Search Results for author: Zhang

Found 26 papers, 7 papers with code

Physics-Inspired Deep Learning Anti-Aliasing Framework in Efficient Channel State Feedback

no code implementations12 Mar 2024 Yu-Chien Lin, Yan Xin, Ta-Sung Lee, Charlie, Zhang, Zhi Ding

Acquiring downlink channel state information (CSI) at the base station is vital for optimizing performance in massive Multiple input multiple output (MIMO) Frequency-Division Duplexing (FDD) systems.

Modeling Link-level Road Traffic Resilience to Extreme Weather Events Using Crowdsourced Data

no code implementations22 Oct 2023 Songhua Hu, Kailai Wang, Lingyao Li, Yingrui Zhao, Zhenbing He, Yunpeng, Zhang

Climate changes lead to more frequent and intense weather events, posing escalating risks to road traffic.

An Active Noise Control System Based on Soundfield Interpolation Using a Physics-informed Neural Network

1 code implementation19 Sep 2023 Yile, Zhang, Fei Ma, Thushara Abhayapala, Prasanga Samarasinghe, Amy Bastine

An ANC system is designed to take advantage of the interpolated signal to reduce noise signal within the ROI.

Leveraging Contextual Counterfactuals Toward Belief Calibration

no code implementations13 Jul 2023 Qiuyi, Zhang, Michael S. Lee, Sherol Chen

Beliefs and values are increasingly being incorporated into our AI systems through alignment processes, such as carefully curating data collection principles or regularizing the loss function used for training.

counterfactual Counterfactual Reasoning

Substructure Aware Graph Neural Networks

1 code implementation Proceedings of the AAAI Conference on Artificial Intelligence 2023 Zeng, D., Liu, Chen, W., Zhou, L., Zhang, M., & Qu, H

Despite the great achievements of Graph Neural Networks (GNNs) in graph learning, conventional GNNs struggle to break through the upper limit of the expressiveness of first-order Weisfeiler-Leman graph isomorphism test algorithm (1-WL) due to the consistency of the propagation paradigm of GNNs with the 1-WL. Based on the fact that it is easier to distinguish the original graph through subgraphs, we propose a novel framework neural network framework called Substructure Aware Graph Neural Networks (SAGNN) to address these issues.

Graph Learning Graph Regression

Research and Optimization of Heliostat Field Layout Based on Mixed Strategy Whale Optimization Algorithm

no code implementations 无 2022 Zhang, Hao

For the above problems, the new heliostatic field layout derived based on the idea of radiation grid layout and the no-occlusion principle is studied。At the same time, the detailed calculation process of the shadow occlusion efficiency is given in the process of establishing the optical efficiency model, and then the key parameters in the mirror field layout are optimized in combination with the intelligent optimization algorithm.


Leveraging Initial Hints for Free in Stochastic Linear Bandits

no code implementations8 Mar 2022 Ashok Cutkosky, Chris Dann, Abhimanyu Das, Qiuyi, Zhang

We study the setting of optimizing with bandit feedback with additional prior knowledge provided to the learner in the form of an initial hint of the optimal action.

Segmentation-Based vs. Regression-Based Biomarker Estimation: A Case Study of Fetus Head Circumference Assessment from Ultrasound Images

1 code implementation Journal of Imaging 2022 Zhang, Jing; Caroline Petitjean; and Samia Ainouz

Even if this type of segmentation-free approaches have been boosted with deep learning, it is not yet clear how well direct approach can compare to segmentation approaches, which are expected to be still more accurate.

2D Semantic Segmentation Computational Efficiency +2

The Implicit Values of A Good Hand Shake: Handheld Multi-Frame Neural Depth Refinement

1 code implementation CVPR 2022 Ilya Chugunov, Yuxuan Zhang, Zhihao Xia, Xuaner, Zhang, Jiawen Chen, Felix Heide

Modern smartphones can continuously stream multi-megapixel RGB images at 60Hz, synchronized with high-quality 3D pose information and low-resolution LiDAR-driven depth estimates.

Topological Structure and Semantic Information Transfer Network for Cross-Scene Hyperspectral Image Classification

1 code implementation journal 2021 Zhang, Yuxiang and Li, Wei and Zhang, Mengmeng and Qu, Ying and Tao, Ran and Qi, Hairong

The method employs the graph structure to characterize topological relationships and the graph convolutional network (GCN) that is good at processing for crossscene HSI classification.

Domain Adaptation Hyperspectral Image Classification

Time Series Anomaly Detection for Smart Grids: A Survey

no code implementations16 Jul 2021 Jiuqi, Zhang, Di wu, Benoit Boulet

With the rapid increase in the integration of renewable energy generation and the wide adoption of various electric appliances, power grids are now faced with more and more challenges.

Anomaly Detection Time Series +1

Roof Damage Assessment from Automated 3D Building Models

no code implementations4 Jun 2021 Kenichi Sugihara, Martin Wallace, Kongwen, Zhang, Youry Khmelevsky

Since technicians are drawing these polygons manually with digitizers, depending on aerial photos, not all building polygons are precisely orthogonal.

