Multi-Source Video Domain Adaptation With Temporal Attentive Moment Alignment Network

Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios, which relaxes the assumption in conventional Unsupervised Domain Adaptation (UDA) that source data are sampled from a single domain and match a uniform data distribution. The MSDA is more ch...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems for video technology 2023-08, Vol.33 (8), p.3860-3871
Main Authors: Xu, Yuecong, Yang, Jianfei, Cao, Haozhi, Wu, Keyu, Wu, Min, Li, Zhengguo, Chen, Zhenghua
Format: Article
Language:English
Subjects:
action recognition
Adaptation
Alignment
Benchmark testing
Benchmarks
dataset
Feature extraction
Kinetic theory
Measurement
moment alignment
Multi-source
Neural networks
Task analysis
Training
video domain adaptation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios, which relaxes the assumption in conventional Unsupervised Domain Adaptation (UDA) that source data are sampled from a single domain and match a uniform data distribution. The MSDA is more challenging due to the existence of different domain shifts between distinct domain pairs. When considering videos, the negative transfer would be provoked by spatial-temporal features and can be formulated into a more challenging Multi-Source Video Domain Adaptation (MSVDA) problem. In this paper, we address the MSVDA problem by proposing a novel Temporal Attentive Moment Alignment Network (TAMAN) which aims for effective feature transfer by dynamically aligning both spatial and temporal feature moments. The TAMAN further constructs robust global temporal features by attending to dominant domain-invariant local temporal features with high local classification confidence and low disparity between global and local feature discrepancies. To facilitate future research on the MSVDA problem, we introduce comprehensive benchmarks, covering extensive MSVDA scenarios. Empirical results demonstrate a superior performance of the proposed TAMAN across multiple MSVDA benchmarks.
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2023.3234307