Published August 17, 2021
| Version Published
Conference paper
Open
Emotion Recognition from 3D Motion Capture Data using Deep CNNs
- 1. Department of Computer Science University of Cyprus Nicosia, Cyprus
- 2. School of ICT Bahrain Polytechnic Bahrain
- 3. CYENS - CoE University of Cyprus Nicosia, Cyprus
Description
Creating detailed and interactive game environments is an area of great importance in the video game industry. This includes creating realistic Non-Player Characters which respond seamlessly to the players actions. Machine learning had great contributions to the area, overcoming scalability and robustness shortcomings of hand-scripted models. We introduce the early results of a reinforcement learning approach in building a simulation environment for heterogeneous, multi-agent nonplayer characters in a dynamic road network game scene.
Notes
Files
IEEE-COG2021-EmotionRecognition.pdf
Files
(828.2 kB)
Name | Size | Download all |
---|---|---|
md5:b3837fbcc1b4cf032015c1d992471677
|
828.2 kB | Preview Download |