VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection
Peng Wu, Xuerong Zhou, Guansong Pang, Lingru Zhou, Qingsen Yan, Peng Wang, Yanning Zhang
De quem é
- Northwestern Polytechnical Universityafiliação declarada pelos autores, segundo o OpenAlex
- Singapore Management Universityafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- Understanding R1-Zero-Like Training: A Critical PerspectiveNational University of Singapore · 1.676 citações
- SpatialVLA: Exploring Spatial Representations for Visual-Language-Action ModelsFudan University · 701 citações
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement LearningNorthwestern University · 539 citações
- Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and ProspectsAnt Group · 500 citações
- Equivariant Multi-Modality Image FusionNorthwestern Polytechnical University · 473 citações
- Large language models for robotics: Opportunities, challenges, and perspectivesNorthwestern Polytechnical University · 448 citações