AI Paper Atlas

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

Contextual Heterogeneous Graph Network for Human-Object Interaction Detection

Hai Wang, Wei-shi Zheng, Ling Yingbiao

ECCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 97 citations (OpenAlex)

Read the paper

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 intra-class message to baseline (ablation)baseline · V-COCOAP_role: 47.4 -> 52.0Improved
add inter-class message to baseline (ablation)baseline · V-COCOAP_role: 47.4 -> 51.4Improved
add both intra- and inter-class messages (ablation)baseline · HICO-DET Default (Full)mAP: 13.73 -> 17.57Improved
add both messages (ablation)baseline · HICO-DET Known Object (Full)mAP: 16.92 -> 21.00Improved
add contextual graph attention (ablation)Proposed heterogeneous graph · V-COCOAP_role: 49.5 -> 52.7Improved
add contextual graph attention (ablation)Proposed heterogeneous graph · HICO-DET Default (Full)mAP: 15.34 -> 17.57Improved
add intra-class context in attention (ablation)Proposed heterogeneous graph · V-COCOAP_role: 51.2 -> 52.7Improved
add interactiveness weight (ablation)Proposed heterogeneous graph · HICO-DET Known Object (Full)mAP: 19.95 -> 21.00Improved
use heterogeneous instead of homogeneous graph (intra-class function) (ablation)Proposed heterogeneous graph · V-COCOAP_role: 49.3 -> 52.7Improved
use heterogeneous instead of homogeneous graph (inter-class function) (ablation)Proposed heterogeneous graph · HICO-DET Default (Full)mAP: 12.6 -> 17.5Improved
add intra-class message (ablation)Proposed · V-COCO complex scenesAP_role: 54.7 -> 55.1Improved
add intra-class message (ablation)Proposed · HICO-DET simple scenesmAP: 15.7 -> 15.7No 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