DeepAI AI Chat
Log In Sign Up

Channel-Temporal Attention for First-Person Video Domain Adaptation

by   Xianyuan Liu, et al.
The University of Sheffield

Unsupervised Domain Adaptation (UDA) can transfer knowledge from labeled source data to unlabeled target data of the same categories. However, UDA for first-person action recognition is an under-explored problem, with lack of datasets and limited consideration of first-person video characteristics. This paper focuses on addressing this problem. Firstly, we propose two small-scale first-person video domain adaptation datasets: ADL_small and GTEA-KITCHEN. Secondly, we introduce channel-temporal attention blocks to capture the channel-wise and temporal-wise relationships and model their inter-dependencies important to first-person vision. Finally, we propose a Channel-Temporal Attention Network (CTAN) to integrate these blocks into existing architectures. CTAN outperforms baselines on the two proposed datasets and one existing dataset EPIC_cvpr20.


page 5

page 11


Learning Temporal Consistency for Source-Free Video Domain Adaptation

Video-based Unsupervised Domain Adaptation (VUDA) methods improve the ro...

EXTERN: Leveraging Endo-Temporal Regularization for Black-box Video Domain Adaptation

To enable video models to be applied seamlessly across video tasks in di...

Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022

In this report, we present the technical details of our submission to th...

CycDA: Unsupervised Cycle Domain Adaptation from Image to Video

Although action recognition has achieved impressive results over recent ...

Unsupervised clothing change adaptive person ReID

Clothing changes and lack of data labels are both crucial challenges in ...