Research map / Video / Video-language understanding
A Large-Scale Comprehensive Dataset and Copy-Overlap Aware Evaluation Protocol for Segment-Level Video Copy Detection
Sifeng He, Xudong Yang, Chen Jiang, Gang Liang, Wei Zhang, Tan Pan, Qing Wang, Furong Xu, Chunguang Li, JinXiong Liu, Hui Xu, Kaiming Huang and 4 more
Check 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 |
|---|---|---|---|
| Use DINO features with SPD rather than the other tested feature-alignment combinations | Segment-level video copy localization on VCSL positive pairs · VCSL positive pairs (macro over query sets) | F-score: 87.40 | Improved |
| Use DINO features with TN rather than other tested combinations | Video copy detection on VCSL positive and negative pairs · VCSL test | Recall: 77.61 | Improved |
| Use ViSiL features with TN | Video copy detection on VCSL positive and negative pairs · VCSL test | F-score: 61.46 | Improved |
| Train SPD on VCSL instead of VCDB (ablation) | DINO + SPD · VCSL positive pairs (macro over query sets) | F-score: 85.69 -> 87.40 | Improved |
| Use SPD for segment localization | Video copy detection on VCSL · VCSL test (positive and negative pairs) | F-score: 60.70; FRR 0.2726; FAR 0.1732 | Mixed |
| Use different frame feature extractors | Segment-level video copy detection benchmark · VCSL | F-score: 48.04; 51.26; 47.86; 49.96 (with HV) | Mixed |
Closest papers by meaning
- FiGVCL: Fine-Grained Benchmark and Method for Video Copy Localization (TPAMI 2025 · similarity 0.91)
- Self-Supervised Video Copy Localization with Regional Token Representation (ECCV 2024 · similarity 0.89)
- TransVCL: Attention-Enhanced Video Copy Localization Network with Flexible Supervision (AAAI 2023 · similarity 0.87)
- SyncVIS: Synchronized Video Instance Segmentation (NeurIPS 2024 · similarity 0.84)
- VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models (NeurIPS 2024 · similarity 0.83)
- Exploiting Temporal State Space Sharing for Video Semantic Segmentation (CVPR 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.
