Research map / Video / Video-language understanding
Collaborative Temporal Consistency Learning for Point-supervised Natural Language Video Localization
Zhuo Tao, Liang Li, Qi Chen, Yunbin Tu, Zheng-Jun Zha, Amin Beheshti, Qingming Huang, Yuankai Qi, Ming–Hsuan Yang
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 segment-level TCL to frame-level TCL (ablation) | COTEL · Charades-STA ablation | R1@0.5: 46.14 -> 48.45 | Improved |
| add frame-level TCL to segment-level TCL (ablation) | COTEL · Charades-STA ablation | R1@0.5: 47.77 -> 48.45 | Improved |
| add frame-level consistency guidance (FCG) (ablation) | COTEL · Charades-STA ablation | R1@0.5: 48.45 -> 50.24 | Improved |
| add segment-level consistency guidance (SCG) (ablation) | COTEL · Charades-STA ablation | R1@0.5: 48.45 -> 49.66 | Improved |
| add both FCG and SCG (ablation) | COTEL · Charades-STA ablation | R1@0.5: 48.45 -> 53.52 | Improved |
| add L_frame to L_KL (ablation) | COTEL · Charades-STA ablation | R1@0.5: 32.18 -> 47.28 | Improved |
| add L_intra (ablation) | COTEL · Charades-STA ablation | R1@0.5: 47.28 -> 53.01 | Improved |
| add L_inter (ablation) | COTEL · Charades-STA ablation | R1@0.5: 47.28 -> 49.11 | Improved |
| add L_inter on top of L_intra (ablation) | COTEL · Charades-STA ablation | R1@0.5: 53.01 -> 53.52 | Improved |
| tune lambda_intra and lambda_inter in {0.01,0.05,0.1,0.5,1} (ablation) | COTEL · Charades-STA ablation | R1@0.5: best at lambda_intra=0.5, lambda_inter=0.05 | Mixed |
| replace ViGA with COTEL | point-supervised NLVL · TACoS (point-supervised) | R1@0.3: 19.62 -> 38.39 | Improved |
| replace ViGA with COTEL | point-supervised NLVL · Charades-STA (point-supervised) | R1@0.5: 45.05 -> 53.52 | Improved |
Closest papers by meaning
- Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization (AAAI 2025 · similarity 0.89)
- Transferable Video Moment Localization by Moment-Guided Query Prompting (AAAI 2024 · 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 0.87)
- Unsupervised Domain Adaptative Temporal Sentence Localization with Mutual Information Maximization (AAAI 2024 · similarity 0.87)
- Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding (ICLR 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.
