AI Paper Atlas

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

Exploring Predicate Visual Context in Detecting of Human-Object Interactions

Frederic Z Zhang, Yuhui Yuan, Dylan Campbell, Zhuoyao Zhong, Stephen Gould

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 77 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 cross-attention with frozen encoder features as keys/values (ablation)UPT-like two-stage detector · HICO-DET (Default, Full)mAP: 31.47 -> 31.51No clear effect
use backbone C5 features instead of encoder features as cross-attention keys/values (ablation)PViC · HICO-DET (Default, Full)mAP: 31.51 -> 32.89Improved
use higher-resolution or lower-level features (C3, C4, FPN P3) as keys/values (ablation)PViC · HICO-DET (Default, Full)mAP: 32.89 -> 29.59 (C3 with head)Hurt
add encoder features alongside C5 keys/values (ablation)PViC · HICO-DET (Default, Full)mAP: 32.89 -> 32.69No clear effect
add a lightweight window-attention feature head on C5 (ablation)PViC · HICO-DET (Default, Full)mAP: 32.89 -> 33.54Improved
stack more attention layers in feature head (2x vs 1x) (ablation)PViC · HICO-DET (Default, Full)mAP: 33.54 -> 33.57No clear effect
replace UPT modified self-attention with vanilla self-attention plus box positional embeddings (ablation)PViC · HICO-DET (Default, Full)mAP: 33.54 -> 33.59No clear effect
add spatial features in query fusion (with no self-attn) (ablation)PViC explicit queries · HICO-DET (Default, Full)mAP: 32.60 -> 32.87Improved
use additive positional embeddings in cross-attention (ablation)PViC · HICO-DET (Default, Full)mAP: 33.59 -> 33.43No clear effect
concatenate positional embeddings (removing cross-terms) and modulate with box width/height (ablation)PViC · HICO-DET (Default, Full)mAP: 33.59 -> 33.91Improved
increase decoder layers beyond two (ablation)PViC · HICO-DET (Default, Full)mAP: 34.18 -> 34.03No clear effect
replace single-scale C5 with multiscale deformable cross-attention (ablation)PViC · HICO-DET (Default, Full)mAP: 34.18 -> 33.59Hurt

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