atlas

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

What To Look at and Where: Semantic and Spatial Refined Transformer for Detecting Human-Object Interactions

CVPR 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 52 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Replace QPIC with SSRTHOI detection with ResNet-50 · V-COCO Scenario 1mAP: 58.79 -> 63.73Helped
Use SSRT instead of QPICHOI detection with ResNet-50 · V-COCO Scenario 1, read-objAP: 35.76 -> 51.80 (+16.04)Helped
Use SSRT instead of QPICHOI detection with ResNet-50 · V-COCO Scenario 1, drink-instrAP: 44.26 -> 55.69 (+11.43)Helped
Use SSRT instead of QPICHOI detection with ResNet-50 · V-COCO Scenario 1, talk-on-phone-instrAP: 40.26 -> 51.65 (+11.39)Helped
Use SSRT instead of QPICHOI detection with ResNet-50 · V-COCO Scenario 1, cut-instrAP: 38.07 -> 47.34 (+9.27)Helped
Use SSRT instead of QPICHOI detection with ResNet-50 · V-COCO Scenario 1, eat-objAP: 58.80 -> 66.61 (+7.81)Helped

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