AI Paper Atlas

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

Learning Affordance Grounding From Exocentric Images

Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, Dacheng Tao

CVPR 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 57 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
Transfer exocentric affordance knowledge with AIM, ACP, and L_KTCross-view affordance grounding model · AGD20K SeenKLD: 1.773 -> 1.538Improved
Transfer exocentric affordance knowledge with AIM, ACP, and L_KTCross-view affordance grounding model · AGD20K UnseenKLD: 1.994 -> 1.787Improved
Add AIM to the otherwise unmodified model (ablation)Cross-view affordance grounding model · AGD20K SeenNSS: 0.302 -> 0.674Improved
Add AIM to the otherwise unmodified model (ablation)Cross-view affordance grounding model · AGD20K UnseenNSS: 0.445 -> 0.682Improved
Add ACP to the otherwise unmodified model (ablation)Cross-view affordance grounding model · AGD20K SeenNSS: 0.302 -> 0.687Improved
Add ACP to the otherwise unmodified model (ablation)Cross-view affordance grounding model · AGD20K UnseenNSS: 0.445 -> 0.666Improved
Add L_KT to the otherwise unmodified model (ablation)Cross-view affordance grounding model · AGD20K SeenNSS: 0.302 -> 0.344Improved
Add L_KT to the otherwise unmodified model (ablation)Cross-view affordance grounding model · AGD20K UnseenNSS: 0.445 -> 0.622Improved
Vary the low-rank dictionary rank r (ablation)AIM module · AGD20KperformanceNo clear effect
Increase the number of exocentric images from 2 to 3 (ablation)Cross-view affordance grounding model · AGD20Kperformance: 2 to 3Improved

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