All attributes + SVM

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Visual Social Relationship RecognitiononPIPA
Accuracy· 2017-04-21
57.2
best: 66.7 (SocialGPT)
SOTA
A Domain Based Approach to Social Relation Recognition arXiv:1704.06456
Visual Social Relationship RecognitiononPIPA
Accuracy (domain)· 2017-04-21
67.8
best: 72.3 (GR2N)
SOTA
A Domain Based Approach to Social Relation Recognition arXiv:1704.06456