AI Paper Atlas

Research map / Detection and segmentation / CNN features

Contextual Attention for Hand Detection in the Wild

Supreeth Narasimhaswamy, Zhengwei Wei, Yang Wang, Justin Zhang, Minh Hoai

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 70 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 contextual attention module to MaskRCNN (ablation)MaskRCNN · Oxford-Hand testAP: 69.9% -> 73.0%Improved
add contextual attention module to MaskRCNN (ablation)MaskRCNN · TV-Hand testAP: 59.9% -> 60.3%No clear effect
add semantics context component (ablation)Hand-CNN · Oxford-Hand testAP: 71.4% -> 73.0%Improved
add similarity context component (ablation)Hand-CNN · Oxford-Hand testAP: 70.8% -> 73.0%Improved
add semantics context component (ablation)Hand-CNN · TV-Hand testAP: 59.4% -> 60.3%Improved
add similarity context component (ablation)Hand-CNN · TV-Hand testAP: 59.6% -> 60.3%Improved
add COCO-Hand-S to TV-Hand training data (ablation)MaskRCNN · Oxford-Hand testAP: 62.5% -> 69.9%Improved
add COCO-Hand-S to TV-Hand training data (ablation)MaskRCNN · TV-Hand testAP: 55.4% -> 59.9%Improved
use COCO-Hand (masked unannotated hands) instead of COCO-Hand-S (ablation)MaskRCNN · Oxford-Hand testAP: 69.9% -> 76.7%Improved
use COCO-Hand (masked unannotated hands) instead of COCO-Hand-S (ablation)MaskRCNN · TV-Hand testAP: 59.9% -> 63.5%Improved
share weights between orientation branch and MaskRCNN branch (ablation)Hand-CNN · hand detectionAPImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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