computer-vision-6
Human Interaction Recognition
3260 papers • 126 benchmarks • 313 datasets
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.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in human-interaction-recognition-6
Trend
Dataset
Best Model
Actions
UT
UT
BIT
BIT
SBU
SBU
Libraries
iUse these libraries to find human-interaction-recognition-6 models and implementations
Datasets
Subtasks
Most implemented papers
Interaction Relational Network for Mutual Action Recognition
Mauricio Perez, A. Kot, Jun Liu•Thu Oct 10 2019
This work proposes a simpler yet very powerful architecture, named Interaction Relational Network, which utilizes minimal prior knowledge about the structure of the human body to identify by itself how to relate the body parts from the individuals interacting and is capable of paramount sequential relational reasoning.
85
