Researchers have developed Transformer-based models to generate human motion in interactive scenarios, focusing on how one person's movement influences another's. They created a dataset from boxing videos to train and compare models like the simple Transformer, iTransformer, and Crossformer. The study found that a basic Transformer model, enhanced with person ID embeddings, effectively generated plausible, interaction-aware motions without posture collapse, outperforming more complex architectures that accumulated errors. AI
IMPACT Introduces a method for generating realistic, interaction-aware human motion, potentially impacting animation and virtual reality.
RANK_REASON Academic paper on a novel approach to human motion generation using Transformer models.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
