Research map / Video / Video-language understanding
The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning
Xinyang Zhou, Fanyue Wei, Lixin Duan, Angela Yao, Wen Li
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 video synthesizer for dynamic context (VSDC) (ablation) | QD-DETR · QVHighlights val | mAP average: 42.54 -> 46.39 | Improved |
| add temporal dynamics enhancement module (TDEM) (ablation) | QD-DETR · QVHighlights val | mAP average: 42.54 -> 44.84 | Improved |
| combine VSDC and TDEM (ablation) | QD-DETR · QVHighlights val | R1@0.7: 46.77 -> 53.67 | Improved |
| combine VSDC and TDEM (ablation) | QD-DETR · QVHighlights val | Spurious R1@0.7: 9.35 -> 8.26 | Improved |
| select similar video pairs instead of random pairs for synthesis (ablation) | QD-DETR · QVHighlights val | mAP average: 47.56 -> 49.05 | Improved |
| add TD-DETR to BAM-DETR | BAM-DETR · QVHighlights val (spurious) | Spurious R1@0.7: 7.16 -> 1.61 | Improved |
| add TD-DETR to CG-DETR | CG-DETR · QVHighlights val (spurious) | Spurious R1@0.7: 4.65 -> 2.58 | Improved |
| add TD-DETR to QD-DETR | QD-DETR · QVHighlights val | mAP@0.75: 41.82 -> 49.86 | Improved |
| add TD-DETR to BAM-DETR | BAM-DETR · QVHighlights val | mAP average: 47.61 -> 48.82 | Improved |
| add TD-DETR to SnAG | SnAG · Charades-STA test | R1@0.7: 37.32 -> 42.35 | Improved |
| set sampling ratio alpha to 0.7 rather than 0.0 (ablation) | TD-DETR · QVHighlights val | mAP average: 10.09 -> 49.05 | Improved |
| set beta to 0.7 rather than 0.9 (less dynamics) (ablation) | TD-DETR · QVHighlights val | mAP average: 47.83 -> 49.05 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BAM-DETR — BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos (ECCV 2024) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval (NeurIPS 2025 · similarity 0.89)
- When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions (NeurIPS 2025 · similarity 0.89)
- Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval (AAAI 2025 · similarity 0.89)
- Transferable Video Moment Localization by Moment-Guided Query Prompting (AAAI 2024 · similarity 0.89)
- Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language (AAAI 2024 · similarity 0.88)
- Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models (AAAI 2025 · similarity 0.88)
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.
