Human Interaction Recognition

15 benchmarks22 papers

Human Interaction Recognition (HIR) is a field of study that involves the development of computer algorithms to detect and recognize human interactions in videos, images, or other multimedia content. The goal of HIR is to automatically identify and analyze the social interactions between people, their body language, and facial expressions.

Benchmarks

Human Interaction Recognition on NTU RGB+D 120

Accuracy (Cross-Setup)Accuracy (Cross-Subject)Accuracy

Human Interaction Recognition on NTU RGB+D

Accuracy (Cross-Subject)Accuracy (Cross-View)

Human Interaction Recognition on MOW

PrecisionRecallF1-Score

Human Interaction Recognition on UT

Accuracy

Human Interaction Recognition on BIT

Accuracy

Human Interaction Recognition on EPIC-SOUNDS

Top-1 accuracy %

Human Interaction Recognition on SBU

Accuracy

Human Interaction Recognition on SBU / SBU-Refine

Accuracy

Human Interaction Recognition on UT-Interaction

Accuracy (Set 1)Accuracy (Set 2)