3 papers
cs.CV2026
MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval?
Uicheol Jung, Juyoung Hong, Geuntaek Lim +1
Text-video retrieval requires representations that can distinguish videos with similar scenes, actions, and temporal patterns. Recent multimodal large language models have been ada…
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…