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.
-
-
Articles récents
-
Neural networks news
Intel NN News
- AI Technology: What Do You Need to Get Started?
Enterprises will need a full AI technology stack to maintain competitive advantage, but few have […]
- Looking Forward to RSAC 2025
The RSAC 2025 conference is just around the corner, where companies show how they use Intel […]
- Intel Presents Cutting-Edge AI Research at ICLR 2025
Intel is pleased to present 10 main conference papers, five workshop papers and leading the […]
- AI Technology: What Do You Need to Get Started?
-