multi-model-learning

Here are 2 public repositories matching this topic...

ly-zhu / cof-net

Code for the paper: Visually Guided Sound Source Separation using Cascaded Opponent Filter Network

self-supervised-learning sound-source-localization audio-visual-learning sound-source-separation audio-visual-sound-separation multi-model-learning

Updated Apr 19, 2022
Python

amramer / Personality-Aware-Non-verbal-Behavior-Generation

Star

A multimodal transformer that generates personality-aware listener avatars (facial expressions, body and hand gestures) in dyadic conversations. Built with PyTorch using VQ-VAE and transformers, trained on UDIVA. Beats a personality-agnostic baseline on FID and P-FID, and 86% of study participants identified the extroverted avatar.

deep-learning transformers pytorch affective-computing data-pipeline personality gesture-recognition facial-expressions computer-vison human-motion smpl-x human-motion-prediction motion-generation vision-transformers multi-model-learning virtual-avatars generative-ai human-motion-generation

Updated Oct 13, 2026
Python

Add this topic to your repo

To associate your repository with the multi-model-learning topic, visit your repo's landing page and select "manage topics."

Learn more