Josef Šivic

Adobe Systems (United States) — United States

Computer Science · Physical Sciences

74h-index31.7kcitations262works3.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Image and Video Retrieval Techniques(89), Human Pose and Action Recognition(63), Multimodal Machine Learning Applications(60), Robotics and Sensor-Based Localization(46), Advanced Vision and Imaging(40)

Publications262 total

MARTS-DB: a database of mechanisms and reactions of terpene synthases
BMC Bioinformatics·2025Open Access
Generalization Beyond Benchmarks: Evaluating Learnable Protein-Ligand Scoring Functions on Unseen Targets
arXiv (Cornell University)·2025Open Access
BoltzGen: Toward Universal Binder Design
2025· 10 citedOpen Access
Quantum computing for faster enzyme discovery and engineering
Nature Catalysis·2025· 3 cited
ResidualViT for Efficient Temporally Dense Video Encoding
arXiv (Cornell University)·2025Open Access
Taurine Inhibits Apolipoprotein E4 Aggregation
2025Open Access
EditDuet: A Multi-Agent System for Video Non-Linear Editing
2025Open Access
Improving Personalized Search with Regularized Low-Rank Parameter Updates
arXiv (Cornell University)·2025Open Access
Improving Personalized Search with Regularized Low-Rank Parameter Updates
2025
Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS
Nature Biotechnology·2025· 27 citedOpen Access
Multi-step manipulation task and motion planning guided by video demonstration
arXiv (Cornell University)·2025Open Access
Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS
2025· 5 citedOpen Access
PhysPose: Refining 6D Object Poses with Physical Constraints
arXiv (Cornell University)·2025Open Access
Large-scale Pre-training for Grounded Video Caption Generation
arXiv (Cornell University)·2025Open Access
6D Object Pose Tracking in Internet Videos for Robotic Manipulation
arXiv (Cornell University)·2025Open Access
Emergence of molecular structures from repository-scale self-supervised learning on tandem mass spectra
2025· 2 citedOpen Access
Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation
International Journal of Computer Vision·2025· 4 citedOpen Access
Learning to engineer protein flexibility
arXiv (Cornell University)·2024· 1 citedOpen Access
Temporally Consistent Object 6D Pose Estimation for Robot Control
IEEE Robotics and Automation Letters·2024· 2 cited
Generative Timelines for Instructed Visual Assembly
arXiv (Cornell University)·2024Open Access
page 1 of 14Next →

Frequent Co-authors

Andrew Zisserman(17), Ivan Laptev(14), Tomáš Pajdla(11), Akihiko Torii(10), Relja Arandjelović(6), Bryan Russell(6), Alexei A. Efros(6), Masatoshi Okutomi(6), Marc Pollefeys(5), Torsten Sattler(5), James Philbin(4), Michael Isard(4), Ignacio Rocco(4), Antoine Miech(4), Mark Everingham(4), Jean Ponce(4), Ondřej Chum(3), William T. Freeman(3), Oliver Whyte(3), Cordelia Schmid(3)