6 papers
SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding
Jiwook Han, Geo Ahn, Youngrae Kim +1
Multimodal Large Language Models (MLLMs) have shown strong performance on Video Temporal Grounding (VTG). However, their coarse recognition capabilities are insufficient for fine-g…
Universal Domain Adaptation for Semantic Segmentation
Seun-An Choe, Keon-Hee Park, Jinwoo Choi +1
Unsupervised domain adaptation for semantic segmentation (UDA-SS) aims to transfer knowledge from labeled source data to unlabeled target data. However, traditional UDA-SS methods…
MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
Kyungho Bae, Jinhyung Kim, Sihaeng Lee +3
In this work, we tackle action-scene hallucination in Video Large Language Models (Video-LLMs), where models incorrectly predict actions based on the scene context or scenes based…
DEVIAS: Learning Disentangled Video Representations of Action and Scene
Kyungho Bae, Geo Ahn, Youngrae Kim +1
Video recognition models often learn scene-biased action representation due to the spurious correlation between actions and scenes in the training data. Such models show poor perfo…
Infusing Environmental Captions for Long-Form Video Language Grounding
Hyogun Lee, Soyeon Hong, Mujeen Sung +1
In this work, we tackle the problem of long-form video-language grounding (VLG). Given a long-form video and a natural language query, a model should temporally localize the precis…
Open-Set Domain Adaptation for Semantic Segmentation
Seun-An Choe, Ah-Hyung Shin, Keon-Hee Park +2
Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer the pixel-wise knowledge from the labeled source domain to the unlabeled target domain. However, cur…