High Frequency
High-frequency analysis focuses on extracting information from rapidly changing signals or data, aiming to improve accuracy and efficiency in various applications. Current research emphasizes leveraging frequency domain information alongside spatial or temporal data, employing techniques like wavelet transforms, Fourier transforms, and specialized neural network architectures such as Transformers and Graph Neural Networks. This approach is proving valuable across diverse fields, including financial modeling (high-frequency trading), image processing (super-resolution, compression), and signal processing (noise reduction, medical imaging), leading to improved model performance and more efficient algorithms.
Papers
FTMoMamba: Motion Generation with Frequency and Text State Space Models
Chengjian Li, Xiangbo Shu, Qiongjie Cui, Yazhou Yao, Jinhui Tang
TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba
Xiaowen Ma, Zhenliang Ni, Xinghao Chen
MFF-FTNet: Multi-scale Feature Fusion across Frequency and Temporal Domains for Time Series Forecasting
Yangyang Shi, Qianqian Ren, Yong Liu, Jianguo Sun
HC$^3$L-Diff: Hybrid conditional latent diffusion with high frequency enhancement for CBCT-to-CT synthesis
Shi Yin, Hongqi Tan, Li Ming Chong, Haofeng Liu, Hui Liu, Kang Hao Lee, Jeffrey Kit Loong Tuan, Dean Ho, Yueming Jin
DPCL-Diff: The Temporal Knowledge Graph Reasoning based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive Learning
Yukun Cao, Lisheng Wang, Luobing Huang