Výsledky vyhledávání - "Jiang, Guilin"

Report

Stock Volatility Prediction Based on Transformer Model Using Mixed-Frequency Data

Autor: Liu, Wenting, Gui, Zhaozhong, Jiang, Guilin, Tang, Lihua, Zhou, Lichun, Leng, Wan, Zhang, Xulong, Liu, Yujiang

With the increasing volume of high-frequency data in the information age, both challenges and opportunities arise in the prediction of stock volatility. On one hand, the outcome of prediction using tradition method combining stock technical and macro

Externí odkaz: http://arxiv.org/abs/2309.16196

Zobrazit plný text záznamu

Report

An Empirical Study of Attention Networks for Semantic Segmentation

Autor: Guo, Hao, Si, Hongbiao, Jiang, Guilin, Zhang, Wei, Liu, Zhiyan, Zhu, Xuanyi, Zhang, Xulong, Liu, Yang

Semantic segmentation is a vital problem in computer vision. Recently, a common solution to semantic segmentation is the end-to-end convolution neural network, which is much more accurate than traditional methods.Recently, the decoders based on atten

Externí odkaz: http://arxiv.org/abs/2309.10217

Zobrazit plný text záznamu

Report

EdgeMA: Model Adaptation System for Real-Time Video Analytics on Edge Devices

Autor: Wang, Liang, Zhang, Nan, Qu, Xiaoyang, Wang, Jianzong, Wan, Jiguang, Li, Guokuan, Hu, Kaiyu, Jiang, Guilin, Xiao, Jing

Real-time video analytics on edge devices for changing scenes remains a difficult task. As edge devices are usually resource-constrained, edge deep neural networks (DNNs) have fewer weights and shallower architectures than general DNNs. As a result,

Externí odkaz: http://arxiv.org/abs/2308.08717

Zobrazit plný text záznamu

Report

Multi-QuartzNet: Multi-Resolution Convolution for Speech Recognition with Multi-Layer Feature Fusion

Autor: Luo, Jian, Wang, Jianzong, Cheng, Ning, Jiang, Guilin, Xiao, Jing

In this paper, we propose an end-to-end speech recognition network based on Nvidia's previous QuartzNet model. We try to promote the model performance, and design three components: (1) Multi-Resolution Convolution Module, replaces the original 1D tim

Externí odkaz: http://arxiv.org/abs/2011.13090

Zobrazit plný text záznamu

Report

End-to-end Silent Speech Recognition with Acoustic Sensing

Autor: Luo, Jian, Wang, Jianzong, Cheng, Ning, Jiang, Guilin, Xiao, Jing

Silent speech interfaces (SSI) has been an exciting area of recent interest. In this paper, we present a non-invasive silent speech interface that uses inaudible acoustic signals to capture people's lip movements when they speak. We exploit the speak

Externí odkaz: http://arxiv.org/abs/2011.11315

Zobrazit plný text záznamu