AI Paper Atlas

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

VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions

Oytun Ulutan, A S M Iftekhar, B. S. Manjunath

CVPR 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 251 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 the Spatial attention branch to the Visual branch (ablation)VSGNet · V-COCO test, Scenario 1mAP: 47.3 -> 50.33Improved
add the Spatial attention branch to the Visual branch (ablation)VSGNet · V-COCO test, Scenario 2mAP: 52.15 -> 55.32Improved
add the Graph branch to the Visual branch without Spatial attention (ablation)VSGNet · V-COCO test, Scenario 1mAP: 47.3 -> 48.19Improved
add the Graph branch to the Visual branch without Spatial attention (ablation)VSGNet · V-COCO test, Scenario 2mAP: 52.15 -> 53.12Improved
add the Graph branch to the Visual+Spatial model (ablation)VSGNet · V-COCO test, Scenario 1mAP: 50.33 -> 51.76Improved
add the Graph branch to the Visual+Spatial model (ablation)VSGNet · V-COCO test, Scenario 2mAP: 55.32 -> 57.03Improved
replace Resnet-152 with VGG-19 as the backbone (ablation)VSGNet · V-COCO, Scenario 1mAP: 51.76 -> 48.37Hurt
replace Resnet-152 with InceptionV3 as the backbone (ablation)VSGNet · V-COCO, Scenario 1mAP: 51.76 -> 49.39Hurt
replace Resnet-152 with SqueezeNet as the backbone (ablation)VSGNet · V-COCO, Scenario 1mAP: 51.76 -> 43.4Hurt
replace Resnet-152 with Resnet34 as the backbone (ablation)VSGNet · V-COCO, Scenario 1mAP: 51.76 -> 50.88Hurt
replace Resnet-152 with Resnet50 as the backbone (ablation)VSGNet · V-COCO, Scenario 1mAP: 51.76 -> 51.01Hurt
replace Resnet-152 with Resnet101 as the backbone (ablation)VSGNet · V-COCO, Scenario 1mAP: 51.76 -> 50.01Hurt

Later papers that compared with this method

6 later accepted papers report VSGNet as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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