AI Paper Atlas

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

HCVRD: A Benchmark for Large-Scale Human-Centered Visual Relationship Detection

Bohan Zhuang, Qi Wu, Chunhua Shen, Ian Reid, Anton van den Hengel

AAAI 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 47 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 learned metric learning module (ablation)WSRD · HCVRD non-zero-shotpredicate det. R@50 top-1: 22.55 -> 31.08Improved
add web-crawled data (ablation)WSRD · HCVRD long-tail subsetpredicate det. R@50 top-1: 18.01 -> 24.55Improved
add noise filtering of web data (ablation)WSRD · HCVRD non-zero-shotpredicate det. R@50 top-1: 30.36 -> 31.08Improved
metric learning with web data vs SeparateCNNWSRD · HCVRD non-zero-shotpredicate det. R@50 top-1: 29.00 -> 31.08Improved
metric learning with web data vs classification baselinesWSRD · HCVRD non-zero-shotrelationship det. R@50 top-1: 0.21 -> 0.53Improved
WSRD vs SeparateCNN in zero-shotWSRD · HCVRD zero-shotpredicate det. R@50 top-1: 2.75 -> 8.15Improved

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