Video Action Understanding

TL;DR

This paper provides a comprehensive tutorial on supervised video action understanding, covering fundamental concepts, datasets, model architectures, and evaluation metrics to guide researchers in this complex field.

Contribution

It systematically organizes key topics, datasets, and methods in supervised video action understanding, offering a pedagogical guide for newcomers and researchers.

Findings

Clarifies taxonomy of action problems

Catalogs notable video datasets

Describes state-of-the-art model architectures

Abstract

Many believe that the successes of deep learning on image understanding problems can be replicated in the realm of video understanding. However, due to the scale and temporal nature of video, the span of video understanding problems and the set of proposed deep learning solutions is arguably wider and more diverse than those of their 2D image siblings. Finding, identifying, and predicting actions are a few of the most salient tasks in this emerging and rapidly evolving field. With a pedagogical emphasis, this tutorial introduces and systematizes fundamental topics, basic concepts, and notable examples in supervised video action understanding. Specifically, we clarify a taxonomy of action problems, catalog and highlight video datasets, describe common video data preparation methods, present the building blocks of state-of-the art deep learning model architectures, and formalize domain-specific metrics to baseline proposed solutions. This tutorial is intended to be accessible to a general computer science audience and assumes a conceptual understanding of supervised learning.