Research map / Video / Video segmentation and tracking
Self-Training Multi-Sequence Learning with Transformer for Weakly Supervised Video Anomaly Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Multi-Sequence Learning with VideoSwin-RGB instead of RTFM with VideoSwin-RGB | Weakly supervised VAD · UCF-Crime | AUC (%): +2.31% | Helped |
| Use Multi-Sequence Learning with VideoSwin-RGB instead of RTFM with VideoSwin-RGB | Weakly supervised VAD · XD-Violence | AP (%): 0.64% | Helped |
| Use Multi-Sequence Learning with VideoSwin-RGB and ten-crop instead of the strongest reported ShanghaiTech baseline | Weakly supervised VAD · ShanghaiTech | AUC (%) | Helped |
| Replace standard Transformer projections with depthwise separable 1D convolution in CTE (ablation) | MSLNet · ShanghaiTech | AUC (%): +0.42 | Helped |
| Replace standard Transformer projections with depthwise separable 1D convolution in CTE (ablation) | MSLNet · UCF-Crime | AUC (%): +0.21 | Helped |
| Multiply snippet anomaly scores by video-level anomaly probability at inference (ablation) | MSLNet · ShanghaiTech | AUC (%): +0.95 | Helped |
| Multiply snippet anomaly scores by video-level anomaly probability at inference (ablation) | MSLNet · UCF-Crime | AUC (%): +0.68 | Helped |
Closest papers by meaning
- Learning Event Completeness for Weakly Supervised Video Anomaly Detection (ICML 2025 · similarity 0.89)
- Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection (CVPR 2024 · similarity 0.87)
- Harnessing Large Language Models for Training-free Video Anomaly Detection (CVPR 2024 · similarity 0.87)
- Federated Weakly Supervised Video Anomaly Detection with Multimodal Prompt (AAAI 2025 · similarity 0.87)
- Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection (CVPR 2024 · similarity 0.86)
- VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.