Search Results for author: Jie Zhu

Found 36 papers, 12 papers with code

融合目标端句法的AMR-to-Text生成(AMR-to-Text Generation with Target Syntax)

no code implementations CCL 2020 Jie Zhu, Junhui Li

抽象语义表示到文本(AMR-to-Text)生成的任务是给定AMR图, 生成相同语义表示的文本。可以把此任务当作一个从源端AMR图到目标端句子的机器翻译任务。目前存在的一些方法都在探索如何更好的对图结构进行建模。然而, 它们都存在一个未限定的问题, 因为在生成阶段许多句法的决策并不受语义图的约束, 从而忽略了句子内部潜藏的句法信息。为了明确考虑这一不足, 该文提出一种直接而有效的方法, 显示的在AMR-to-Text生成的任务中融入句法信息, 并在Transformer和目前该任务最优性能的模型上进行了实验。实验结果表明, 在现存的两份标准英文数据集LDC2018E86和LDC2017T10上, 都取得了显著的提升, 达到了新的最高性能。

AMR-to-Text Generation Text Generation

VSANet: Real-time Speech Enhancement Based on Voice Activity Detection and Causal Spatial Attention

no code implementations11 Oct 2023 Yuewei Zhang, Huanbin Zou, Jie Zhu

The deep learning-based speech enhancement (SE) methods always take the clean speech's waveform or time-frequency spectrum feature as the learning target, and train the deep neural network (DNN) by reducing the error loss between the DNN's output and the target.

Action Detection Activity Detection +2

Magnitude-and-phase-aware Speech Enhancement with Parallel Sequence Modeling

no code implementations11 Oct 2023 Yuewei Zhang, Huanbin Zou, Jie Zhu

In speech enhancement (SE), phase estimation is important for perceptual quality, so many methods take clean speech's complex short-time Fourier transform (STFT) spectrum or the complex ideal ratio mask (cIRM) as the learning target.

Speech Enhancement

Learning to Rank Onset-Occurring-Offset Representations for Micro-Expression Recognition

no code implementations7 Oct 2023 Jie Zhu, Yuan Zong, Jingang Shi, Cheng Lu, Hongli Chang, Wenming Zheng

This paper focuses on the research of micro-expression recognition (MER) and proposes a flexible and reliable deep learning method called learning to rank onset-occurring-offset representations (LTR3O).

Learning-To-Rank Micro Expression Recognition +1

ATM: Action Temporality Modeling for Video Question Answering

no code implementations5 Sep 2023 Junwen Chen, Jie Zhu, Yu Kong

Despite significant progress in video question answering (VideoQA), existing methods fall short of questions that require causal/temporal reasoning across frames.

Contrastive Learning Optical Flow Estimation +2

Understanding Self-Supervised Pretraining with Part-Aware Representation Learning

no code implementations27 Jan 2023 Jie Zhu, Jiyang Qi, Mingyu Ding, Xiaokang Chen, Ping Luo, Xinggang Wang, Wenyu Liu, Leye Wang, Jingdong Wang

The study is mainly motivated by that random views, used in contrastive learning, and random masked (visible) patches, used in masked image modeling, are often about object parts.

Contrastive Learning Representation Learning

Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment

1 code implementation11 Aug 2022 Jie Zhu, Leye Wang, Xiao Han

By simulating the attack mechanism as the safety test, SafeCompress can automatically compress a big model to a small one following the dynamic sparse training paradigm.

Inference Attack Membership Inference Attack +2

Psychologically-Inspired Music Recommendation System

no code implementations6 May 2022 Danila Rozhevskii, Jie Zhu, Boyuan Zhao

In the last few years, automated recommendation systems have been a major focus in the music field, where companies such as Spotify, Amazon, and Apple are competing in the ability to generate the most personalized music suggestions for their users.

Music Recommendation Recommendation Systems

Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localization

no code implementations18 Mar 2022 Kangbo Sun, Jie Zhu

In the second stage, we propose a simple and effective method for evaluating the confidence of pseudo-labels based on classification discrimination, and by learning consistency from high-quality pseudo-labels, we further refine the localization network to get better localization performance.

Pseudo Label Weakly-Supervised Object Localization

Sky Computing: Accelerating Geo-distributed Computing in Federated Learning

1 code implementation24 Feb 2022 Jie Zhu, Shenggui Li, Yang You

In this paper, we proposed Sky Computing, a load-balanced model parallelism framework to adaptively allocate the weights to devices.

