Adversarial Domain Adaptation for Action Recognition Around the Clock
- Resource Type
- Conference
- Authors
- Ulhaq, Anwaar
- Source
- 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Digital Image Computing: Techniques and Applications (DICTA), 2022 International Conference on. :1-6 Nov, 2022
- Subject
- Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Adaptation models
Visualization
Image recognition
Surveillance
Digital images
Supervised learning
Adversarial machine learning
Task analysis
Unsupervised learning
Standards
- Language
Due to the numerous potential applications in visual surveillance and nighttime driving, recognizing human action in low-light conditions remains a difficult problem in computer vision. Existing methods separate action recognition and dark enhancement into two distinct steps to accomplish this task. However, isolating the recognition and enhancement impedes end-to-end learning of the space-time representation for video action classification. This paper presents a domain adaptation-based action recognition approach that uses adversarial learning in cross-domain settings to learn cross-domain action recognition. Supervised learning can train it on a large amount of labeled data from the source domain (daytime action sequences). However, it uses deep domain invariant features to perform unsupervised learning on many unlabelled data from the target domain (night-time action sequences). The resulting augmented model, named 3D-DiNet can be trained using standard backpropagation with an additional layer. It achieves SOTA performance on InFAR and XD145 actions datasets.