Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis. (arXiv:2304.10073v2 [cs.CV] UPDATED)

How can we teach a computer to recognize 10,000 different actions? Deep
learning has evolved from supervised and unsupervised to self-supervised
approaches. In this paper, we present a new contrastive learning-based
framework for decision tree-based classification of actions, including
human-human interactions (HHI) and human-object interactions (HOI). The key
idea is to translate the original multi-class action recognition into a series
of binary classification tasks on a pre-constructed decision tree. Under the
new framework of contrastive learning, we present the design …

arxiv autism binary class action classification computer decision decision trees deep learning design diagnosis framework human human interactions interactions matrix paper recognition series the key translate tree trees unsupervised video