Distributed Computing Federated Learning

Merging Control Strategies of Connected and Autonomous Vehicles at Freeway On-Ramps: A Comprehensive Review

no code implementations18 Feb 2022 Jie Zhu, Said Easa, Kun Gao

This paper presents a comprehensive review of the existing ramp merging strategies leveraging CAVs, focusing on the latest trends and developments in the research field.

Autonomous Vehicles

Flow-level Coordination of Connected and Autonomous Vehicles in Multilane Freeway Ramp Merging Areas

no code implementations18 Feb 2022 Jie Zhu, Ivana Tasic, Xiaobo Qu

The strategy is formulated under an optimization framework, where the optimal control plan is determined based on real-time traffic conditions.

Autonomous Vehicles

E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation

1 code implementation14 Dec 2021 Jie Zhu, Huabin Huang, Banghuai Li, Leye Wang

In this paper, we notice that the class weights of categories that tend to share many adjacent boundary pixels lack discrimination, thereby limiting the performance.

Metric Learning Model Optimization +2

MSP : Refine Boundary Segmentation via Multiscale Superpixel

no code implementations3 Dec 2021 Jie Zhu, Huabin Huang, Banghuai Li, Yong liu, Leye Wang

Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map.

Scene Parsing Segmentation +1

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.

Simple Recurrent Neural Networks is all we need for clinical events predictions using EHR data

1 code implementation3 Oct 2021 Laila Rasmy, Jie Zhu, Zhiheng Li, Xin Hao, Hong Thoai Tran, Yujia Zhou, Firat Tiryaki, Yang Xiang, Hua Xu, Degui Zhi

As a result, deep learning models developed for sequence modeling, like recurrent neural networks (RNNs) are common architecture for EHR-based clinical events predictive models.

Bayesian Optimization

Continuous Treatment Recommendation with Deep Survival Dose Response Function

no code implementations24 Aug 2021 Jie Zhu, Blanca Gallego

We propose a general formulation for continuous treatment recommendation problems in settings with clinical survival data, which we call the Deep Survival Dose Response Function (DeepSDRF).

Selection bias

Improving Freeway Merging Efficiency via Flow-Level Coordination of Connected and Autonomous Vehicles

no code implementations4 Aug 2021 Jie Zhu, Ivana Tasic, Xiaobo Qu

Freeway on-ramps are typical bottlenecks in the freeway network due to the frequent disturbances caused by their associated merging, weaving, and lane-changing behaviors.

Autonomous Vehicles

Einstein-Podolsky-Rosen Steering in Two-sided Sequential Measurements with One Entangled Pair

no code implementations4 Feb 2021 Jie Zhu, Meng-Jun Hu, Guang-Can Guo, Chuan-Feng Li, Yong-Sheng Zhang

Non-locality sharing amongmultiple observers is predicted and experimentally observed.

Quantum Physics

Diagonalization of Hamiltonian for finite-sized dispersive media: Canonical quantization with numerical mode-decomposition (CQ-NMD)

no code implementations28 Jan 2021 Dong-Yeop Na, Jie Zhu, Weng Cho Chew

We present a new math-physics modeling approach, called canonical quantization with numerical mode-decomposition, for capturing the physics of how incoming photons interact with finite-sized dispersive media, which is not describable by the previous Fano-diagonalization methods.

Quantization Quantum Physics

CDS -- Causal Inference with Deep Survival Model and Time-varying Covariates

1 code implementation26 Jan 2021 Jie Zhu, Blanca Gallego

Causal inference in longitudinal observational health data often requires the accurate estimation of treatment effects on time-to-event outcomes in the presence of time-varying covariates.

Causal Inference Recommendation Systems +1

Dynamic prediction of time to event with survival curves

no code implementations26 Jan 2021 Jie Zhu, Blanca Gallego

With the ever-growing complexity of primary health care system, proactive patient failure management is an effective way to enhancing the availability of health care resource.

counterfactual Management +1

Category Disentangled Context: Turning Category-irrelevant Features Into Treasures

no code implementations1 Jan 2021 Keke Tang, Guodong Wei, Jie Zhu, Yuexin Ma, Runnan Chen, Zhaoquan Gu, Wenping Wang

Deep neural networks have achieved great success in computer vision, thanks to their ability in extracting category-relevant semantic features.

