We pursue high-impact and original research in vision and learning
We read, code, discuss, and write about computer vision and machine learning
NeurIPS 2026
Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs
Learn more
NeurIPS 2026
EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
Learn more
NeurIPS 2026
TraCE: Trajectory-Aware Concepts for Explainable Video Understanding
Learn more
ECCV 2026
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
Learn more
ECCV 2026
ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA
Learn more
IEEE TPAMI 2026 · IF 18.6
CA²ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition
Learn more
NeurIPS 2025 · Spotlight (3.5%)
Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
Learn more
ICCV 2025 · Highlight (2.9%)
ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning
Learn more
CVPR 2025 · Highlight (3.7%)
MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
Learn more
BMVC 2025 · Oral (3.8%)
HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization
Learn more
Previous
Next
Lab at a Glance
Highlights from our recent research and growing team
News
Show More News
10월 7일 (수) 18:00
전자정보대학관 211-1호
참가 신청
오늘 하루 보지 않기
닫기
