AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Disentangling and Reusing Interaction Cues for Zero-Shot HOI Detection

Jie Gu, He-Yang Xu, Hongxiang Gao, Chengyu Liu

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 0 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 CORD module (ablation)baseline CLIP two-stage HOI · HICO-DET UVUnseen mAP: 24.88 -> 28.58Improved
add SLF module (ablation)baseline CLIP two-stage HOI · HICO-DET UVUnseen mAP: 24.88 -> 27.19Improved
add SLF on top of CORD (ablation)DRIC · HICO-DET UVUnseen mAP: 28.58 -> 29.49Improved
use orthogonal projection instead of concatenation (ablation)CORD · HICO-DET UVUnseen mAP: 28.41 -> 29.49Improved
use orthogonal projection instead of subtraction (ablation)CORD · HICO-DET UVUnseen mAP: 28.05 -> 29.49Improved
use orthogonal projection instead of cross-attention (ablation)CORD · HICO-DET UVUnseen mAP: 28.86 -> 29.49Improved
fuse all layers L1-L12 instead of final layer only (ablation)SLF · HICO-DET UVUnseen mAP: 28.58 -> 29.49Improved
fuse L6-L12 instead of L1-L12 (ablation)SLF · HICO-DET UVUnseen mAP: 29.03 -> 29.49Hurt
fuse L1-L6 + L12 instead of L1-L12 (ablation)SLF · HICO-DET UVUnseen mAP: 28.85 -> 29.49Hurt
two-stage training instead of one-stage joint (ablation)DRIC · HICO-DET UVUnseen mAP: 28.78 -> 29.49Improved
two-stage training instead of one-stage joint (ablation)DRIC · HICO-DET UVFull mAP: 33.18 -> 33.95Improved
replace background with task-irrelevant scenes (drop rate)DRIC vs baseline · HICO-DET UVFull mAP drop rate: 12.26% -> 2.18%Improved

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