Research map / Video / Video-language understanding
Compositional Temporal Grounding With Structured Variational Cross-Graph Correspondence Learning
Juncheng Li, Junlin Xie, Long Qian, Linchao Zhu, Siliang Tang, Fei Wu, Yi Yang, Yueting Zhuang, Xin Eric Wang
Check 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 Semantic-Contextualized Learning (ablation) | VISA · Charades-CG Novel-Composition | R@1, IoU=0.5: 43.75 -> 45.41 | Improved |
| Add Semantic-Contextualized Learning (ablation) | VISA · ActivityNet-CG Novel-Word | R@1, IoU=0.5: 29.41 -> 30.14 | Improved |
| Add Visual-Contextualized Learning (ablation) | VISA · Charades-CG Novel-Composition | R@1, IoU=0.5: 42.26 -> 45.41 | Improved |
| Add Visual-Contextualized Learning (ablation) | VISA · ActivityNet-CG Novel-Word | R@1, IoU=0.5: 28.09 -> 30.14 | Improved |
| Add Hierarchical Semantics Aggregation (ablation) | VISA · Charades-CG Novel-Composition | R@1, IoU=0.5: 44.22 -> 45.41 | Improved |
| Add Hierarchical Semantics Aggregation (ablation) | VISA · ActivityNet-CG Novel-Word | R@1, IoU=0.5: 29.31 -> 30.14 | Improved |
| Use variational cross-graph correspondence learning instead of cross-modal self-attention (ablation) | VISA · Charades-CG Novel-Composition | R@1, IoU=0.5: 41.08 -> 45.41 | Improved |
| Use variational cross-graph correspondence learning instead of cross-modal self-attention (ablation) | VISA · ActivityNet-CG Novel-Word | R@1, IoU=0.5: 26.37 -> 30.14 | Improved |
| Learn structured contextual representations rather than use detection and SRL labels directly as features (ablation) | VISA · Charades-CG Novel-Composition | R@1, IoU=0.5: 12.97 -> 45.41 | Improved |
| Learn structured contextual representations rather than use detection and SRL labels directly as features (ablation) | VISA · ActivityNet-CG Novel-Word | R@1, IoU=0.5: 10.07 -> 30.14 | Improved |
| Use VISA rather than the strongest reported baseline | Charades-CG · Novel-Composition | mIoU: 31.43 -> 42.03 | Improved |
| Use VISA rather than the strongest reported baseline | ActivityNet-CG · Novel-Composition | mIoU: 29.07 -> 35.85 | Improved |
Closest papers by meaning
- Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding (TPAMI 2023 · similarity 0.98)
- DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-To-Fine Contrastive Ranking (CVPR 2023 · similarity 0.92)
- Explore Inter-contrast between Videos via Composition for Weakly Supervised Temporal Sentence Grounding (AAAI 2022 · similarity 0.91)
- Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network (AAAI 2025 · similarity 0.90)
- Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding (NeurIPS 2025 · similarity 0.89)
- Universal Video Temporal Grounding with Generative Multi-modal Large Language Models (NeurIPS 2025 · similarity 0.89)
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.
