PT
Pavel Tokmakov
cs.CVcs.ROcs.LGcs.AIcs.GRcs.LOcs.PLeess.IVmath.OC
On Valency
published · living versionsW_rpzhv4hz·v1 · currentpublished
GPWM: Modeling the World as 3D Particle Motion
with Robert Ren, Matthew Bronars, He Zhu, Yikai Tang +3
1 version
Preprints & journals
40 papers in the corpus · 2014–2026What 30,000 Hours of Ego-centric Video Does Not Teach2610.12464v1 · Jiahua Dong, Anurag Bagchi, Yash Jangir et al.2026 · 0 citationsarXiv
UniGen-AR: Unifying Visual Generation with Auto-Regressive Modeling2607.24157v1 · Zhipeng Bao, Zhen Zhu, Nupur Kumari et al.2026 · 0 citationsarXiv
Robot Critics that Sweat the Small Stuff2606.21572v1 · Sruthi Sudhakar, Junbang Liang, Sreehari Rammohan et al.2026 · 0 citationsarXiv
RoboDream: Compositional World Models for Scalable Robot Data Synthesis2606.02577v1 · Junjie Ye, Rong Xue, Basile Van Hoorick et al.2026 · 0 citationsarXiv
A careful examination of large behavior models for multitask dexterous manipulation.41984998 · Barreiros, Jose, Beaulieu, Andrew, Bhat, Aditya et al.2026 · 9 citationsScience robotics. 2026;11(113):eaea6201
Capturing Visual Environment Structure Correlates with Control Performance2602.04880v1 · Jiahua Dong, Yunze Man, Pavel Tokmakov et al.2026 · 0 citationsarXiv
AnyView: Synthesizing Any Novel View in Dynamic Scenes2601.16982v2 · Basile Van Hoorick, Dian Chen, Shun Iwase et al.2026 · 0 citationsarXiv
Walk through Paintings: Egocentric World Models from Internet Priors2601.15284v2 · Anurag Bagchi, Zhipeng Bao, Homanga Bharadhwaj et al.2026 · 2 citationsarXiv
Video Generators are Robot Policies2508.00795v1 · Junbang Liang, Pavel Tokmakov, Ruoshi Liu et al.2025 · 0 citationsarXiv
Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors2506.12716v1 · Wen-Hsuan Chu, Lei Ke, Jianmeng Liu et al.2025 · 0 citationsarXiv
Understanding Complexity in VideoQA via Visual Program Generation2505.13429v1 · Cristobal Eyzaguirre, Igor Vasiljevic, Achal Dave et al.2025 · 0 citationsarXiv
ReferEverything: Towards Segmenting Everything We Can Speak of in Videos2410.23287v2 · Anurag Bagchi, Zhipeng Bao, Yu-Xiong Wang et al.2024 · 3 citationsarXiv
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion2409.09896v1 · Vitor Guizilini, Pavel Tokmakov, Achal Dave et al.2024 · 0 citationsarXiv
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation2406.16862v1 · Junbang Liang, Ruoshi Liu, Ege Ozguroglu et al.2024 · 1 citationarXiv
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis2405.14868v2 · Basile Van Hoorick, Rundi Wu, Ege Ozguroglu et al.2024 · 30 citationsarXiv
pix2gestalt: Amodal Segmentation by Synthesizing Wholes2401.14398v1 · Ege Ozguroglu, Ruoshi Liu, D'idac Sur'is et al.2024 · 43 citationsarXiv
Understanding Video Transformers via Universal Concept Discovery2401.10831v3 · Matthew Kowal, Achal Dave, Rares Ambrus et al.2024 · 9 citationsarXiv
Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models2310.06992v2 · Wen-Hsuan Chu, Adam W. Harley, Pavel Tokmakov et al.2023 · 9 citationsarXiv
Tracking through Containers and Occluders in the Wild2305.03052v1 · Basile Van Hoorick, Pavel Tokmakov, Simon Stent et al.2023 · 13 citationsarXiv
Object Discovery from Motion-Guided Tokens2303.15555v1 · Zhipeng Bao, Pavel Tokmakov, Yu-Xiong Wang et al.2023 · 12 citationsCVPR 2023
Zero-1-to-3: Zero-shot One Image to 3D Object2303.11328v1 · Ruoshi Liu, Rundi Wu, Basile Van Hoorick et al.2023 · 858 citationsarXiv
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking2302.03802v2 · Ziqi Pang, Jie Li, Pavel Tokmakov et al.2023 · 66 citationsarXiv
Breaking the "Object" in Video Object Segmentation2212.06200v2 · Pavel Tokmakov, Jie Li, Adrien Gaidon2022 · 34 citationsarXiv
Object Permanence Emerges in a Random Walk along Memory2204.01784v2 · Pavel Tokmakov, Allan Jabri, Jie Li et al.2022 · 12 citationsarXiv
Discovering Objects that Can Move2203.10159v1 · Zhipeng Bao, Pavel Tokmakov, Allan Jabri et al.2022 · 34 citationsarXiv
Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty2104.12446v2 · Boris Ivanovic, Kuan-Hui Lee, Pavel Tokmakov et al.2021 · 43 citationsarXiv
Learning to Track with Object Permanence2103.14258v2 · Pavel Tokmakov, Jie Li, Wolfram Burgard et al.2021 · 226 citationsarXiv
Unsupervised Learning of Video Representations via Dense Trajectory Clustering2006.15731v1 · Pavel Tokmakov, Martial Hebert, Cordelia Schmid2020 · 22 citationsarXiv
TAO: A Large-Scale Benchmark for Tracking Any Object2005.10356v1 · Achal Dave, Tarasha Khurana, Pavel Tokmakov et al.2020 · 165 citationsarXiv
Unlocking the Full Potential of Small Data with Diverse Supervision1911.12911v3 · Ziqi Pang, Zhiyuan Hu, Pavel Tokmakov et al.2019 · 1 citationarXiv
Learning to Track Any Object1910.11844v1 · Achal Dave, Pavel Tokmakov, Cordelia Schmid et al.2019 · 7 citationsarXiv
A Study on Action Detection in the Wild1904.12993v2 · Yubo Zhang, Pavel Tokmakov, Martial Hebert et al.2019 · 15 citationsarXiv
Towards Segmenting Anything That Moves1902.03715v4 · Achal Dave, Pavel Tokmakov, Deva Ramanan2019 · 84 citationsarXiv
Learning Compositional Representations for Few-Shot Recognition1812.09213v3 · Pavel Tokmakov, Yu-Xiong Wang, Martial Hebert2018 · 124 citationsarXiv
A Structured Model For Action Detection1812.03544v5 · Yubo Zhang, Pavel Tokmakov, Martial Hebert et al.2018 · 101 citationsarXiv
Learning to Segment Moving Objects1712.01127v1 · Pavel Tokmakov, Cordelia Schmid, Karteek Alahari2017 · 93 citationsarXiv
Learning Video Object Segmentation with Visual Memory1704.05737v2 · Pavel Tokmakov, Karteek Alahari, Cordelia Schmid2017 · 347 citationsarXiv
Learning Motion Patterns in Videos1612.07217v2 · Pavel Tokmakov, Karteek Alahari, Cordelia Schmid2016 · 273 citationsarXiv
Weakly-Supervised Semantic Segmentation using Motion Cues1603.07188v3 · Pavel Tokmakov, Karteek Alahari, Cordelia Schmid2016 · 45 citationsarXiv
Relational Linear Programs1410.3125v1 · Kristian Kersting, Martin Mladenov, Pavel Tokmakov2014 · 1 citationarXiv
Career total: 53 works. 40 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.