AI Paper Atlas

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

CVPR 2022 · Video › Video-language understanding · approach: Temporal video grounding · 69 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add Semantic-Contextualized Learning (ablation)VISA · Charades-CG Novel-CompositionR@1, IoU=0.5: 43.75 -> 45.41Improved
Add Semantic-Contextualized Learning (ablation)VISA · ActivityNet-CG Novel-WordR@1, IoU=0.5: 29.41 -> 30.14Improved
Add Visual-Contextualized Learning (ablation)VISA · Charades-CG Novel-CompositionR@1, IoU=0.5: 42.26 -> 45.41Improved
Add Visual-Contextualized Learning (ablation)VISA · ActivityNet-CG Novel-WordR@1, IoU=0.5: 28.09 -> 30.14Improved
Add Hierarchical Semantics Aggregation (ablation)VISA · Charades-CG Novel-CompositionR@1, IoU=0.5: 44.22 -> 45.41Improved
Add Hierarchical Semantics Aggregation (ablation)VISA · ActivityNet-CG Novel-WordR@1, IoU=0.5: 29.31 -> 30.14Improved
Use variational cross-graph correspondence learning instead of cross-modal self-attention (ablation)VISA · Charades-CG Novel-CompositionR@1, IoU=0.5: 41.08 -> 45.41Improved
Use variational cross-graph correspondence learning instead of cross-modal self-attention (ablation)VISA · ActivityNet-CG Novel-WordR@1, IoU=0.5: 26.37 -> 30.14Improved
Learn structured contextual representations rather than use detection and SRL labels directly as features (ablation)VISA · Charades-CG Novel-CompositionR@1, IoU=0.5: 12.97 -> 45.41Improved
Learn structured contextual representations rather than use detection and SRL labels directly as features (ablation)VISA · ActivityNet-CG Novel-WordR@1, IoU=0.5: 10.07 -> 30.14Improved
Use VISA rather than the strongest reported baselineCharades-CG · Novel-CompositionmIoU: 31.43 -> 42.03Improved
Use VISA rather than the strongest reported baselineActivityNet-CG · Novel-CompositionmIoU: 29.07 -> 35.85Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy