2 papers
cs.CV2026
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…
cs.CV2024
Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization
Geuntaek Lim, Hyunwoo Kim, Joonsoo Kim +1
Weakly supervised temporal action localization (WTAL) aims to detect action instances in untrimmed videos using only video-level annotations. Since many existing works optimize WTA…