AI Paper Atlas

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

Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration

Ting Lei, Shaofeng Yin, Qingchao Chen, Yuxin Peng, Yang Liu

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 8 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 interaction-aware prompts (INP) (ablation)INP-CC · SWIG-HOI FullmAP: 14.43 -> 15.54Improved
add concept calibration (CC) (ablation)INP-CC · SWIG-HOI FullmAP: 14.43 -> 15.30Improved
add CC on top of INP (ablation)INP-CC · SWIG-HOI FullmAP: 15.54 -> 16.74Improved
add INP on top of CC (ablation)INP-CC · SWIG-HOI FullmAP: 15.30 -> 16.74Improved
add CC on top of INP (ablation)INP-CC · SWIG-HOI UnseenmAP: 10.15 -> 11.02Improved
add interaction-aware prompts of size 128 without selection to common prompt (ablation)INP-CC · SWIG-HOI FullmAP: 15.30 -> 15.98Improved
add selection mechanism to prompts (ablation)INP-CC · SWIG-HOI FullmAP: 15.98 -> 16.74Improved
reduce prompt size from 128 to 64 (ablation)INP-CC · SWIG-HOI FullmAP: 16.74 -> 16.31Hurt
increase prompt size from 128 to 256 (ablation)INP-CC · SWIG-HOI FullmAP: 16.74 -> 16.18Hurt
cluster CLIP embeddings of descriptions instead of HOI names (ablation)INP-CC · SWIG-HOI FullmAP: 16.17 -> 15.93Hurt
cluster with Instructor T5 embeddings of descriptions instead of CLIP names (ablation)INP-CC · SWIG-HOI FullmAP: 16.17 -> 16.74Improved
use hard negative sampling instead of easy (ablation)INP-CC · SWIG-HOI FullmAP: 15.95 -> 16.74Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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