Skip to Main content Skip to Navigation
Conference papers

Contrastive predictive coding for video representation learning

Abstract : Contrastive Predictive Coding (CPC) (van den Oord et al., 2018) has been successfully used to learn representations for different signals (audio, text, images). It uses an autoregressive modeling and contrastive estimation to learn long-term temporal relation inside the raw signal while remaining robust to local noise. The result is a higher level signal representation useful to solve downstream tasks. Using CPC to learn representations for videos remains challenging due to the structure and the high dimensionality of the signal. In this work, we propose different implementations of CPC for video signal. The learned representation increases the performance of an action recognition classifier.
Document type :
Conference papers
Complete list of metadata

https://hal-cea.archives-ouvertes.fr/cea-03547497
Contributor : Rabarisoa Jaonary Connect in order to contact the contributor
Submitted on : Friday, January 28, 2022 - 3:35:27 PM
Last modification on : Friday, August 5, 2022 - 3:44:43 PM
Long-term archiving on: : Friday, April 29, 2022 - 9:30:47 PM

File

video_cpc.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : cea-03547497, version 1

Citation

Guillaume Lorre, Jaonary Rabarisoa, Astrid Orcesi, Samia Ainouz, Stéphane Canu. Contrastive predictive coding for video representation learning. ICML2019 - 36th International Conference on Machine Learning - Workshop on Self-Supervised Learning, Jun 2019, Long Beach, United States. ⟨cea-03547497⟩

Share

Metrics

Record views

106

Files downloads

106