Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network

Page view(s)
21
Checked on Oct 16, 2023
Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network
Title:
Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network
Journal Title:
2021 IEEE/CVF International Conference on Computer Vision
DOI:
Publication URL:
Keywords:
Publication Date:
17 October 2021
Citation:
Xu, Y., Yang, J., Cao, H. et al. Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network. Proceedings of the IEEE/CVF International Conference on Computer Vision. (2021)
Abstract:
Partial Domain Adaptation (PDA) is a practical and general domain adaptation scenario, which relaxes the fully shared label space assumption such that the source label space subsumes the target one. The key challenge of PDA is the issue of negative transfer caused by source-only classes. For videos, such negative transfer could be triggered by both spatial and temporal features, which leads to a more challenging Partial Video Domain Adaptation (PVDA) problem. In this paper, we propose a novel Partial Adversarial Temporal Attentive Network (PATAN) to address the PVDA problem by utilizing both spatial and temporal features for filtering source-only classes. Besides, PATAN constructs effective overall temporal features by attending to local temporal features that contribute more toward the class filtration process. We further introduce new benchmarks to facilitate research on PVDA problems, covering a wide range of PVDA scenarios. Empirical results demonstrate the state-of-the-art performance of our proposed PATAN across the multiple PVDA benchmarks.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic Funds
Grant Reference no. : A20H6b0151
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
ISSN:
N/A
Files uploaded:


File Size Format Action
07404.pdf 4.50 MB PDF Open
07404-supp.pdf 11.41 MB PDF Open