AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Self-Supervised Social Relation Representation for Human Group Detection

Jiacheng Li, Ruize Han, Haomin Yan, Zekun Qian, Wei Feng, Song Wang

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 13 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 self-supervised behavior-simulator first-stage training (ablation)two-stage group detector · PANDA group detectionF1 (%): 44.6 -> 53.2Improved
add self-supervised behavior-simulator first-stage training (ablation)two-stage group detector · JRDB-Group group detectionF1 (%): 48.8 -> 56.9Improved
add fine-tuning of the embedding network in stage 2 (ablation)two-stage group detector · PANDA group detectionF1 (%): 51.1 -> 53.2Improved
add fine-tuning of the embedding network in stage 2 (ablation)two-stage group detector · JRDB-Group group detectionF1 (%): 49.2 -> 56.9Improved
add self-supervised first stage when only 10% of labels are used (ablation)two-stage group detector · PANDA group detection (10% train)F1 (%): 27.6 -> 40.9Improved
add self-supervised first stage; 10% labels vs 50% labels without it (ablation)two-stage group detector · PANDA group detection (10% vs 50% train)F1 (%): 39.8 -> 40.9Improved
freeze the embedding network (no fine-tuning) with only 10% labels (ablation)two-stage group detector · JRDB-Group group detection (10% train)F1 (%): 37 and 43.8Improved
use proposed method instead of best baseline ARGARG · PANDA group detectionF1 (%): 25.4 -> 53.2Improved
use proposed method instead of JRDB-Group baselineJRDB-Group baseline · JRDB-Group group detectionF1 (%): 38.4 -> 56.9Improved
use proposed method instead of simple distance baselines under IOU^GMDis.Mat + label propagation · JRDB-Group group detectionIOU^GM (%): 12.9 -> 32.5Improved

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