Locally Linear Region Knowledge Distillation

no code implementations9 Oct 2020 Xiang Deng, Zhongfei, Zhang

To the end, the student is able to better capture the local shape of the teacher function and thus achieves a better performance.

Knowledge Distillation

Deep Collective Learning: Learning Optimal Inputs and Weights Jointly in Deep Neural Networks

no code implementations17 Sep 2020 Xiang Deng, Zhongfei, Zhang

It is well observed that in deep learning and computer vision literature, visual data are always represented in a manually designed coding scheme (eg., RGB images are represented as integers ranging from 0 to 255 for each channel) when they are input to an end-to-end deep neural network (DNN) for any learning task.

Image Classification

GraphFederator: Federated Visual Analysis for Multi-party Graphs

no code implementations27 Aug 2020 Dongming Han, Wei Chen, Rusheng Pan, Yijing Liu, Jiehui Zhou, Ying Xu, Tianye Zhang, Changjie Fan, Jianrong Tao, Xiaolong, Zhang

This paper presents GraphFederator, a novel approach to construct joint representations of multi-party graphs and supports privacy-preserving visual analysis of graphs.

Human-Computer Interaction Cryptography and Security Graphics

DASC: Towards A Road Damage-Aware Social-Media-Driven Car Sensing Framework for Disaster Response Applications

no code implementations4 Jun 2020 Md Tahmid Rashid, Daniel, Zhang, Dong Wang

iii) How to efficiently guide the cars to the event locations with little prior knowledge of the road damage caused by the disaster, while also handling the dynamics of the physical world and social media?

Disaster Response

RCNet: Incorporating Structural Information into Deep RNN for MIMO-OFDM Symbol Detection with Limited Training

no code implementations15 Mar 2020 Zhou Zhou, Lingjia Liu, Shashank Jere, Jianzhong, Zhang, Yang Yi

In this paper, we investigate learning-based MIMO-OFDM symbol detection strategies focusing on a special recurrent neural network (RNN) -- reservoir computing (RC).


Multi-task Temporal Convolutional Network for Predicting Water Quality Sensor

1 code implementation International Conference on Neural Information Processing (ICONIP 2019) 2019 Zhang, Yifan; Thorburn, Peter; Fitch, Peter

Also, the changing patterns of several water quality variables can only be revealed by processing long term historical observations, which is not well supported by conventional data-driven models.

Management Time Series Prediction

A Joint Learning Framework With BERT for Spoken Language Understanding

no code implementations journal 2019 Zhang, ZC (Zhang, Zhichang) ; Zhang, ZW (Zhang, Zhenwen) ; Chen, HY (Chen, Haoyuan) ; Zhang, ZM (Zhang, Zhiman)

In this paper, we propose a novel encoder-decoder framework based multi-task learning model, which conducts joint training for intent classification and slot filling tasks.

Decoder intent-classification +6

Data-Free Point Cloud Network for 3D Face Recognition

no code implementations12 Nov 2019 Ziyu, Zhang, Feipeng, Da, Yi, Yu

To ease the inconsistent distribution between model data and real faces, different point sampling methods are used in train and test phase.

3D Object Classification Face Recognition +1

Deep Reinforcement Learning for Personalized Search Story Recommendation

no code implementations26 Jul 2019 Jason, Zhang, Junming Yin, Dongwon Lee, Linhong Zhu

In recent years, \emph{search story}, a combined display with other organic channels, has become a major source of user traffic on platforms such as e-commerce search platforms, news feed platforms and web and image search platforms.

Image Retrieval Imitation Learning +2

Zero-Shot Learning via Latent Space Encoding

no code implementations26 Dec 2017 Yunlong Yu, Zhong Ji, Jichang Guo, Zhongfei, Zhang

Instead of requiring a projection function to transfer information across different modalities like most previous work, LSE per- forms the interactions of different modalities via a feature aware latent space, which is learned in an implicit way.

Decoder Retrieval +1

Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-grained Air Quality

no code implementations2 Nov 2017 Zhongang Qi, Tianchun Wang, Guojie Song, Weisong Hu, Xi Li, Zhongfei, Zhang

The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of urban air computing.

feature selection

Machine Learning Based Detection of Clickbait Posts in Social Media

no code implementations5 Oct 2017 Xinyue Cao, Thai Le, Jason, Zhang

In this paper, we make use of a dataset from the clickbait challenge 2017 (clickbait-challenge. com) comprising of over 21, 000 headlines/titles, each of which is annotated by at least five judgments from crowdsourcing on how clickbait it is.

BIG-bench Machine Learning Clickbait Detection

Boosted Zero-Shot Learning with Semantic Correlation Regularization

no code implementations25 Jul 2017 Te Pi, Xi Li, Zhongfei, Zhang

For adaptable knowledge transfer, we devise a Semantic Correlation Regularization (SCR) approach to regularize the boosted model to be consistent with the inter-class semantic correlations.

Model Selection Transfer Learning +1

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