Search Results for author: Rui Zhou

Found 29 papers, 6 papers with code

MATRIX: Multi-Agent Trajectory Generation with Diverse Contexts

no code implementations9 Mar 2024 Zhuo Xu, Rui Zhou, Yida Yin, Huidong Gao, Masayoshi Tomizuka, Jiachen Li

Data-driven methods have great advantages in modeling complicated human behavioral dynamics and dealing with many human-robot interaction applications.

Data Augmentation Motion Planning

Mel-FullSubNet: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR

no code implementations21 Feb 2024 Rui Zhou, Xian Li, Ying Fang, Xiaofei Li

In this work, we propose Mel-FullSubNet, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

A Novel Field-Free SOT Magnetic Tunnel Junction With Local VCMA-Induced Switching

no code implementations24 Dec 2023 Rui Zhou, Haiyang Zhang, Hao Wang, Jin He, Qijun Huang, Sheng Chang

By integrating the local voltage-controlled magnetic anisotropy (VCMA) effect, Dzyaloshinskii-Moriya interaction (DMI) effect, and spin-orbit torque (SOT) effect, we propose a novel device structure for field-free magnetic tunnel junction (MTJ).

Network Topology Inference with Sparsity and Laplacian Constraints

no code implementations2 Sep 2023 Jiaxi Ying, Xi Han, Rui Zhou, Xiwen Wang, Hing Cheung So

We tackle the network topology inference problem by utilizing Laplacian constrained Gaussian graphical models, which recast the task as estimating a precision matrix in the form of a graph Laplacian.

Time Series

End-to-End Lane detection with One-to-Several Transformer

2 code implementations1 May 2023 Kunyang Zhou, Rui Zhou

We first propose the one-to-several label assignment, which combines one-to-many and one-to-one label assignment to solve label semantic conflicts while keeping end-to-end detection.

Lane Detection

Multi-Exposure HDR Composition by Gated Swin Transformer

no code implementations15 Mar 2023 Rui Zhou, Yan Niu

Fusing a sequence of perfectly aligned images captured at various exposures, has shown great potential to approach High Dynamic Range (HDR) imaging by sensors with limited dynamic range.

feature selection Image Generation

Multi-modal Machine Learning in Engineering Design: A Review and Future Directions

no code implementations14 Feb 2023 Binyang Song, Rui Zhou, Faez Ahmed

In the rapidly advancing field of multi-modal machine learning (MMML), the convergence of multiple data modalities has the potential to reshape various applications.

Cross-Modal Information Retrieval Design Synthesis +2

CAB: Empathetic Dialogue Generation with Cognition, Affection and Behavior

1 code implementation3 Feb 2023 Pan Gao, Donghong Han, Rui Zhou, Xuejiao Zhang, Zikun Wang

For behavior, we use appropriate dialogue acts to guide the dialogue generation to enhance the empathy expression.

Dialogue Generation

A novel automatic wind power prediction framework based on multi-time scale and temporal attention mechanisms

no code implementations2 Feb 2023 Meiyu Jiang, Jun Shen, XueTao Jiang, Lihui Luo, Rui Zhou, Qingguo Zhou

Accurate wind power forecasting is crucial for developing a new power system that heavily relies on renewable energy sources.

A Data Quality Assessment Framework for AI-enabled Wireless Communication

no code implementations13 Dec 2022 Hanning Tang, Liusha Yang, Rui Zhou, Jing Liang, Hong Wei, Xuan Wang, Qingjiang Shi, Zhi-Quan Luo

Using artificial intelligent (AI) to re-design and enhance the current wireless communication system is a promising pathway for the future sixth-generation (6G) wireless network.

Speech Dereverberation with a Reverberation Time Shortening Target

1 code implementation20 Oct 2022 Rui Zhou, Wenye Zhu, Xiaofei Li

The proposed RTS target suppresses reverberation and meanwhile maintains the exponential decaying property of reverberation, which will ease the network training, and thus reduce signal distortion caused by the prediction error.

Denoising Speech Denoising +1

PVT-COV19D: Pyramid Vision Transformer for COVID-19 Diagnosis

no code implementations30 Jun 2022 Lilang Zheng, Jiaxuan Fang, Xiaorun Tang, Hanzhang Li, Jiaxin Fan, Tianyi Wang, Rui Zhou, Zhaoyan Yan

A large number of experiments on the COV19-CT-DB dataset demonstrate the effectiveness of the proposed method.

