Research map / Label-efficient and robust learning / Domain adaptation and generalization
Borrowing Eyes for the Blind Spot: Overcoming Data Scarcity in Malicious Video Detection via Cross-Domain Retrieval Augmentation
Rongpei Hong, Jian Lang, Ting Zhong, Fan Zhou
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 cross-domain image-text augmenter (ablation) | CRAVE · FakeTT | ACC: 77.25 -> 84.95 | Improved |
| add cross-domain image-text augmenter (ablation) | CRAVE · MHClipEN | M-F1: 65.29 -> 79.81 | Improved |
| use Pseudo-Pair Retriever instead of vanilla video retriever (ablation) | CRAVE · FakeTT | ACC: 82.94 -> 84.95 | Improved |
| use Pseudo-Pair Retriever instead of vanilla video retriever (ablation) | CRAVE · MHClipEN | M-F1: 74.02 -> 79.81 | Improved |
| use Pseudo-Pair Retriever instead of random retrieval (ablation) | CRAVE · MHClipEN | M-F1: 72.07 -> 79.81 | Improved |
| add cross-domain decoupling learning (DIO, DUO) (ablation) | CRAVE · FakeTT | ACC: 81.60 -> 84.95 | Improved |
| add cross-domain contrastive learning (ablation) | CRAVE · FakeTT | ACC: 81.27 -> 84.95 | Improved |
| add cross-domain contrastive learning (ablation) | CRAVE · MHClipEN | M-F1: 72.81 -> 79.81 | Improved |
| add decoupling learning (ablation) | CRAVE · MHClipEN | M-F1: 76.60 -> 79.81 | Improved |
| add conventional spatial augmentation of videos to best baseline | FakeRec · FakeTT | ACC: 79.53 -> 78.26 | No clear effect |
| add temporal video augmentation to best baseline | FakeRec · FakeTT | ACC: 79.53 -> 72.91 | Hurt |
| use LLaVA zero-shot style cross-domain transfer instead of CRAVE | LLaVA · FakeTT | ACC: 84.95 -> 46.93 | Hurt |
Closest papers by meaning
- VarCMP: Adapting Cross-Modal Pre-Training Models for Video Anomaly Retrieval (AAAI 2025 · similarity 0.83)
- Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection (NeurIPS 2024 · similarity 0.83)
- Vid-SME: Membership Inference Attacks against Large Video Understanding Models (NeurIPS 2025 · similarity 0.83)
- VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection (AAAI 2024 · similarity 0.82)
- Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models (ICML 2025 · similarity 0.82)
- Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs (NeurIPS 2025 · similarity 0.82)
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.
