23 papers
LightAIR: Lightweight Action Inversion and Riemannian Rectification for Text-based Person Anomaly Search
Yulun Zhang, Zixu Li, Zhiwei Chen +6
Traditional Text-based Person Search (TPS) is typically limited to matching static appearance attributes, severely neglecting dynamic action information. The Text-based Person Anom…
The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering
Yuqian Fu, Tianwen Qian, Yanjun Li +30
EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize beyond common daily-life scena…
RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval
Jiale Huang, Zixu Li, Zhiheng Fu +3
Composed Image Retrieval (CIR) constitutes a pivotal paradigm requiring models to perform joint reasoning on reference images and modification texts. However, the prevalence of Noi…
ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification
Yupeng Zhang, Yuzhong Feng, Ruize Han +3
Open-domain open-vocabulary detection (ODOVD) requires detectors to generalize to both novel categories and unseen domains, making it more challenging than open-vocabulary detectio…
IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval
Jiale Huang, Zixu Li, Zhiwei Chen +3
Composed Video Retrieval (CVR) is designed to retrieve a target video that matches a reference video modified by a modification text. While existing methods explore cross-modal cor…
R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking
Zixu Li, Yupeng Hu, Zhiheng Fu +3
The CoVR-R challenge evaluates composed video retrieval, where a system must retrieve a target video from a large gallery given a reference video and a textual edit instruction. Th…