Search Results for author: Zhe Zhang

Found 40 papers, 6 papers with code

MTL-SLT: Multi-Task Learning for Spoken Language Tasks

no code implementations NLP4ConvAI (ACL) 2022 Zhiqi Huang, Milind Rao, Anirudh Raju, Zhe Zhang, Bach Bui, Chul Lee

The proposed framework benefits from three key aspects: 1) pre-trained sub-networks of ASR model and language model; 2) multi-task learning objective to exploit shared knowledge from different tasks; 3) end-to-end training of ASR and downstream NLP task based on sequence loss.

Automatic Speech Recognition Multi-Task Learning +2

PERT: A New Solution to Pinyin to Character Conversion Task

no code implementations24 May 2022 Jinghui Xiao, Qun Liu, Xin Jiang, Yuanfeng Xiong, Haiteng Wu, Zhe Zhang

Pinyin to Character conversion (P2C) task is the key task of Input Method Engine (IME) in commercial input software for Asian languages, such as Chinese, Japanese, Thai language and so on.

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network

no code implementations5 May 2022 Muhan Wang, Zhe Zhang, Yue Wang, Silin Gao, Xiaolan Qiu

Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations.

3D Reconstruction Super-Resolution

Robust Action Gap Increasing with Clipped Advantage Learning

no code implementations20 Mar 2022 Zhe Zhang, Yaozhong Gan, Xiaoyang Tan

Advantage Learning (AL) seeks to increase the action gap between the optimal action and its competitors, so as to improve the robustness to estimation errors.

Smoothing Advantage Learning

no code implementations20 Mar 2022 Yaozhong Gan, Zhe Zhang, Xiaoyang Tan

Advantage learning (AL) aims to improve the robustness of value-based reinforcement learning against estimation errors with action-gap-based regularization.

A Novel Gradient Descent Least Squares (GDLS) Algorithm for Efficient SMV Gridless Line Spectrum Estimation with Applications in Tomographic SAR Imaging

no code implementations16 Mar 2022 Ruizhe Shi, Zhe Zhang, Xiaolan Qiu, Chibiao Ding

Numerical simulations and real data experiments show that the proposed GDLS algorithm outperforms the state-of-the-art methods e. g., CS and ANM, in terms of estimation performances.

Optimal Methods for Risk Averse Distributed Optimization

no code implementations10 Mar 2022 Guanghui Lan, Zhe Zhang

We propose two distributed algorithms, namely the distributed risk averse optimization (DRAO) method and the distributed risk averse optimization with sliding (DRAO-S) method, to close the gap.

Distributed Optimization

Robust Semi-supervised Federated Learning for Images Automatic Recognition in Internet of Drones

no code implementations3 Jan 2022 Zhe Zhang, Shiyao Ma, Zhaohui Yang, Zehui Xiong, Jiawen Kang, Yi Wu, Kejia Zhang, Dusit Niyato

This emerging technology relies on sharing ground truth labeled data between Unmanned Aerial Vehicle (UAV) swarms to train a high-quality automatic image recognition model.

Federated Learning

Multi-View Stereo with Transformer

no code implementations1 Dec 2021 Jie Zhu, Bo Peng, Wanqing Li, Haifeng Shen, Zhe Zhang, Jianjun Lei

It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable matching for MVS.

Finite Sample Analysis of Average-Reward TD Learning and $Q$-Learning

no code implementations NeurIPS 2021 Sheng Zhang, Zhe Zhang, Siva Theja Maguluri

The focus of this paper is on sample complexity guarantees of average-reward reinforcement learning algorithms, which are known to be more challenging to study than their discounted-reward counterparts.

Q-Learning

Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Design

no code implementations26 Oct 2021 Zhe Zhang, Shiyao Ma, Jiangtian Nie, Yi Wu, Qiang Yan, Xiaoke Xu, Dusit Niyato

In this paper, we present a robust semi-supervised FL system design, where the system aims to solve the problem of data availability and non-IID in FL.

Federated Learning

The First Airborne Experiment of Sparse Microwave Imaging: Prototype System Design and Result Analysis

no code implementations20 Oct 2021 Zhe Zhang, Bingchen Zhang, Chenglong Jiang, Xingdong Liang, Longyong Chen, Wen Hong, Yirong Wu

In this paper we report the first airborne experiments of sparse microwave imaging, conducted in September 2013 and May 2014, using our prototype sparse microwave imaging radar system.

