Research map / Video / Video segmentation and tracking
Cross-Domain Learning for Video Anomaly Detection with Limited Supervision
Yashika Jain, Ali Dabouei, Min Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add unlabeled external data without uncertainty weighting or cosine loss (ablation) | Weakly-supervised VAD baseline · UCF-R open-set c=1 | AUC (%): 84.32 -> 84.67 | Improved |
| add uncertainty-based reweighing of external-data bias (ablation) | CDL with external data · UCF-R open-set c=1 | AUC (%): 84.67 -> 84.80 | Improved |
| add cosine similarity loss term on I3D/CLIP representations (ablation) | CDL with uncertainty weighting · UCF-R open-set c=1 | AUC (%): 84.80 -> 85.39 | Improved |
| add CDL with HACS external data | Ours trained on UCF-Crime · XDV (source: UCF-Crime) | AP (%): 58.13 -> 65.14 | Improved |
| add CDL with XDV as external data | Ours trained on UCF-Crime · XDV (source: UCF-Crime) | AP (%): 58.13 -> 68.37 | Improved |
| add external data to source-domain training | Ours trained on UCF-Crime · UCF-Crime original test | AUC (%): 84.49 -> 84.73 | No clear effect |
| add CDL with HACS external data | Ours trained on XDV · UCF-R (source: XDV) | AUC (%): 76.39 -> 88.50 | Improved |
| add CDL external data to model trained on XDV | Ours trained on XDV · XDV (source: XDV) | AP (%): 75.13 -> 78.61 | Improved |
| add CDL unlabeled data in open-set setting across c values (ablation) | Ours · UCF-Crime open-set | AUC (%): 75.17 -> 77.45 (c=1); 83.02 -> 83.37 (c=9) | Improved |
| increase cosine similarity loss coefficient lambda_3 from 1e-9 to 1e-3, then beyond (ablation) | CDL · UCF-Crime open-set c=1 | AUC (%) | Mixed |
| increase number of segments n_s from 16 to 64, then beyond (ablation) | CDL · UCF-Crime open-set c=1 | AUC (%) | Mixed |
| add more unlabeled HACS videos beyond 11,000 (ablation) | CDL (UCF-Crime source) · XDV | AP (%) | No clear effect |
Closest papers by meaning
- Learning Event Completeness for Weakly Supervised Video Anomaly Detection (ICML 2025 · similarity 0.89)
- Towards Multi-Domain Learning for Generalizable Video Anomaly Detection (NeurIPS 2024 · similarity 0.89)
- Harnessing Large Language Models for Training-free Video Anomaly Detection (CVPR 2024 · similarity 0.89)
- MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection (NeurIPS 2025 · similarity 0.87)
- Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models (ICML 2025 · similarity 0.87)
- 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.
