Alibaba has released a new AI model that can read emotions from video footage. The R1-Omni model uses computer vision to infer emotional states, including descriptions of clothing and surroundings. This development builds upon the HumanOmni model and aims to challenge OpenAI’s latest advancements in the field.
Source: https://www.bloomberg.com/news/articles/2025-03-12/alibaba-releases-emotional-intelligence-model-to-rival-chatgpt