End-to-End Spoken Language Understanding using RNN-Transducer ASR

no code implementations30 Jun 2021 Anirudh Raju, Gautam Tiwari, Milind Rao, Pranav Dheram, Bryan Anderson, Zhe Zhang, Bach Bui, Ariya Rastrow

We propose an end-to-end trained spoken language understanding (SLU) system that extracts transcripts, intents and slots from an input speech utterance.

Automatic Speech Recognition Natural Language Understanding +1

BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices

no code implementations13 Apr 2021 Zhe Zhou, Bizhao Shi, Zhe Zhang, Yijin Guan, Guangyu Sun, Guojie Luo

At the hardware design level, we propose a pipelined CirCore architecture, which supports efficient block-circulant matrices computation.

Edge-computing

High-Dimensional Differentially-Private EM Algorithm: Methods and Near-Optimal Statistical Guarantees

no code implementations1 Apr 2021 Zhe Zhang, Linjun Zhang

In this paper, we develop a general framework to design differentially private expectation-maximization (EM) algorithms in high-dimensional latent variable models, based on the noisy iterative hard-thresholding.

Inheritance-guided Hierarchical Assignment for Clinical Automatic Diagnosis

no code implementations27 Jan 2021 Yichao Du, Pengfei Luo, Xudong Hong, Tong Xu, Zhe Zhang, Chao Ren, Yi Zheng, Enhong Chen

Clinical diagnosis, which aims to assign diagnosis codes for a patient based on the clinical note, plays an essential role in clinical decision-making.

Decision Making

MöbiusE: Knowledge Graph Embedding on Möbius Ring

no code implementations7 Jan 2021 Yao Chen, Jiangang Liu, Zhe Zhang, Shiping Wen, Wenjun Xiong

In this work, we propose a novel Knowledge Graph Embedding (KGE) strategy, called M\"{o}biusE, in which the entities and relations are embedded to the surface of a M\"{o}bius ring.

Knowledge Graph Embedding

Stabilizing Q Learning Via Soft Mellowmax Operator

no code implementations17 Dec 2020 Yaozhong Gan, Zhe Zhang, Xiaoyang Tan

Learning complicated value functions in high dimensional state space by function approximation is a challenging task, partially due to that the max-operator used in temporal difference updates can theoretically cause instability for most linear or non-linear approximation schemes.

Multi-agent Reinforcement Learning Q-Learning

Efficient Construction of Nonlinear Models over Normalized Data

no code implementations23 Nov 2020 Zhaoyue Chen, Nick Koudas, Zhe Zhang, Xiaohui Yu

For the case of NN, we propose algorithms to train the network taking normalized data as the input.

Optimal Algorithms for Convex Nested Stochastic Composite Optimization

no code implementations19 Nov 2020 Zhe Zhang, Guanghui Lan

However, In the current literature, there exists a significant gap in the iteration complexities between these NSCO problems and other simpler stochastic composite optimization problems (e. g., sum of smooth and nonsmooth functions) without the nested structure.

AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild

2 code implementations26 Oct 2020 Zhe Zhang, Chunyu Wang, Weichao Qiu, Wenhu Qin, Wenjun Zeng

To make the task truly unconstrained, we present AdaFuse, an adaptive multiview fusion method, which can enhance the features in occluded views by leveraging those in visible views.

Pose Estimation

Deep Learning for Wireless Coded Caching with Unknown and Time-Variant Content Popularity

no code implementations21 Aug 2020 Zhe Zhang, Meixia Tao

This approach, on one hand, can learn the caching policy in continuous action space by using the actor-critic architecture.

Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach

1 code implementation CVPR 2020 Zhe Zhang, Chunyu Wang, Wenhu Qin, Wen-Jun Zeng

Then we lift the multi-view 2D poses to the 3D space by an Orientation Regularized Pictorial Structure Model (ORPSM) which jointly minimizes the projection error between the 3D and 2D poses, along with the discrepancy between the 3D pose and IMU orientations.

