Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition

Abstract

In recent years, a number of approaches based on 2D or 3D convolutional neural networks (CNN) have emerged for video action recognition, achieving state-of-the-art results on several large-scale benchmark datasets. In this paper, we carry out in-depth comparative analysis to better understand the differences between these approaches and the progress made by them. To this end, we develop an unified framework for both 2D-CNN and 3D-CNN action models, which enables us to remove bells and whistles and provides a common ground for fair comparison. We then conduct an effort towards a large-scale analysis involving over 300 action recognition models. Our comprehensive analysis reveals that a) a significant leap is made in efficiency for action recognition, but not in accuracy; b) 2D-CNN and 3DCNN models behave similarly in terms of spatio-temporal representation abilities and transferability.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 19, 2021
Accession Number
AD1151701

Entities

People

  • Aude Oliva
  • Chun-fu Chen
  • John Cohn
  • Kandan Ramakrishnan
  • Quanfu Fan
  • Rameswar Panda
  • Rogerio Feris

Organizations

  • Massachusetts Institute of Technology

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Computer Languages
  • Computer Programs
  • Computer Vision
  • Computers
  • Computing System Architectures
  • Convolution
  • Convolutional Neural Networks
  • Detection
  • Dimensionality Reduction
  • Image Recognition
  • Information Processing
  • Information Science
  • Machine Learning
  • Neural Networks
  • Object Recognition
  • Pattern Recognition
  • Recognition

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks