AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Exploiting Contextual Objects and Relations for 3D Visual Grounding

Li Yang, Chunfeng Yuan, Ziqi Zhang, Zhongang Qi, Yan Xu, Wei Liu, Ying Shan, Bing Li, Weiping Yang, Peng Li, Yan Wang, Weiming Hu

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
add learning of contextual objects (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 34.66 -> 44.42Improved
add learning of contextual relations only (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 34.66 -> 37.33Improved
add both contextual objects and relations (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 34.66 -> 49.57Improved
add contextual relations on top of objects (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 44.42 -> 49.57Improved
supervised learning on labeled noun phrases (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 34.66 -> 38.33Improved
add pseudo labels for unlabeled noun phrases (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 38.33 -> 44.42Improved
add Distance & Orientation relation features (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 44.42 -> 46.57Improved
add Volume & Dimension relation features (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 44.42 -> 46.05Improved
add Perspective-related relation features (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 44.42 -> 47.44Improved
perspective features on view-dependent subset (ablation)CORE-3DVG baseline · Nr3D View-dep.Acc@0.25: 40.75 -> 46.46Improved
combine all three relation feature types (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 44.42 -> 47.90Improved
add relation matching network without weakly-supervised losses (ablation)CORE-3DVG baseline · Nr3D overallAcc@0.25: 47.90 -> 47.80No clear effect

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