Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition

Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
Title:
Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
Other Titles:
CVPR2021 Workshop
DOI:
Publication URL:
Keywords:
Publication Date:
29 June 2021
Citation:
Yi Cheng, Fen Fang, Ying Sun, Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition, CVPR2021 Workshop, 29 June 2021
Abstract:
In this report, we present the technical details of our approach to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition. The EPIC-KITCHENS-100 dataset consists of daily kitchen activities focusing on the interaction between human hands and their surrounding objects. It is very challenging to accurately recognize these fine-grained activities, due to the presence of distracting objects and visually similar action classes, especially in the unlabelled target domain. Based on an existing method for video domain adaptation, i.e., TA3N, we propose to learn hand-centric features by leveraging the hand bounding box information for UDA on fine-grained action recognition. This helps reduce the distraction from background as well as facilitate the learning of domain-invariant features. To achieve high quality hand localization, we adopt an uncertainty-aware domain adaptation network, i.e., MEAA, to train a domain-adaptive hand detector, which only uses very limited hand bounding box annotations in the source domain but can generalize well to the unlabelled target domain. Our submission achieved the 1st place in terms of top-1 action recognition accuracy, using only RGB and optical flow modalities as input.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - AME Programmatic Funding Scheme
Grant Reference no. : A18A2b0046
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:
1063-6919
Files uploaded:

File Size Format Action
epic-kitchens-2021-report-cameraready-v2.pdf 1.41 MB PDF Request a copy