3D Absolute Human Pose Estimation

3dDepthNet: Point Cloud Guided Depth Completion Network for Sparse Depth and Single Color Image

no code implementations20 Mar 2020 Rui Xiang, Feng Zheng, Huapeng Su, Zhe Zhang

In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks.

Autonomous Driving Depth Completion +1

Simple and Lightweight Human Pose Estimation

1 code implementation23 Nov 2019 Zhe Zhang, Jie Tang, Gangshan Wu

Specifically, our LPN-50 can achieve 68. 7 in AP score on the COCO test-dev set, with only 2. 7M parameters and 1. 0 GFLOPs, while the inference speed is 17 FPS on an Intel i7-8700K CPU machine.

Keypoint Detection

Leveraging Structural and Semantic Correspondence for Attribute-Oriented Aspect Sentiment Discovery

no code implementations IJCNLP 2019 Zhe Zhang, Munindar P. Singh

Opinionated text often involves attributes such as authorship and location that influence the sentiments expressed for different aspects.

Semantic correspondence

Multi-objective multi-generation Gaussian process optimizer for design optimization

1 code implementation29 Jun 2019 Xiaobiao Huang, Minghao Song, Zhe Zhang

We present a multi-objective evolutionary optimization algorithm that uses Gaussian process (GP) regression-based models to select trial solutions in a multi-generation iterative procedure.

TonY: An Orchestrator for Distributed Machine Learning Jobs

no code implementations24 Mar 2019 Anthony Hsu, Keqiu Hu, Jonathan Hung, Arun Suresh, Zhe Zhang

Training machine learning (ML) models on large datasets requires considerable computing power.

Limbic: Author-Based Sentiment Aspect Modeling Regularized with Word Embeddings and Discourse Relations

no code implementations EMNLP 2018 Zhe Zhang, Munindar Singh

We propose Limbic, an unsupervised probabilistic model that addresses the problem of discovering aspects and sentiments and associating them with authors of opinionated texts.

General Classification Semantic Similarity +4

Trifo-VIO: Robust and Efficient Stereo Visual Inertial Odometry using Points and Lines

no code implementations6 Mar 2018 Feng Zheng, Grace Tsai, Zhe Zhang, Shaoshan Liu, Chen-Chi Chu, Hongbing Hu

In this paper, we present the Trifo Visual Inertial Odometry (Trifo-VIO), a tightly-coupled filtering-based stereo VIO system using both points and lines.

PIRVS: An Advanced Visual-Inertial SLAM System with Flexible Sensor Fusion and Hardware Co-Design

no code implementations2 Oct 2017 Zhe Zhang, Shaoshan Liu, Grace Tsai, Hongbing Hu, Chen-Chi Chu, Feng Zheng

In this paper, we present the PerceptIn Robotics Vision System (PIRVS) system, a visual-inertial computing hardware with embedded simultaneous localization and mapping (SLAM) algorithm.

Simultaneous Localization and Mapping

Exploring compression techniques for ROOT IO

1 code implementation23 Apr 2017 Zhe Zhang, Brian Bockelman

ROOT provides an flexible format used throughout the HEP community.

Distributed, Parallel, and Cluster Computing

Learn-Memorize-Recall-Reduce A Robotic Cloud Computing Paradigm

no code implementations16 Apr 2017 Shaoshan Liu, Bolin Ding, Jie Tang, Dawei Sun, Zhe Zhang, Grace Tsai, Jean-Luc Gaudiot

The rise of robotic applications has led to the generation of a huge volume of unstructured data, whereas the current cloud infrastructure was designed to process limited amounts of structured data.

Identifying Significant Predictive Bias in Classifiers

no code implementations24 Nov 2016 Zhe Zhang, Daniel B. Neill

We present a novel subset scan method to detect if a probabilistic binary classifier has statistically significant bias -- over or under predicting the risk -- for some subgroup, and identify the characteristics of this subgroup.

Pyramid-based Visual Tracking Using Sparsity Represented Mean Transform

no code implementations CVPR 2014 Zhe Zhang, Kin Hong Wong

Firstly, we extend the original mean shift approach to handle orientation space and scale space and name this new method as mean transform.

Visual Tracking

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