiantao Hu, Xingsen Huang, Yuqing Huang, Gleb Kirichenko, Josef Kittler, Yutong Kou, Simiao Lai, Bing Li, Xin Li, Shubo Lin, Huchuan Lu, Deshui Miao, Christian Micheloni, Juan David Mogollon, Moritz Nottebaum, Kannappan Palaniappan, Ziqi Pang, Zekun Qian, Gani Rahmon, Aleksandr Romanov, Liangtao Shi, Roman A. Solovyev, Elham Soltani Kazemi, Imad Eddine Toubal, Jovana Videnovic, Dong Wang, Yaowei Wang, Yu-Xiong Wang, Zhixiang Wang, Xiaojun Wu, Jinxia Xie, Tianyang Xu, Chaocan Xue, Yuanliang Xue, Ming-Hsuan Yang, Dmitriy Yurtov, Chunui Zhang, Xiangqun Zhang, Yunfei Zhang, Qingfang Zheng, Bineng Zhong, Fuan Zhong, Jinglin Zhou, Jingmeng Zhou, Junbao Zhou, Yong Zhou, Xuefeng Zhu
2025	A*	`conf`	Understanding Complexity in VideoQA via Visual Program Generation. ICML Cristóbal Eyzaguirre, Igor Vasiljevic, Achal Dave, Jiajun Wu, Rares Andrei Ambrus, Thomas Kollar, Juan Carlos Niebles, Pavel Tokmakov
2025	J	`jnl`	Understanding Complexity in VideoQA via Visual Program Generation. CoRR Cristóbal Eyzaguirre, Igor Vasiljevic, Achal Dave, Jiajun Wu, Rares Andrei Ambrus, Thomas Kollar, Juan Carlos Niebles, Pavel Tokmakov
2025	J	`jnl`	Video Generators are Robot Policies. CoRR Junbang Liang, Pavel Tokmakov, Ruoshi Liu, Sruthi Sudhakar, Paarth Shah, Rares Ambrus, Carl Vondrick
2024	Misc	`conf`	Dreamitate: Real-World Visuomotor Policy Learning via Video Generation. CoRL Junbang Liang, Ruoshi Liu, Ege Ozguroglu, Sruthi Sudhakar, Achal Dave, Pavel Tokmakov, Shuran Song, Carl Vondrick
2024	J	`jnl`	Dreamitate: Real-World Visuomotor Policy Learning via Video Generation. CoRR Junbang Liang, Ruoshi Liu, Ege Ozguroglu, Sruthi Sudhakar, Achal Dave, Pavel Tokmakov, Shuran Song, Carl Vondrick
2024	J	`jnl`	GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion. CoRR Vitor Guizilini, Pavel Tokmakov, Achal Dave, Rares Ambrus
2024	—	`conf`	Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis. ECCV (24) Basile Van Hoorick, Rundi Wu, Ege Ozguroglu, Kyle Sargent, Ruoshi Liu, Pavel Tokmakov, Achal Dave, Changxi Zheng, Carl Vondrick
2024	J	`jnl`	Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis. CoRR Basile Van Hoorick, Rundi Wu, Ege Ozguroglu, Kyle Sargent, Ruoshi Liu, Pavel Tokmakov, Achal Dave, Changxi Zheng, Carl Vondrick
2024	J	`jnl`	ReferEverything: Towards Segmenting Everything We Can Speak of in Videos. CoRR Anurag Bagchi, Zhipeng Bao, Yu-Xiong Wang, Pavel Tokmakov, Martial Hebert
2024	—	`conf`	The Second Visual Object Tracking Segmentation VOTS2024 Challenge Results. ECCV Workshops (7) Matej Kristan, Jirí Matas, Pavel Tokmakov, Michael Felsberg, Luka Cehovin Zajc, Alan Lukezic, Khanh-Tung Tran, Xuan-Son Vu, Johanna Björklund, Hyung Jin Chang, Gustavo Fernández, Minasadat Attari, Antoni B. Chan, Liang Chen, Xin Chen, Jaired Collins, Yutao Cui, Ganesh Sai Manas Devarapu, Yinglong Du, Heng Fan, Wan-Cyuan Fan, Zhenhua Feng, Mingqi Gao, Rama Krishna Sai S. Gorthi, Raghav Goyal, Jungong Han, Bijaya Kumar Hatuwal, Zhenyu He, Xiantao Hu, Xingsen Huang, Yuqing Huang, Dongmei Jiang, Ben Kang, Kannappan Palaniappan, Josef Kittler, Simiao Lai, Ning Li, Xiaohai Li, Xin Li, Cheng Liang, Liting Lin, Haibin Ling, Ting Liu, Ziquan Liu, Huchuan Lu, Yifei Luo, Deshui Miao, Juan David Mogollon, Ziqi Pang, Jaswanth Reddy Pochimireddy, Viktor Prutyanov, Gani Rahmon, Aleksandr Romanov, Liangtao Shi, Mennatullah Siam, Leonid Sigal, Arun Kumar Sivapuram, Roman A. Solovyev, Elham Soltani Kazemi, Imad Eddine Toubal, Jia Wan, Limin Wang, Xinying Wang, Yaowei Wang, Yu-Xiong Wang, Zhiquan Wang, Gangshan Wu, Qiangqiang Wu, Xiaojun Wu, Zihao Xia, Jinxia Xie, Chenlong Xu, Tianyang Xu, Yong Xu, Chaocan Xue, Chao Yang, Jinyu Yang, Ming-Hsuan Yang, Chenyang Yu, Ke Yu, Chunhui Zhang, Jiaming Zhang, Zhipeng Zhang, Feng Zheng, Yaozong Zheng, Bineng Zhong, Jinglin Zhou, Junbao Zhou, Yong Zhou, Zikun Zhou, Guibo Zhu, Jiawen Zhu, Xuefeng Zhu, Vladimir V. Zunin
