Attention Network
Attention networks are computational models designed to selectively focus on relevant information within large datasets, improving efficiency and accuracy in various tasks. Current research emphasizes developing adaptive and efficient attention mechanisms, particularly within large vision-language models and for handling complex data structures like CW-complexes and time series. These advancements are significantly impacting fields like medical image analysis, material science, and personalized medicine by enabling more accurate and efficient processing of high-dimensional data, leading to improved diagnostic tools and predictive models.
Papers
Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding
Tatsunori Taniai, Ryo Igarashi, Yuta Suzuki, Naoya Chiba, Kotaro Saito, Yoshitaka Ushiku, Kanta Ono
QEAN: Quaternion-Enhanced Attention Network for Visual Dance Generation
Zhizhen Zhou, Yejing Huo, Guoheng Huang, An Zeng, Xuhang Chen, Lian Huang, Zinuo Li
Hybrid Convolutional and Attention Network for Hyperspectral Image Denoising
Shuai Hu, Feng Gao, Xiaowei Zhou, Junyu Dong, Qian Du
Histo-Genomic Knowledge Distillation For Cancer Prognosis From Histopathology Whole Slide Images
Zhikang Wang, Yumeng Zhang, Yingxue Xu, Seiya Imoto, Hao Chen, Jiangning Song