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…
CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models
Sangin Lee, Yukyung Choi
In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To address this, recent studies hav…
Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection
Sangin Lee, Seokjun Kwon, Jeongmin Shin +2
General object detection (OD) struggles to detect objects in the target domain that differ from the training distribution. To address this, recent studies demonstrate that training…
Boosting Cross-spectral Unsupervised Domain Adaptation for Thermal Semantic Segmentation
Seokjun Kwon, Jeongmin Shin, Namil Kim +2
In autonomous driving, thermal image semantic segmentation has emerged as a critical research area, owing to its ability to provide robust scene understanding under adverse visual…
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…