Research map / Video / Video-language understanding
WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding
Mengze Li, Han Wang, Wenqiao Zhang, Jiaxu Miao, Zhou Zhao, Shengyu Zhang, Wei Ji, Fei Wu
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 Structure-guided Video Hierarchical Understanding (SVHU) (ablation) | WINNER · VidSTG declarative | m vIoU: 7.42 to 9.97 alone | Improved |
| add Decomposition Structure Alignment (DSA) (ablation) | WINNER · VidSTG declarative | m vIoU: 7.42 to 10.89 alone | Improved |
| combine SVHU and DSA (ablation) | WINNER · VidSTG declarative and interrogative | m vIoU: 11.61 vs 10.89 (declarative); 10.23 vs 9.65 (interrogative) | Improved |
| WINNER weakly supervised vs AWGU and Vis-Ctx baselines | WINNER · VidSTG declarative, interrogative, HC-STVG | m vIoU: 11.61 vs 9.34 (declarative); 14.20 vs 9.76 (HC-STVG) | Improved |
| weakly supervised WINNER vs fully supervised GroundeR and STPR | WINNER · VidSTG declarative | m vIoU: 11.61 vs 9.78 (GroundeR) and 10.40 (STPR); below STGRN 19.75 | Improved |
| WINNER interrogative vs Vis-Ctx | WINNER · VidSTG interrogative | m vIoU: 10.23 vs 8.69 for Vis-Ctx; 10.23 vs 10.65 for WSSTG T (supervised) | Mixed |
Later papers that compared with this method
3 later accepted papers report WINNER as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding (AAAI 2026 · better on 3 of 3 shared results)
- Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding (ICLR 2025 · better on 3 of 3 shared results)
- Weakly-Supervised Spatio-Temporal Video Grounding with Variational Cross-Modal Alignment (ECCV 2024 · better on 8 of 9 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
- Learning Multi-Scale Video-Text Correspondence for Weakly Supervised Temporal Article Gronding (AAAI 2024 · similarity 0.90)
- Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding (CVPR 2024 · similarity 0.88)
- Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models (CVPR 2025 · similarity 0.88)
- Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding (AAAI 2024 · similarity 0.88)
- STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding (CVPR 2025 · similarity 0.87)
- TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment (NeurIPS 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.
