AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions

Shuang Li, Yilun Du, Antonio Torralba, Josef Sivic, Bryan Russell

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 18 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 sparsity loss (ablation)concatenation baseline · V-HICO test (seen classes)Phrase mAP (ko): 41.86 -> 50.79Improved
add sparsity loss (ablation)concatenation baseline · V-HICO test (seen classes)Relation mAP (ko): 11.34 -> 16.23Improved
add human ROI-pooled feature to object feature (ablation)(cat)+Spa · V-HICO test (seen classes)Phrase mAP (ko): 50.79 -> 55.60Improved
add human ROI-pooled feature to object feature (ablation)(cat)+Spa · V-HICO test (seen classes)Relation mAP (ko): 16.23 -> 15.91No clear effect
add temporal contrastive loss (ablation)(cat)+Spa+Hum · V-HICO test (seen classes)Relation mAP (ko): 15.91 -> 16.94Improved
add temporal contrastive loss (ablation)(cat)+Spa+Hum · V-HICO test (seen classes)Phrase mAP (ko): 55.60 -> 54.42Hurt
add contextual frame feature (ablation)(cat)+Spa+Hum+Tem · V-HICO test (seen classes)Relation mAP (ko): 16.94 -> 18.56Improved
add contextual frame feature (ablation)(cat)+Spa+Hum+Tem · V-HICO test (seen classes)Relation Recall@1: 25.61 -> 30.12Improved
concatenate instead of add features (ablation)Baseline · V-HICO test (seen classes)Phrase mAP (ko): 40.59 -> 41.86No clear effect
use learned full model instead of human spatial prior alone (ablation)human-prior baseline · V-HICO test (seen classes)Phrase mAP (ko): 46.67 -> 55.90Improved
full method vs prior method on unseen object classesOurs vs Peyre2017 · V-HICO unseen test (51 unseen object classes)Phrase mAP (ko): 38.19 -> 67.21Improved

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