AI Paper Atlas

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

Towards Context-Aware Interaction Recognition for Visual Relationship Detection

Bohan Zhuang, Lingqiao Liu, Chunhua Shen, Ian Reid

ICCV 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 162 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
use context-aware classifier instead of context-independent classifier (appearance) (ablation)Baseline1-app · VRD predicate detectionRecall@100: 18.13 -> 52.36Improved
use context-aware classifier instead of context-independent classifier (spatial) (ablation)Baseline1-spatial · VRD predicate detectionRecall@100: 17.77 -> 51.17Improved
use context-aware classifier instead of one class per interaction-context combination (spatial) (ablation)Baseline2-spatial · VRD predicate detectionRecall@100: 13.85 -> 51.17Improved
use context-aware classifier instead of one class per combination (appearance) (ablation)Baseline2-app · VRD predicate detectionRecall@100: 27.23 -> 52.36Improved
add attention pooling to context-aware appearance classifier (ablation)AP+C · VRD predicate detectionRecall@100: 52.36 -> 53.12Improved
make attention context-aware instead of direct attention (ablation)AP+C+AT · VRD predicate detectionRecall@100: 53.12 -> 53.59Improved
add context-aware attention to context-aware appearance classifier (ablation)AP+C · VRD relationship detectionRecall@100: 16.46 -> 17.39Improved
use appearance instead of spatial features in zero-shot predicate detectionSpatial+C · VRD zero-shot predicate detectionRecall@100: 16.42 -> 16.37Hurt
use context-aware classifier with spatial features in zero-shot setting (ablation)Baseline2-spatial · VRD zero-shot predicate detectionRecall@100: 0.43 -> 16.42Improved
add language priors to Faster-RCNN + AP+C+CAT (ablation)Faster-RCNN + (AP+C+CAT) · VRD relationship detectionRecall@50: 20.14 -> 20.35No clear effect
add context-aware attention to appearance classifier on Visual Phrase dataset zero-shot (ablation)AP+C · Visual Phrase dataset zero-shot phrase detectionRecall@50: 16.4 -> 18.7Improved

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