Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey

Abstract

Video analysis tasks such as action recognition have received increasing research interest with growing applications in fields such as smart healthcare, thanks to the introduction of large-scale datasets and deep learning-based representations. However, video models trained on existing datasets suffer from significant performance degradation when deployed directly to real-world applications due to domain shifts between the training public video datasets (source video domains) and real-world videos (target video domains). Further, with the high cost of video annotation, it is more practical to use unlabeled videos for training. To tackle performance degradation and address concerns in high video annotation cost uniformly, the video unsupervised domain adaptation (VUDA) is introduced to adapt video models from the labeled source domain to the unlabeled target domain by alleviating video domain shift, improving the generalizability and portability of video models. This paper surveys recent progress in VUDA with deep learning. We begin with the motivation of VUDA, followed by its definition, and recent progress of methods for both closed-set VUDA and VUDA under different scenarios, and current benchmark datasets for VUDA research. Eventually, future directions are provided to promote further VUDA research. The repository of this survey is provided at https://github.com/xuyu0010/awesome-video-domain-adaptation.

Final version accepted by and to be published by ACM Computing Surveys (IF: 23.8 by 2023). Survey on Video Unsupervised Domain Adaptation (VUDA)

References in corpus (19)

• An Introduction to Variational Autoencoders
• Deep Visual Domain Adaptation: A Survey
• Unsupervised Data Augmentation for Consistency Training
• HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
• A New Representation of Skeleton Sequences for 3D Action Recognition
• The ApolloScape Open Dataset for Autonomous Driving and its Application
• A review of domain adaptation without target labels
• Generalizing to Unseen Domains via Adversarial Data Augmentation
• A Review on Deep Learning Techniques for Video Prediction
• TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning
• Space-Time Correspondence as a Contrastive Random Walk
• Generalization error bounds in semi-supervised classification under the cluster assumption
• Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice
• Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
• Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition
• Adversarial Bipartite Graph Learning for Video Domain Adaptation
• Online Adaptation to Label Distribution Shift
• Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing
• Transferable Time-Series Forecasting under Causal Conditional Shift

Cited by in corpus (1)

• DP2Unlearning: An Efficient and Guaranteed Unlearning Framework for LLMs