loading page

Tiny Video Networks
  • AJ Piergiovanni,
  • Anelia Angelova,
  • Michael Ryoo
AJ Piergiovanni
Google Inc

Corresponding Author:ajpiergi@google.com

Author Profile
Anelia Angelova
Google Inc
Author Profile
Michael Ryoo
Google Inc
Author Profile

Abstract

Automatic video understanding is becoming more important for applications where real-time performance is crucial and compute is limited. Yet, accurate solutions so far have been computationally intensive. We propose efficient models for videos - Tiny Video Networks - which are video architectures, automatically designed to comply with fast runtimes and, at the same time are effective at video recognition tasks. The Tiny Video Networks run at faster-than-real-time speeds and demonstrate strong performance across several video benchmarks. These models not only provide new tools for real-time video applications, but also enable fast research and development in video understanding. Code and models are available.
11 Jul 2021Submitted to Applied AI Letters
12 Jul 2021Submission Checks Completed
12 Jul 2021Assigned to Editor
21 Jul 2021Reviewer(s) Assigned
26 Aug 2021Review(s) Completed, Editorial Evaluation Pending
26 Aug 2021Editorial Decision: Revise Minor
01 Sep 20211st Revision Received
02 Sep 2021Submission Checks Completed
02 Sep 2021Assigned to Editor
03 Sep 2021Reviewer(s) Assigned
28 Sep 2021Review(s) Completed, Editorial Evaluation Pending
28 Sep 2021Editorial Decision: Accept
Feb 2022Published in Applied AI Letters volume 3 issue 1. 10.1002/ail2.38