M.‐X. Tang

Pose Matters: Evaluating Vision Transformers and CNNs for Human Action Recognition on Small COCO Subsets

2025 · arXiv (Cornell University)

This study explores human action recognition using a three-class subset of the COCO image corpus, benchmarking models from simple fully connected networks to transformer architectures. The binary Vision Transformer (ViT) achieved 90% mean test accuracy, …