Work

Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification

Year: 2018

Type: conference-paper

Source: Lecture notes in computer science

Parent work: Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XV

DOI: 10.1007/978-3-030-01267-0_19

Authors: Saining Xie, Chen Sun, Jonathan Huang, Zhuowen Tu, Kevin Murphy

Institutions: Google (United States), University of California San Diego

Language: English

Topic: Human Pose and Action Recognition

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: RI: Small: Unraveling and Building Top-Down Generators in Deep Convolutional Neural Networks, RI:Small: Unsupervised Discriminatively-Generative Learning:

OpenAlex ID: W2883429621

FWCI: 44.7

Cites: 63

Cited by: 1,608

Related to: 10