Gedas Bertasius

9

Papers

138

Total Citations

Papers (9)

Video ReCap: Recursive Captioning of Hour-Long Videos

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

NeurIPS 2025arXiv

Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos

ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos

BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

BIMBA: Selective-Scan Compression for Long-Range Video Question Answering

LoCoNet: Long-Short Context Network for Active Speaker Detection

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos