Tomáš Souček

Computer Science · Physical Sciences

16h-index568citations36works6.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Multimodal Machine Learning Applications(24), Advanced Image and Video Retrieval Techniques(20), Video Analysis and Summarization(20), Domain Adaptation and Few-Shot Learning(7), Human Pose and Action Recognition(6)

Publications36 total

Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
arXiv (Cornell University)·2025Open Access
Geometric Image Synchronization with Deep Watermarking
arXiv (Cornell University)·2025Open Access
ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions
2025· 1 cited
6D Object Pose Tracking in Internet Videos for Robotic Manipulation
arXiv (Cornell University)·2025Open Access
ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions
arXiv (Cornell University)·2024Open Access
TransNet V2: An Effective Deep Network Architecture for Fast Shot Transition Detection
2024· 34 citedOpen Access
GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos
2024· 6 cited
Multi-Task Learning of Object States and State-Modifying Actions From Web Videos
IEEE Transactions on Pattern Analysis and Machine Intelligence·2024· 7 cited
GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos
arXiv (Cornell University)·2023Open Access
Multi-Task Learning of Object State Changes from Uncurated Videos
arXiv (Cornell University)·2022· 4 citedOpen Access
Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 17 cited
Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos
arXiv (Cornell University)·2022· 2 citedOpen Access
Video Search with Context-Aware Ranker and Relevance Feedback
Lecture notes in computer science·2022· 15 cited
Enhanced SOMHunter for Known-item Search in Lifelog Data
2021· 18 cited
Is the Reign of Interactive Search Eternal? Findings from the Video Browser Showdown 2020
ACM Transactions on Multimedia Computing Communications and Applications·2021· 56 citedOpen Access
On the User-Centric Comparative Remote Evaluation of Interactive Video Search Systems
IEEE Multimedia·2021· 17 citedOpen Access
W2VV++ BERT Model at VBS 2021
Lecture notes in computer science·2021· 8 cited
How Many Neighbours for Known-Item Search?
Lecture notes in computer science·2021· 2 cited
SOMHunter: Lightweight Video Search System with SOM-Guided Relevance Feedback
2020· 22 cited
A W2VV++ Case Study with Automated and Interactive Text-to-Video Retrieval
2020· 23 cited
page 1 of 2Next →

Frequent Co-authors

Jakub Lokoč(23), Gregor Kovalčík(10), František Mejzlík(9), Ivan Laptev(8), Patrik Veselý(6), Josef Šivic(6), Ladislav Peška(5), Jaroslav Moravec(4), Přemysl Čech(4), Jean-Baptiste Alayrac(4), Antoine Miech(4), Dima Damen(4), Michael Wray(4), Luca Rossetto(3), Miroslav Kratochvíl(3), Josef Sivic(3), Ralph Gasser(2), Werner Bailer(2), Klaus Schoeffmann(2), Stefanos Vrochidis(2)