2024	A*	`conf`	Understanding Video Transformers via Universal Concept Discovery. CVPR Matthew Kowal, Achal Dave, Rares Ambrus, Adrien Gaidon, Konstantinos G. Derpanis, Pavel Tokmakov
2024	J	`jnl`	Understanding Video Transformers via Universal Concept Discovery. CoRR Matthew Kowal, Achal Dave, Rares Ambrus, Adrien Gaidon, Konstantinos G. Derpanis, Pavel Tokmakov
2024	A*	`conf`	Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models. ICRA Wen-Hsuan Chu, Adam W. Harley, Pavel Tokmakov, Achal Dave, Leonidas J. Guibas, Katerina Fragkiadaki
2024	A*	`conf`	pix2gestalt: Amodal Segmentation by Synthesizing Wholes. CVPR Ege Ozguroglu, Ruoshi Liu, Dídac Surís, Dian Chen, Achal Dave, Pavel Tokmakov, Carl Vondrick
2024	J	`jnl`	pix2gestalt: Amodal Segmentation by Synthesizing Wholes. CoRR Ege Ozguroglu, Ruoshi Liu, Dídac Surís, Dian Chen, Achal Dave, Pavel Tokmakov, Carl Vondrick
2023	A*	`conf`	Breaking the "Object" in Video Object Segmentation. CVPR Pavel Tokmakov, Jie Li, Adrien Gaidon
2023	A*	`conf`	Object Discovery from Motion-Guided Tokens. CVPR Zhipeng Bao, Pavel Tokmakov, Yu-Xiong Wang, Adrien Gaidon, Martial Hebert
2023	J	`jnl`	Object Discovery from Motion-Guided Tokens. CoRR Zhipeng Bao, Pavel Tokmakov, Yu-Xiong Wang, Adrien Gaidon, Martial Hebert
2023	A*	`conf`	Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking. CVPR Ziqi Pang, Jie Li, Pavel Tokmakov, Dian Chen, Sergey Zagoruyko, Yu-Xiong Wang
2023	J	`jnl`	Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking. CoRR Ziqi Pang, Jie Li, Pavel Tokmakov, Dian Chen, Sergey Zagoruyko, Yu-Xiong Wang
2023	A*	`conf`	Tracking Through Containers and Occluders in the Wild. CVPR Basile Van Hoorick, Pavel Tokmakov, Simon Stent, Jie Li, Carl Vondrick
2023	J	`jnl`	Tracking through Containers and Occluders in the Wild. CoRR Basile Van Hoorick, Pavel Tokmakov, Simon Stent, Jie Li, Carl Vondrick
2023	A*	`conf`	Zero-1-to-3: Zero-shot One Image to 3D Object. ICCV Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, Carl Vondrick
2023	J	`jnl`	Zero-1-to-3: Zero-shot One Image to 3D Object. CoRR Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, Carl Vondrick
2023	J	`jnl`	Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models. CoRR Wen-Hsuan Chu, Adam W. Harley, Pavel Tokmakov, Achal Dave, Leonidas J. Guibas, Katerina Fragkiadaki
2022	J	`jnl`	Breaking the "Object" in Video Object Segmentation. CoRR Pavel Tokmakov, Jie Li, Adrien Gaidon
2022	A*	`conf`	Discovering Objects that Can Move. CVPR Zhipeng Bao, Pavel Tokmakov, Allan Jabri, Yu-Xiong Wang, Adrien Gaidon, Martial Hebert
2022	J	`jnl`	Discovering Objects that Can Move. CoRR Zhipeng Bao, Pavel Tokmakov, Allan Jabri, Yu-Xiong Wang, Adrien Gaidon, Martial Hebert
2022	A	`conf`	Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty. IROS Boris Ivanovic, Kuan-Hui Lee, Pavel Tokmakov, Blake Wulfe, Rowan McAllister, Adrien Gaidon, Marco Pavone
2022	A*	`conf`	Object Permanence Emerges in a Random Walk along Memory. ICML Pavel Tokmakov, Allan Jabri, Jie Li, Adrien Gaidon
2022	J	`jnl`	Object Permanence Emerges in a Random Walk along Memory. CoRR Pavel Tokmakov, Allan Jabri, Jie Li, Adrien Gaidon
2021	J	`jnl`	Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty. CoRR Boris Ivanovic, Kuan-Hui Lee, Pavel Tokmakov, Blake Wulfe, Rowan McAllister, Adrien Gaidon, Marco Pavone
2021	A*	`conf`	Learning to Track with Object Permanence. ICCV Pavel Tokmakov, Jie Li, Wolfram Burgard, Adrien Gaidon
