Faster, Smaller, and Simpler Model for Multiple Facial Attributes Transformation

Autor: Jonathan Hans Soeseno, Daniel Stanley Tan, Wen-Yin Chen, Kai-Lung Hua

Publikováno v: IEEE Access, Vol 7, Pp 36400-36412 (2019)

There are many existing models that are capable of changing hair color or changing facial expressions. These models are typically implemented as deep neural networks that require a large number of computations in order to perform the transformations.

Externí odkaz: https://doaj.org/article/b6e6260f9168483990256f0abb61160b

Controllable and Identity-Aware Facial Attribute Transformation

Autor: Jonathan Hans Soeseno, Kai-Lung Hua, Daniel Stanley Tan

Publikováno v: IEEE Transactions on Cybernetics, 52(6), 4825-4836. IEEE Advancing Technology for Humanity
Tan, D S, Soeseno, J H & Hua, K-L 2022, ' Controllable and Identity-Aware Facial Attribute Transformation ', IEEE Transactions on Cybernetics, vol. 52, no. 6, pp. 4825-4836 . https://doi.org/10.1109/TCYB.2021.3071172

Modifying facial attributes without the paired dataset proves to be a challenging task. Previously, approaches either required supervision from a ground-truth transformed image or required training a separate model for mapping every pair of attribute

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2091920518598fe37c385b9088799e89
https://doi.org/10.1109/tcyb.2021.3071172

CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion

Autor: Jonathan Hans Soeseno, Trista Pei-Chun Chen, Wei-Chao Chen, Ying-Sheng Luo

Motion synthesis in a dynamic environment has been a long-standing problem for character animation. Methods using motion capture data tend to scale poorly in complex environments because of their larger capturing and labeling requirement. Physics-bas

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f4fe3da3ca4aa59ac91d2151bab25b46
http://arxiv.org/abs/2005.03288