AI Paper Atlas

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

Human-centric Relation Segmentation: Dataset and Solution

Sifeng Liu, Zitian Wang, Yulu Gao, Lejian Ren, Yue Liao, Guanghui Ren, Bo Hu Li, Shuicheng Yan

TPAMI 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 12 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 multi-level feature fusion on DLA-34 (ablation)SMS · PIC test, RSAR: 29.87 -> 30.08Improved
add multi-level feature fusion on ResNet-50 (ablation)SMS · PIC test, RSAR: 29.00 -> 29.97Improved
add multi-level feature fusion on ResNet-50 (ablation)SMS · PIC test, HRSAR: 19.08 -> 19.23Improved
add multi-level feature fusion on DLA-34 (ablation)SMS · PIC test, HRSAR: 19.73 -> 19.73No clear effect
use SOLOv2 instead of PolarMask for entity segmentation (ablation)SMS · PIC test, RSAR: 19.88 -> 29.87Improved
use SOLOv2 instead of SOLO for entity segmentation (ablation)SMS · PIC test, HRSAR: 18.11 -> 19.73Improved
estimate object offset in addition to subject offset (ablation)SMS · PIC test, RSAR: 29.71 -> 29.87No clear effect
estimate object offset in addition to subject offset (ablation)SMS · PIC test, HRSAR: 19.65 -> 19.73No clear effect
learned interacted part classification instead of most frequent part (ablation)SMS · PIC test, HRS actionAR: 10.66 -> 12.22Improved
learned interacted part classification instead of nearest part (ablation)SMS · PIC test, HRS actionAR: 9.08 -> 12.22Improved
larger model SMS-L instead of SMSSMS · PIC test, HRSAR: 19.23 -> 21.35Improved
use ResNet-50 instead of DLA-34 backboneSMS · PIC test, HRSAR: 19.73 -> 19.23Hurt

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