5 papers
Video-Oasis: Rethinking Evaluation of Video Understanding
Geuntaek Lim, Sungjune Park, Jaeyun Lee +5
The inherent complexity of video understanding makes it difficult to determine whether Video-LLM benchmark performance stems from visual perception, linguistic reasoning, or knowle…
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
Geo Ahn, Inwoong Lee, Taeoh Kim +3
Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of previously observed primitives. In this work, we tackle a key fa…
Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation
Su Ho Han, Jeongseok Hyun, Pilhyeon Lee +3
Multimodal large language models (MLLMs) demonstrate strong video understanding by attending to visual tokens relevant to textual queries. To directly adapt this for localization i…
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
Jeongseok Hyun, Sukjun Hwang, Su Ho Han +6
Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with t…
Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval
WonJun Moon, Cheol-Ho Cho, Woojin Jun +5
In a retrieval system, simultaneously achieving search accuracy and efficiency is inherently challenging. This challenge is particularly pronounced in partially relevant video retr…