AI Paper Atlas

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

HOI Analysis: Integrating and Decomposing Human-Object Interaction

Yong-Lu Li, Xinpeng Liu, Xiaoqian Wu, Yizhuo Li, Cewu Lu

NeurIPS 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 68 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 inter-pair transformation (instance exchange) (ablation)IDN · HICO-DET Default FullmAP: 22.63 -> 23.36Improved
add integration validity loss L_cls^u (ablation)IDN · HICO-DET Default FullmAP: 19.98 -> 23.36Improved
add decomposition validity loss L_cls^ho (ablation)IDN · HICO-DET Default FullmAP: 21.39 -> 23.36Improved
add interactiveness validity loss L_bin (ablation)IDN · HICO-DET Default FullmAP: 22.01 -> 23.36Improved
add AE verb classification pre-training loss (ablation)IDN · HICO-DET Default FullmAP: 19.60 -> 23.36Improved
add AE reconstruction loss (ablation)IDN · HICO-DET Default FullmAP: 21.07 -> 23.36Improved
combine integration, decomposition and AE scores instead of integration only (ablation)IDN · HICO-DET Default FullmAP: 21.26 -> 23.36Improved
use per-verb MLP pairs instead of single conditioned MLP with verb indicator (ablation)IDN · HICO-DET Default FullmAP: 20.86 -> 23.36Improved
use loop through integrated features instead of using f_u directly (ablation)IDN · HICO-DET Default FullmAP: 21.77 -> 23.36Improved
apply integration/decomposition as proxy task to iCANiCAN · HICO-DET Default FullmAP: 14.84 -> 18.98Improved
use HICO-DET fine-tuned (DRG) detector instead of COCO detectorIDN · HICO-DET Default FullmAP: 23.36 -> 26.29Improved

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