AI Paper Atlas

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

Geometric Features Informed Multi-Person Human-Object Interaction Recognition in Videos

Tanqiu Qiao, Qianhui Men, Frederick W. B. Li, Yoshiki Kubotani, Shigeo Morishima, Hubert P. H. Shum

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 22 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 geometric features (skeleton and object keypoints) fused with visual features, versus visual-only ASSIGNASSIGN · MPHOIF1@10 sub-activity: 59.1 -> 68.6Improved
add geometric features fused with visual features, versus visual-only ASSIGNASSIGN · CAD-120F1@10 sub-activity: 88.0 -> 89.5Improved
add geometric features fused with visual features, versus ASSIGNASSIGN · Bimanual ActionsF1@10 sub-activity: 84.0 -> 85.0Improved
add human skeleton features to geometric-level graph (ablation)2G-GCN · CAD-120F1@10 sub-activity: 87.7 -> 89.5Improved
add object keypoint features to geometric-level graph (ablation)2G-GCN · CAD-120F1@10 sub-activity: 88.3 -> 89.5Improved
add the embedding function on geometric features (ablation)2G-GCN · CAD-120F1@10 sub-activity: 89.4 -> 89.5Improved
add similarity-based adaptive adjacency matrix in the GCN (ablation)2G-GCN · CAD-120F1@10 sub-activity: 88.7 -> 89.5Improved
add human-object attention connections in fusion-level graph (ablation)2G-GCN · CAD-120F1@10 sub-activity: 73.4 -> 89.5Improved
add object-object attention connections in fusion-level graph (ablation)2G-GCN · CAD-120F1@10 sub-activity: 88.3 -> 89.5Improved
add human-geometry connection to the fusion-level graph (ablation)2G-GCN · CAD-120F1@10 sub-activity: 89.5 -> 89.0Hurt
add human skeleton features to geometric-level graph (ablation)2G-GCN · CAD-120F1@10 object affordance: 91.0 -> 92.4Improved
add human-object attention connections in fusion-level graph (ablation)2G-GCN · CAD-120F1@10 object affordance: 90.3 -> 92.4Improved

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