Frequency Selective Augmentation for Video Representation Learning

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 46
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKim, Jinhyungko
dc.contributor.authorKim, Taeohko
dc.contributor.authorShim, Minhoko
dc.contributor.authorHan, Dongyoonko
dc.contributor.authorWee, Dongyoonko
dc.contributor.authorKim, Junmoko
dc.date.accessioned2023-12-05T12:01:30Z-
dc.date.available2023-12-05T12:01:30Z-
dc.date.created2023-11-29-
dc.date.issued2023-02-07-
dc.identifier.citation37th AAAI Conference on Artificial Intelligence, AAAI 2023, pp.1124 - 1132-
dc.identifier.urihttp://hdl.handle.net/10203/315775-
dc.description.abstractRecent self-supervised video representation learning methods focus on maximizing the similarity between multiple augmented views from the same video and largely rely on the quality of generated views. However, most existing methods lack a mechanism to prevent representation learning from bias towards static information in the video. In this paper, we propose frequency augmentation (FreqAug), a spatio-temporal data augmentation method in the frequency domain for video representation learning. FreqAug stochastically removes specific frequency components from the video so that learned representation captures essential features more from the remaining information for various downstream tasks. Specifically, FreqAug pushes the model to focus more on dynamic features rather than static features in the video via dropping spatial or temporal low-frequency components. To verify the generality of the proposed method, we experiment with FreqAug on multiple self-supervised learning frameworks along with standard augmentations. Transferring the improved representation to five video action recognition and two temporal action localization downstream tasks shows consistent improvements over baselines.-
dc.languageEnglish-
dc.publisherAAAI Press-
dc.titleFrequency Selective Augmentation for Video Representation Learning-
dc.typeConference-
dc.identifier.scopusid2-s2.0-85167712472-
dc.type.rimsCONF-
dc.citation.beginningpage1124-
dc.citation.endingpage1132-
dc.citation.publicationname37th AAAI Conference on Artificial Intelligence, AAAI 2023-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationWashington-
dc.contributor.localauthorKim, Junmo-
dc.contributor.nonIdAuthorKim, Jinhyung-
dc.contributor.nonIdAuthorKim, Taeoh-
dc.contributor.nonIdAuthorShim, Minho-
dc.contributor.nonIdAuthorHan, Dongyoon-
dc.contributor.nonIdAuthorWee, Dongyoon-
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0