Kinetics-400

anchor

Findings

• IC-194Temporal modeling in video models drives representational alignment to early visual cortex, while action classification task drives alignment to late brain areas [source]
• IC-195Transformers achieve high brain alignment in early visual cortex at much shallower network depth than CNNs [source]
• IC-196Models trained on Something-Something-V2 (which contains no faces) show reduced alignment with face-selective FFA compared to the same models trained on Kinetics-400 [source]
• IC-197Model computational complexity (FLOPs) shows a significant negative correlation with brain alignment in high-level brain areas [source]