4 papers
ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning
Jongseo Lee, Kyungho Bae, Kyle Min +2
In this work, we tackle the problem of video classincremental learning (VCIL). Many existing VCIL methods mitigate catastrophic forgetting by rehearsal training with a few temporal…
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…
GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap
Hyogun Lee, Kyungho Bae, Seong Jong Ha +3
In this work, we tackle the challenging problem of unsupervised video domain adaptation (UVDA) for action recognition. We specifically focus on scenarios with a substantial domain…