[Submitted on 30 Nov 2023 ( v1 ), last revised 6 Sep 2024 (this version, v3)] Title:DEVIAS: Learning Disentangled Video Representations of Action and Scene View a PDF of the paper titled DEVIAS: Learning Disentangled Video Representations of Action and Scene, by Kyungho Bae and 3 other authors View PDF HTML (experimental) Abstract:Video recognition models often learn scene-biased action representation due to the spurious correlation between actions and scenes in the training data.
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile