Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances-Reference-Cited by-同舟云学术

Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances

Published:2023-05-29 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE International Conference on Robotics and Automation (ICRA)
language:
Short-container-title:

Author:

Reddy Arun V.¹,Shah Ketul¹,Paul William²,Mocharla Rohita²,Hoffman Judy³,Katyal Kapil D.²,Manocha Dinesh⁴,de Melo Celso M.⁵,Chellappa Rama¹

Affiliation:

1. Johns Hopkins University,Dept. of Electrical & Computer Engineering,Baltimore,MD,USA

2. Johns Hopkins University Applied Physics Lab,Laurel,MD,USA

3. Georgia Institute of Technology,Atlanta,GA,USA

4. University of Maryland,College Park,MD,USA

5. Army Research Lab,Adelphi,MD,USA

Funder

Army Research Laboratory (ARL)

Publisher

IEEE

Link

Reference59 articles.

3. Adapting visual category models to new domains;saenko;European Conference on Computer Vision,0

5. Cycada: Cycle-consistent adversarial domain adaptation;hoffman;Int Conference on Machine Learning,0

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Enhancing human action recognition with GAN-based data augmentation;Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II;2024-06-07

2. Real-time human action recognition from aerial videos using autozoom and synthetic data;Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II;2024-06-07

3. An evaluation of large pre-trained models for gesture recognition using synthetic videos;Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II;2024-06-07