Intel Labs at The Winter Conference on Applications of Computer Vision

Intel presents five computer vision papers that detail novel works that include a Dynamic Scene Graph Detection Transformer, a Fast Learnable Once-for-all Adversarial Training method, a method for quantizing convolutional neural networks for efficient training, face access models applied in a hypothetical social network, and a novel non-local self-attentive pooling method.  

Ce contenu a été publié dans Non classé. Vous pouvez le mettre en favoris avec ce permalien.

Laisser un commentaire