Research map / Video / Video-language understanding
Weakly-Supervised Video Object Grounding via Causal Intervention
Wei Juan Wang, Junyu Gao, Changsheng Xu
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 adversarial contrastive learning (ACL) in spatial (ablation) | STVG baseline · YouCook2-BB test | query accuracy micro: 48.98 -> 49.54 | Improved |
| add ACL in temporal (ablation) | STVG baseline · YouCook2-BB test | query accuracy micro: 48.98 -> 49.86 | Improved |
| add spatial and temporal ACL (ablation) | STVG baseline · YouCook2-BB test | query accuracy micro: 48.98 -> 50.45 | Improved |
| add backdoor adjustment (BDA) (ablation) | STVG baseline · YouCook2-BB test | query accuracy micro: 48.98 -> 49.52 | Improved |
| add BDA to Baseline + ACL (ablation) | full model · YouCook2-BB test | query accuracy micro: 50.45 -> 50.61 | Improved |
| add ACL to Baseline + BDA (ablation) | full model · YouCook2-BB test | query accuracy micro: 49.52 -> 50.61 | Improved |
| use element-wise addition instead of attention-based fusion G (ablation) | full model · YouCook2-BB test | query accuracy micro: 50.29 -> 50.61 | Improved |
| add ACL on ActivityNetEntities (ablation) | STVG* · ActivityNetEntities val | query accuracy micro: 29.09 -> 36.75 | Improved |
| add BDA on ActivityNetEntities (ablation) | STVG* · ActivityNetEntities val | query accuracy micro: 29.09 -> 31.45 | Improved |
| add ACL in temporal only (ablation) | STVG* · ActivityNetEntities val | query accuracy micro: 29.09 -> 31.24 | Improved |
| add ACL and BDA (full model) | STVG* · RoboWatch OOD | query accuracy micro (OOD): 32.05 -> 36.12 | Improved |
| add BDA vs ACL for OOD gain (ablation) | STVG baseline · RoboWatch OOD | query accuracy micro (OOD): 35.47 -> 35.89 | Improved |
Closest papers by meaning
- Interventional Video Grounding With Dual Contrastive Learning (CVPR 2021 · similarity 0.90)
- Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding (ICLR 2025 · similarity 0.87)
- Learning Multi-Scale Video-Text Correspondence for Weakly Supervised Temporal Article Gronding (AAAI 2024 · similarity 0.87)
- Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding (CVPR 2024 · similarity 0.87)
- VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding (CVPR 2024 · similarity 0.86)
- Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding (AAAI 2024 · 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.
