AI Paper Atlas

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

CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection

Yunyao Mao, Jiajun Deng, Wengang Zhou, Li Li, Yao Fang, Houqiang Li

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Zero-shot segmentation and detection · 9 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 HOI decoder aggregating CLIP visual features (ablation)CLIP4HOI · HICO-DET RF-UCunseen mAP: 23.80 -> 28.47Improved
add HO interactor (pairwise interaction and spatial injection) (ablation)CLIP4HOI · HICO-DET RF-UCfull mAP: 32.98 -> 34.08Improved
add CLIP class token as decoder input (ablation)CLIP4HOI · HICO-DET RF-UCfull mAP: 33.50 -> 34.08Improved
aggregate mid-level CLIP features instead of final features in decoder (ablation)CLIP4HOI · HICO-DET RF-UCfull mAP: 34.08 -> 32.83Hurt
add global HOI score (ablation)CLIP4HOI · HICO-DET RF-UCunseen mAP: 25.48 -> 28.47Improved
add global HOI score (ablation)CLIP4HOI · HICO-DET RF-UCseen mAP: 36.06 -> 35.48Hurt
add DETR object class priors (ablation)CLIP4HOI · HICO-DET RF-UCunseen mAP: 24.68 -> 28.47Improved
use learnable prompt instead of manual prompt (ablation)CLIP4HOI · HICO-DET RF-UCunseen mAP: 23.92 -> 28.47Improved
increase HOI decoder layers beyond 6 (ablation)CLIP4HOI · HICO-DET RF-UCfull mAP: 34.08 -> 33.94No clear effect
set pairwise loss weight beta to 1.0 vs 5.0 (ablation)CLIP4HOI · HICO-DET RF-UCunseen mAP: 26.41 -> 28.47Improved
use two-stage disentangled pipeline instead of one-stage EoID under large position distribution discrepancyHICO-DET NF-UC unseen · HICO-DET NF-UCunseen mAP: 18.92 -> 28.23Improved

Later papers that compared with this method

2 later accepted papers report CLIP4HOI as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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