2021	J	`jnl`	Learning to Track with Object Permanence. CoRR Pavel Tokmakov, Jie Li, Wolfram Burgard, Adrien Gaidon
2021	—	`conf`	Unlocking the Full Potential of Small Data With Diverse Supervision. CVPR Workshops Ziqi Pang, Zhiyuan Hu, Pavel Tokmakov, Yu-Xiong Wang, Martial Hebert
2020	—	`conf`	TAO: A Large-Scale Benchmark for Tracking Any Object. ECCV (5) Achal Dave, Tarasha Khurana, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan
2020	J	`jnl`	TAO: A Large-Scale Benchmark for Tracking Any Object. CoRR Achal Dave, Tarasha Khurana, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan
2020	—	`conf`	Unsupervised Learning of Video Representations via Dense Trajectory Clustering. ECCV Workshops (2) Pavel Tokmakov, Martial Hebert, Cordelia Schmid
2020	J	`jnl`	Unsupervised Learning of Video Representations via Dense Trajectory Clustering. CoRR Pavel Tokmakov, Martial Hebert, Cordelia Schmid
2019	A*	`conf`	A Structured Model for Action Detection. CVPR Yubo Zhang, Pavel Tokmakov, Martial Hebert, Cordelia Schmid
2019	J	`jnl`	A Study on Action Detection in the Wild. CoRR Yubo Zhang, Pavel Tokmakov, Martial Hebert, Cordelia Schmid
2019	A*	`conf`	Learning Compositional Representations for Few-Shot Recognition. ICCV Pavel Tokmakov, Yu-Xiong Wang, Martial Hebert
2019	J	`jnl`	Learning Generalizable Representations via Diverse Supervision. CoRR Ziqi Pang, Zhiyuan Hu, Pavel Tokmakov, Yu-Xiong Wang, Martial Hebert
2019	J	`jnl`	Learning to Segment Moving Objects. Int. J. Comput. Vis. Pavel Tokmakov, Cordelia Schmid, Karteek Alahari
2019	J	`jnl`	Learning to Track Any Object. CoRR Achal Dave, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan
2019	A*	`conf`	Towards Latent Attribute Discovery From Triplet Similarities. ICCV Ishan Nigam, Pavel Tokmakov, Deva Ramanan
2019	—	`conf`	Towards Segmenting Anything That Moves. ICCV Workshops Achal Dave, Pavel Tokmakov, Deva Ramanan
2019	J	`jnl`	Towards Segmenting Everything That Moves. CoRR Achal Dave, Pavel Tokmakov, Deva Ramanan
2018	J	`jnl`	A Structured Model For Action Detection. CoRR Yubo Zhang, Pavel Tokmakov, Cordelia Schmid, Martial Hebert
2018	J	`jnl`	Learning Compositional Representations for Few-Shot Recognition. CoRR Pavel Tokmakov, Yu-Xiong Wang, Martial Hebert
2018	—	`—`	Learning from motion. (Apprentissage à partir du mouvement). Pavel Tokmakov
2017	A*	`conf`	Learning Motion Patterns in Videos. CVPR Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
2017	A*	`conf`	Learning Video Object Segmentation with Visual Memory. ICCV Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
2017	J	`jnl`	Learning Video Object Segmentation with Visual Memory. CoRR Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
2017	J	`jnl`	Learning to Segment Moving Objects. CoRR Pavel Tokmakov, Cordelia Schmid, Karteek Alahari
2017	J	`jnl`	Relational linear programming. Artif. Intell. Kristian Kersting, Martin Mladenov, Pavel Tokmakov
2016	J	`jnl`	Learning Motion Patterns in Videos. CoRR Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
2016	—	`conf`	Weakly-Supervised Semantic Segmentation Using Motion Cues. ECCV (4) Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
2016	J	`jnl`	Weakly-Supervised Semantic Segmentation using Motion Cues. CoRR Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
2014	J	`jnl`	Relational Linear Programs. CoRR Kristian Kersting, Martin Mladenov, Pavel Tokmakov
2013	—	`conf`	One click mining: interactive local pattern discovery through implicit preference and performance learning. IDEA@KDD Mario Boley, Michael Mampaey, Bo Kang, Pavel Tokmakov, Stefan Wrobel