Posted 2022-10-16Updated 2022-10-24researcha minute read (About 128 words)

Text-Conditioned Motion Generation

Advisor: Wangmeng Zuo, Professor at Harbin Institute of Technology

• The Hydra library is used for the parsing, and the dataset splits utilize the same splits as in Language2Pose (train /Val / test).
• Redefining the parameters that fit the SMPL dataset to the model resulted in the creation of a new dataset.
• By combining several motion-sequence embeddings using transformers, it is possible to encode the VAE’s distribution parameters as in.
• Sampling from a learned distribution function of motion lengths conditional on the input text, we subsequently use a temporal variant autoencoder to synthesize a set of human actions of different lengths.
• Use the diffusion model to enhance the quality of the generated animation when generating human animation.

Companion Chat System Based on Multi-Virtual Actors

Advisor: Wei-Nan Zhang, Associate Professor at Harbin Institute of Technology

• Based on BERT model, our model was successfully lightened and patented, with a performance loss of no more than 5%.
• Spring Boot, MySQL, MyBatis, Shiro, WebSocket, etc. are used to implement the backend service system.
• The gRPC framework is used to provide quick data transfer between the backend service system and our NLP model.
• Won the China International “Internet+” College Students Innovation and Entrepreneurship Competition, “ICAN” International Contest of innovation and “Challenge Cup” University Student Entrepreneurship Program Competition.