Research map / Video / Video-language understanding
Hypotheses Tree Building for One-Shot 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 MHST instead of ViGA | one-shot temporal sentence localization · ActivityNet Captions | R@1, IoU=0.3: 59.61 -> 64.34 | Helped |
| Use MHST instead of ViGA | one-shot temporal sentence localization · Charades-STA | R@1, IoU=0.7: 15.11 -> 34.48 | Helped |
| Add the segment tree (ablation) | one-shot TSL baseline on ActivityNet Captions · ActivityNet Captions | R@1, IoU=0.3: 54.64 -> 62.27 | Helped |
| Add self-supervision (ablation) | one-shot TSL baseline on ActivityNet Captions · ActivityNet Captions | R@1, IoU=0.3: 51.97 -> 54.64 | Helped |
| Add tree pruning (ablation) | MHST on ActivityNet Captions · ActivityNet Captions | R@1, IoU=0.3: 62.27 -> 64.34 | Helped |
| Combine visual and linguistic similarity for node merging (ablation) | MHST on ActivityNet Captions · ActivityNet Captions | R@1, IoU=0.3: 62.10 -> 64.34 | Helped |
| Add the inter-constraint loss (ablation) | MHST with ranking loss on ActivityNet Captions · ActivityNet Captions | R@1, IoU=0.3: 61.16 -> 62.98 | Helped |
| Add the intra-constraint loss (ablation) | MHST with ranking loss on ActivityNet Captions · ActivityNet Captions | R@1, IoU=0.3: 61.16 -> 62.46 | Helped |
| Use both inter- and intra-constraint losses (ablation) | MHST with ranking loss on ActivityNet Captions · ActivityNet Captions | R@1, IoU=0.3: 61.16 -> 64.34 | Helped |
| Apply the one-shot adaptation to 2D-TAN | 2D-TAN on ActivityNet Captions · ActivityNet Captions | R@1, IoU=0.3: 59.45 -> 48.76 | Hurt |
Closest papers by meaning
- Unsupervised Domain Adaptative Temporal Sentence Localization with Mutual Information Maximization (AAAI 2024 · similarity 0.90)
- Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization (AAAI 2025 · similarity 0.89)
- Omnipotent Distillation with LLMs for Weakly-Supervised Natural Language Video Localization: When Divergence Meets Consistency (AAAI 2024 · similarity 0.88)
- Commonsense for Zero-Shot Natural Language Video Localization (AAAI 2024 · similarity 0.88)
- Frame-Voyager: Learning to Query Frames for Video Large Language Models (ICLR 2025 · similarity 0.87)
- Transferable Video Moment Localization by Moment-Guided Query Prompting (AAAI 2024 · similarity 0.87)
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.