LG-GER: Language-guided group emotion recognition via multimodal distillation
arXiv paper introduces LG-GER, a method for group emotion recognition (GER) that integrates faces, poses, interactions, and scene context via multimodal evidence distillation. It uses language guidance to improve inference of collective emotional states from a single image.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Prompt search tool indexes 10,000+ image generation prompts
- Judge refuses to toss indie musician's lawsuit against Suno
- Nvidia sells first H200 chips in China, shipments below allowed total
- Model company acquisitions discussed
- Apple's Luce generates relightable 3D assets from single images