A Closer Look at Spatiotemporal Convolutions for Action Recognition

Computer Vision and Pattern Recognition (CVPR)


In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition. In this work we empirically demonstrate the accuracy advantages of 3D CNNs over 2D CNNs within the framework of residual learning. Furthermore, we show that factorizing the 3D convolutional filters into separate spatial and temporal components yields significantly gains in accuracy. Our empirical study leads to the design of a new spatiotemporal convolutional block “R(2+1)D” which produces CNNs that achieve results comparable or superior to the state-of-the-art on Sports-1M, Kinetics, UCF101, and HMDB51.

Related Publications

All Publications

Towards Generalization Across Depth for Monocular 3D Object Detection

Andrea Simonelli, Samuel Rota Bulò, Lorenzo Porzi, Elisa Ricci, Peter Kontschieder

ECCV - August 22, 2020

The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale

Christian Ertler, Jerneja Mislej, Tobias Ollmann, Lorenzo Porzi, Gerhard Neuhold, Yubin Kuang

ECCV - August 23, 2020

TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video

Tiancheng Zhi, Christoph Lassner, Tony Tung, Carsten Stoll, Srinivasa G. Narasimhan, Minh Vo

ECCV - August 21, 2020

Spatially Aware Multimodal Transformers for TextVQA

Yash Kant, Dhruv Batra, Peter Anderson, Alexander Schwing, Devi Parikh, Jiasen Lu, Harsh Agrawal

ECCV - August 23, 2020

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy