Research map / Video / Video-language understanding
Phrase-Level Temporal Relationship Mining for Temporal Sentence Localization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 phrase-level predictions to refine sentence predictions and train phrase localization with consistency and exclusiveness constraints | TRM · Charades-STA, verb phrase queries | R@1, IoU=0.3: 38.41 -> 57.03 | Helped |
| Use phrase-level predictions to refine sentence predictions and train phrase localization with consistency and exclusiveness constraints | TRM · Charades-STA, sentence queries | R@1, IoU=0.3: 60.48 -> 60.67 | No clear effect |
| Use phrase-level predictions to refine sentence predictions and train phrase localization with consistency and exclusiveness constraints | TRM · ActivityNet Captions val 2, verb phrase queries | R@1, IoU=0.7: 32.88 -> 33.68 | Helped |
| Use phrase-level predictions to refine sentence predictions and train phrase localization with consistency and exclusiveness constraints | TRM · ActivityNet Captions val 2, sentence queries | R@1, IoU=0.7: 31.42 -> 31.18 | No clear effect |
| Train on phrase-level predictions for unseen compositions | TRM · ActivityNet-CG Novel-Composition | R@1, IoU=0.5: 31.51 -> 33.80 | Helped |
| Add phrase features without consistency or exclusiveness constraints (ablation) | TRM · Charades-STA phrase queries | R@1, IoU=0.3, verb phrase: 38.41 -> 41.13 | Helped |
| Add consistency constraint (ablation) | TRM · Charades-STA phrase queries | R@1, IoU=0.3, verb phrase: 38.41 -> 56.69 | Helped |
| Add consistency constraint (ablation) | TRM · Charades-STA phrase queries | R@1, IoU=0.3, noun phrase: 33.13 -> 71.12 | Helped |
| Add exclusiveness constraint without consistency (ablation) | TRM · Charades-STA phrase queries | R@1, IoU=0.3, verb phrase: 38.41 -> 38.90 | No clear effect |
| Add both consistency and exclusiveness constraints (ablation) | TRM · Charades-STA phrase queries | R@1, IoU=0.3, noun phrase: 33.13 -> 78.25 | Helped |
Closest papers by meaning
- Unsupervised Domain Adaptative Temporal Sentence Localization with Mutual Information Maximization (AAAI 2024 · similarity 0.89)
- Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding (NeurIPS 2025 · similarity 0.87)
- Omnipotent Distillation with LLMs for Weakly-Supervised Natural Language Video Localization: When Divergence Meets Consistency (AAAI 2024 · similarity 0.87)
- Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network (AAAI 2025 · similarity 0.87)
- Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding (AAAI 2025 · similarity 0.87)
- Universal Video Temporal Grounding with Generative Multi-modal Large Language Models (NeurIPS 2025 · 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.