COVID-19 Diagnosis

Efficient and Scalable Parametric High-Order Portfolios Design via the Skew-t Distribution

1 code implementation6 Jun 2022 Xiwen Wang, Rui Zhou, Jiaxi Ying, Daniel P. Palomar

Initially, profit and risk were measured by the first two moments of the portfolio's return, a. k. a.

Portfolio Optimization

Speech Dereverberation with A Reverberation Time Shortening Target

no code implementations19 Apr 2022 Rui Zhou, Wenye Zhu, Xiaofei Li

The proposed RTS target suppresses reverberation and meanwhile maintains the exponential decaying property of reverberation, which will ease the network training, and thus reduce signal distortion caused by the prediction error.

Denoising Speech Denoising +1

Boundary Distribution Estimation for Precise Object Detection

no code implementations2 Nov 2021 Peng Zhi, Haoran Zhou, Hang Huang, Rui Zhao, Rui Zhou, Qingguo Zhou

In the field of state-of-the-art object detection, the task of object localization is typically accomplished through a dedicated subnet that emphasizes bounding box regression.

Object object-detection +4

Grouptron: Dynamic Multi-Scale Graph Convolutional Networks for Group-Aware Dense Crowd Trajectory Forecasting

no code implementations29 Sep 2021 Rui Zhou, HongYu Zhou, Huidong Gao, Masayoshi Tomizuka, Jiachen Li, Zhuo Xu

Accurate, long-term forecasting of pedestrian trajectories in highly dynamic and interactive scenes is a long-standing challenge.

Trajectory Forecasting

A General Framework for Revealing Human Mind with auto-encoding GANs

no code implementations10 Feb 2021 Pan Wang, Rui Zhou, Shuo Wang, Ling Li, Wenjia Bai, Jialu Fan, Chunlin Li, Peter Childs, Yike Guo

For this reason, we propose an end-to-end brain decoding framework which translates brain activity into an image by latent space alignment.

Brain Decoding

Searching Personalized $k$-wing in Large and Dynamic Bipartite Graphs

no code implementations4 Jan 2021 Aman Abidi, Lu Chen, Rui Zhou, Chengfei Liu

By exploiting the discoveries, we propose novel algorithms for maintaining the two indices, which substantially reduces the cost of maintenance.

Dynamic optimal reinsurance and dividend-payout in finite time horizon

no code implementations2 Aug 2020 Chonghu Guan, Zuo Quan Xu, Rui Zhou

This paper studies a dynamic optimal reinsurance and dividend-payout problem for an insurance company in a finite time horizon.

Early Detection of Retinopathy of Prematurity (ROP) in Retinal Fundus Images Via Convolutional Neural Networks

no code implementations12 Jun 2020 Xin Guo, Yusuke Kikuchi, Guan Wang, Jinglin Yi, Qiong Zou, Rui Zhou

Retinopathy of prematurity (ROP) is an abnormal blood vessel development in the retina of a prematurely-born infant or an infant with low birth weight.

Specificity

Efficient Deep Representation Learning by Adaptive Latent Space Sampling

no code implementations19 Mar 2020 Yuanhan Mo, Shuo Wang, Chengliang Dai, Rui Zhou, Zhongzhao Teng, Wenjia Bai, Yike Guo

Supervised deep learning requires a large amount of training samples with annotations (e. g. label class for classification task, pixel- or voxel-wised label map for segmentation tasks), which are expensive and time-consuming to obtain.

General Classification Image Classification +2

Index-based Solutions for Efficient Density Peak Clustering

no code implementations8 Feb 2020 Zafaryab Rasool, Rui Zhou, Lu Chen, Chengfei Liu, Jiajie Xu

Efficient query algorithms are proposed for these indices which significantly avoids irrelevant comparisons at the cost of space.

Clustering

Predicting Destinations by a Deep Learning based Approach

no code implementations IEEE Transactions on Knowledge and Data Engineering 2019 Jiajie Xu, Jing Zhao, Rui Zhou, Chengfei Liu

However, the standard attention mechanism uses fixed feature representations, and has a limited ability to represent distinct features of locations.

Cannot find the paper you are looking for? You can Submit a new open access paper.