7 papers
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
Geo Ahn, Inwoong Lee, Taeoh Kim +3
Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of previously observed primitives. In this work, we tackle a key fa…
Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
Jongseo Lee, Wooil Lee, Gyeong-Moon Park +2
Effective explanations of video action recognition models should disentangle how movements unfold over time from the surrounding spatial context. However, existing methods based on…
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition
Jongseo Lee, Joohyun Chang, Dongho Lee +1
We propose Cross-Attention in Audio, Space, and Time (CA^2ST), a transformer-based method for holistic video recognition. Recognizing actions in videos requires both spatial and te…
NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models
Kyuho Lee, Euntae Kim, Jinwoo Choi +1
Video large language models (Video LLMs) have recently achieved strong performance on tasks such as captioning, summarization, and question answering. Many models and training meth…
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…
PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition
Jongseo Lee, Wooil Lee, Gyeong-Moon Park +2
Human action recognition (HAR) has achieved impressive results with deep learning models, but their decision-making process remains opaque due to their black-box nature. Ensuring i…