A Chinese Face Dataset with Dynamic Expressions and Diverse Ages Synthesized by Deep Learning
Shangfeng Han, Yanliang Guo, Xinyi Zhou, Junlong Huang, Linlin Shen, Yuejia Luo · 2023
Read A Chinese Face Dataset with Dynamic Expressions and Diverse Ages Synthesized by Deep Learning by Shangfeng Han, Yanliang Guo, Xinyi Zhou, Junlong Huang, Linlin Shen, Yuejia Luo (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10703811.txt.
Description
Shangfeng Han and co-authors build a made-up Chinese face set with deep-learn craft to fill gaps in stock sets. Past sets lean on still shots, lack age spread, and draw on few faces, since crowd shoots cost time and cash. Their 2023 set grows faces with a style net, in a spread of feels and ages. Slide blends of the net's code yield smooth feel shifts at set force tiers.
Judges rate the faces for feel kind and for three feel marks: cheer, buzz, and rule feel. Scores hold firm and true in the team's checks. A broad, cheap face set frees mood labs from shoot bounds. Mind labs gain a tool for tests on how folks read a face.
Catalog record
| CREATOR | Shangfeng Han, Yanliang Guo, Xinyi Zhou, Junlong Huang, Linlin Shen, Yuejia Luo |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 26 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |