Research map / Video / Video-language understanding
Fast Video Moment Retrieval
Junyu Gao, Changsheng 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 fine-grained semantic distillation loss (ablation) | FVMR · TACoS | R@1 IoU=0.1/0.3/0.5: 48.42/38.68/27.30 -> 53.12/41.48/29.12 | Improved |
| add fine-grained semantic distillation loss (ablation) | FVMR · TACoS | R@5 IoU=0.1/0.3/0.5: 74.10/60.58/48.00 -> 78.12/64.53/50.00 | Improved |
| average matching scores p and q at inference (ablation) | FVMR · TACoS | R@1 IoU=0.1/0.3/0.5: 53.12/41.48/29.12 -> 53.25/42.12/30.30 | Improved |
| add textual feature distillation to score distillation (ablation) | FVMR · TACoS | R@1 IoU=0.1/0.3/0.5: 53.12/41.48/29.12 -> 53.67/42.56/29.34 | Improved |
| use hierarchical semantic-guided attention instead of HGR node matching (ablation) | FVMR · TACoS | R@1 IoU=0.1/0.3/0.5: 51.25/38.55/26.50 -> 53.12/41.48/29.12 | Improved |
| larger common-space dimension D (ablation) | FVMR · TACoS | R@1 | Mixed |
| more Bi-LSTM layers (ablation) | FVMR · TACoS | R@1 | No clear effect |
| learn common space instead of cross-modal interaction (FVMR vs 2D-TAN) | FVMR · TACoS | cross-modal learning time (ms): 135.84 -> 0.14 | Improved |
| FVMR vs 2D-TAN | FVMR · TACoS | R@1 IoU=0.5: 25.32 -> 29.12 | Improved |
| FVMR vs 2D-TAN | FVMR · ActivityNet Captions | R@5 IoU=0.7: 61.96 -> 61.04 | Hurt |
Closest papers by meaning
- Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language (AAAI 2024 · similarity 0.93)
- Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval (AAAI 2024 · similarity 0.91)
- Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval (AAAI 2025 · similarity 0.90)
- Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models (AAAI 2025 · similarity 0.90)
- VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding (NeurIPS 2024 · similarity 0.89)
- CDTR: Semantic Alignment for Video Moment Retrieval Using Concept Decomposition Transformer (AAAI 2025 · similarity 0.89)
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.
