Pavel Tokmakov

Computer Science · Physical Sciences

15h-index1.8kcitations81works1.52yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(23), Video Surveillance and Tracking Methods(21), Advanced Vision and Imaging(21), Advanced Neural Network Applications(15), Advanced Image and Video Retrieval Techniques(13)

Publications81 total

Capturing Visual Environment Structure Correlates with Control Performance
ArXiv.org·2026Open Access
Capturing Visual Environment Structure Correlates with Control Performance
arXiv (Cornell University)·2026Open Access
AnyView: Synthesizing Any Novel View in Dynamic Scenes
arXiv (Cornell University)·2026Open Access
AnyView: Synthesizing Any Novel View in Dynamic Scenes
ArXiv.org·2026Open Access
Walk through Paintings: Egocentric World Models from Internet Priors
arXiv (Cornell University)·2026Open Access
Walk through Paintings: Egocentric World Models from Internet Priors
ArXiv.org·2026Open Access
The Third Visual Object Tracking Segmentation VOTS2025 Challenge Results
2025
Video Generators are Robot Policies
arXiv (Cornell University)·2025Open Access
A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation
arXiv (Cornell University)·2025Open Access
Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors
arXiv (Cornell University)·2025Open Access
Robust Multi-Object 4D Generation for In-the-wild Videos
2025
AllTracker: Efficient Dense Point Tracking at High Resolution
arXiv (Cornell University)·2025Open Access
Understanding Complexity in VideoQA via Visual Program Generation
arXiv (Cornell University)·2025Open Access
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion
2025
The Second Visual Object Tracking Segmentation VOTS2024 Challenge Results
Lecture notes in computer science·2025· 2 cited
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
Lecture notes in computer science·2024· 3 cited
ReferEverything: Towards Segmenting Everything We Can Speak of in Videos
arXiv (Cornell University)·2024Open Access
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion
arXiv (Cornell University)·2024Open Access
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation
arXiv (Cornell University)·2024Open Access
pix2gestalt: Amodal Segmentation by Synthesizing Wholes
2024· 17 cited
page 1 of 5Next →

Frequent Co-authors

Cordelia Schmid(17), Martial Hebert(10), Achal Dave(10), Karteek Alahari(9), Adrien Gaidon(9), Basile Van Hoorick(6), Yu-Xiong Wang(6), Ziqi Pang(5), Deva Ramanan(5), Ruoshi Liu(4), Carl Vondrick(4), Jie Li(4), Rundi Wu(3), Yubo Zhang(3), Dian Chen(3), Rareş Ambruş(3), Sergey Zakharov(2), Carl Vondrick(2), Sergey Zagoruyko(2), Boris Ivanovic(2)