5 papers
ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions
Zihao Liu, Xiaoyu Wu, Wenna Li +2
Open-world video anomaly detection (OWVAD) aims to detect and explain abnormal events under different anomaly definitions, which is important for applications such as intelligent s…
AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation
Tongfei Chen, Shuo Yang, Yuguang Yang +7
Referring Image Segmentation (RIS) aims to segment the object in an image uniquely referred to by a natural language expression. However, RIS training often contains hard-to-align…
Language-guided Open-world Video Anomaly Detection under Weak Supervision
Zihao Liu, Xiaoyu Wu, Jianqin Wu +2
Video anomaly detection (VAD) aims to detect anomalies that deviate from what is expected. In open-world scenarios, the expected events may change as requirements change. For examp…
MLVTG: Mamba-Based Feature Alignment and LLM-Driven Purification for Multi-Modal Video Temporal Grounding
Zhiyi Zhu, Xiaoyu Wu, Zihao Liu +1
Video Temporal Grounding (VTG), which aims to localize video clips corresponding to natural language queries, is a fundamental yet challenging task in video understanding. Existing…
Rethinking Metrics and Benchmarks of Video Anomaly Detection
Zihao Liu, Xiaoyu Wu, Wenna Li +2
Video Anomaly Detection (VAD), which aims to detect anomalies that deviate from expectation, has attracted increasing attention in recent years. Existing advancements in VAD primar…