AI Paper Atlas

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

Reformulating HOI Detection As Adaptive Set Prediction

Mingfei Chen, Yue Liao, Si Liu, Zhiyuan Chen, Fei Wang, Chen Qian

CVPR 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 160 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
reformulate HOI detection as adaptive set prediction with learned interaction queries and matched supervisionAS-Net · HICO-DET test, Default FullmAP: 21.94 -> 28.87Improved
combine vector matching with semantic embedding matching (ablation)AS-Net · HICO-DET test, Default FullmAP: 28.56 -> 28.87; 28.65 -> 28.87Improved
set semantic embedding dimension to 4 instead of 8 (ablation)AS-Net · HICO-DET test, Default FullmAP: 28.87 -> 28.21Hurt
set semantic embedding dimension to 16 or 32 instead of 8 (ablation)AS-Net · HICO-DET test, Default FullmAP: 28.87 -> 28.36; 28.87 -> 28.70Hurt
set embedding loss weight to 0.05 or 0.5 instead of 0.1 (ablation)AS-Net · HICO-DET test, Default FullmAP: 28.87 -> 28.31; 28.87 -> 27.84Hurt
replace parallel instance and interaction branches with a single branch (ablation)AS-Net · HICO-DET test, Default FullmAP: 28.87 -> 25.91Hurt
add an interaction branch to the single-branch model (ablation)AS-Net · HICO-DET test, Default FullmAP: 25.91 -> 27.52Improved
add instance-aware attention to the basic model without embeddings (ablation)AS-Net · HICO-DET test, Default FullmAP: 27.52 -> 27.96Improved
add semantic embeddings to the basic model without instance-aware attention (ablation)AS-Net · HICO-DET test, Default FullmAP: 27.52 -> 27.75Improved
add instance-aware attention to the model with semantic embeddings (ablation)AS-Net · HICO-DET test, Default FullmAP: 27.75 -> 28.87Improved
use three instance-aware attention modules rather than six with embeddings and a 6-layer interaction decoder (ablation)AS-Net · HICO-DET test, Default FullmAP: 28.87 -> 28.39Hurt
reduce both the instance-aware attention modules and interaction decoder layers to three (ablation)AS-Net · HICO-DET test, Default FullmAP: 28.87 -> 28.63Hurt

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