AI Paper Atlas

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

Streamlined Open-Vocabulary Human-Object Interaction Detection

Chang Sun, Dongliang Liao, Changxing Ding

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 2 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
feed interaction queries with image tokens through frozen vision head (Semantic Bootstrapping) (ablation)SL-HOI · SWiG-HOI (Full)mAP: 21.82 -> 23.28Improved
feed interaction queries with image tokens through frozen vision head (Semantic Bootstrapping) (ablation)SL-HOI · SWiG-HOI (Unseen)mAP: 16.55 -> 18.09Improved
add Hierarchical Refinement cross-attention block (ablation)SL-HOI · SWiG-HOI (Full)mAP: 23.28 -> 24.67Improved
add Hierarchical Refinement cross-attention block (ablation)SL-HOI · SWiG-HOI (Unseen)mAP: 18.09 -> 19.04Improved
let interaction queries influence image tokens (no attention mask) (ablation)SL-HOI · SWiG-HOI (Full)mAP: 24.01 -> 24.67Improved
process queries in frozen head instead of multi-scale late fusion decoder (ablation)SL-HOI · SWiG-HOI (Full)mAP: 21.77 -> 23.28Improved
add backbone tokens to late fusion decoder (multi-scale) (ablation)SL-HOI · SWiG-HOI (Unseen)mAP: 16.55 -> 15.73Hurt
add backbone tokens to late fusion decoder (multi-scale) (ablation)SL-HOI · SWiG-HOI (Full)mAP: 21.82 -> 21.77No clear effect
use 2 detection adapter encoder layers rather than 0 (ablation)SL-HOI · SWiG-HOI (Full)mAP: 23.95 -> 24.67Improved
use 2 rather than 5 detection adapter encoder layers (ablation)SL-HOI · SWiG-HOI (Full)mAP: 23.29 -> 24.67Improved
SL-HOI vs BC-HOI on unseen HICO-DET open-vocabSL-HOI · HICO-DET open-vocabulary (Unseen)mAP: 42.31 -> 40.53Hurt

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