Low-Fidelity Video Encoder Optimization for Temporal Action Localization

Mengmeng Xu*, Juan Manuel Pérez-Rúa, Xiatian Zhu, Bernard Ghanem, Brais Martinez

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

11 Scopus citations

Abstract

Most existing temporal action localization (TAL) methods rely on a transfer learning pipeline, first optimizing a video encoder on a large action classification dataset (i.e., source domain), followed by freezing the encoder and training a TAL head on the action localization dataset (i.e., target domain). This results in a task discrepancy problem for the video encoder – trained for action classification, but used for TAL. Intuitively, joint optimization with both the video encoder and TAL head is an obvious solution to this discrepancy. However, this is not operable for TAL subject to the GPU memory constraints, due to the prohibitive computational cost in processing long untrimmed videos. In this paper, we resolve this challenge by introducing a novel low-fidelity (LoFi) video encoder optimization method. Instead of always using the full training configurations in TAL learning, we propose to reduce the mini-batch composition in terms of temporal, spatial or spatio-temporal resolution so that jointly optimizing the video encoder and TAL head becomes operable under the same memory conditions of a mid-range hardware budget. Crucially, this enables the gradients to flow backwards through the video encoder conditioned on a TAL supervision loss, favourably solving the task discrepancy problem and providing more effective feature representations. Extensive experiments show that the proposed LoFi optimization approach can significantly enhance the performance of existing TAL methods. Encouragingly, even with a lightweight ResNet18 based video encoder in a single RGB stream, our method surpasses two-stream (RGB + optical flow) ResNet50 based alternatives, often by a good margin. Our code is publicly available at https://github.com/saic-fi/lofi_action_localization .

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
EditorsMarc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
PublisherNeural information processing systems foundation
Pages9923-9935
Number of pages13
ISBN (Electronic)9781713845393
StatePublished - 2021
Event35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online
Duration: Dec 6 2021Dec 14 2021

Publication series

NameAdvances in Neural Information Processing Systems
Volume12
ISSN (Print)1049-5258

Conference

Conference35th Conference on Neural Information Processing Systems, NeurIPS 2021
CityVirtual, Online
Period12/6/2112/14/21

Bibliographical note

Funding Information:
This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research through the Visual Computing Center (VCC) funding.

Publisher Copyright:
© 2021 Neural information processing systems foundation. All rights reserved.

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Low-Fidelity Video Encoder Optimization for Temporal Action Localization'. Together they form a unique fingerprint.

Cite this