Image Classification

Probability-Density-Based Deep Learning Paradigm for the Fuzzy Design of Functional Metastructures

1 code implementation11 Nov 2020 Ying-Tao Luo, Peng-Qi Li, Dong-Ting Li, Yu-Gui Peng, Zhi-Guo Geng, Shu-Huan Xie, Yong Li, Andrea Alu, Jie Zhu, Xue-Feng Zhu

In quantum mechanics, a norm squared wave function can be interpreted as the probability density that describes the likelihood of a particle to be measured in a given position or momentum.

Targeted Estimation of Heterogeneous Treatment Effect in Observational Survival Analysis

1 code implementation20 Oct 2019 Jie Zhu, Blanca Gallego

The aim of clinical effectiveness research using repositories of electronic health records is to identify what health interventions 'work best' in real-world settings.

Causal Inference Survival Analysis

Modeling Graph Structure in Transformer for Better AMR-to-Text Generation

1 code implementation IJCNLP 2019 Jie Zhu, Junhui Li, Muhua Zhu, Longhua Qian, Min Zhang, Guodong Zhou

Recent studies on AMR-to-text generation often formalize the task as a sequence-to-sequence (seq2seq) learning problem by converting an Abstract Meaning Representation (AMR) graph into a word sequence.

AMR-to-Text Generation Text Generation

Contribution of Radio Halos to the Foreground for SKA EoR Experiments

4 code implementations14 May 2019 Weitian Li, Haiguang Xu, Zhixian Ma, Dan Hu, Zhenghao Zhu, Chenxi Shan, Jingying Wang, Junhua Gu, Dongchao Zheng, Xiaoli Lian, Qian Zheng, Yu Wang, Jie Zhu, Xiang-Ping Wu

The overwhelming foreground contamination is one of the primary impediments to probing the EoR through measuring the redshifted 21 cm signal.

Cosmology and Nongalactic Astrophysics

Separating the EoR Signal with a Convolutional Denoising Autoencoder: A Deep-learning-based Method

1 code implementation25 Feb 2019 Weitian Li, Haiguang Xu, Zhixian Ma, Ruimin Zhu, Dan Hu, Zhenghao Zhu, Junhua Gu, Chenxi Shan, Jie Zhu, Xiang-Ping Wu

When applying the foreground removal methods to uncover the faint cosmological signal from the epoch of reionization (EoR), the foreground spectra are assumed to be smooth.


Attending Category Disentangled Global Context for Image Classification

no code implementations17 Dec 2018 Keke Tang, Guodong Wei, Runnan Chen, Jie Zhu, Zhaoquan Gu, Wenping Wang

In this paper, we propose a general framework for image classification using the attention mechanism and global context, which could incorporate with various network architectures to improve their performance.

Classification General Classification +1

Radio Galaxy Morphology Generation Using DNN Autoencoder and Gaussian Mixture Models

1 code implementation1 Jun 2018 Zhixian Ma, Jie Zhu, Weitian Li, Haiguang Xu

In this work, we propose a morphology generation framework for two typical radio galaxies namely Fanaroff-Riley type-I (FRI) and type-II (FRII) with deep neural network based autoencoder (DNNAE) and Gaussian mixture models (GMMs).

Recurrent Binary Embedding for GPU-Enabled Exhaustive Retrieval from Billion-Scale Semantic Vectors

no code implementations18 Feb 2018 Ying Shan, Jian Jiao, Jie Zhu, JC Mao

Building on top of the powerful concept of semantic learning, this paper proposes a Recurrent Binary Embedding (RBE) model that learns compact representations for real-time retrieval.

Information Retrieval Retrieval

Deep Embedding Forest: Forest-based Serving with Deep Embedding Features

no code implementations15 Mar 2017 Jie Zhu, Ying Shan, JC Mao, Dong Yu, Holakou Rahmanian, Yi Zhang

Built on top of a representative DNN model called Deep Crossing, and two forest/tree-based models including XGBoost and LightGBM, a two-step Deep Embedding Forest algorithm is demonstrated to achieve on-par or slightly better performance as compared with the DNN counterpart, with only a fraction of serving time on conventional hardware.

X-ray Astronomical Point Sources Recognition Using Granular Binary-tree SVM

no code implementations7 Mar 2017 Zhixian Ma, Weitian Li, Lei Wang, Haiguang Xu, Jie Zhu

An approach to recognize the point sources (PS) in the X-ray astronomical images using our newly designed granular binary-tree support vector machine (GBT-SVM) classifier is proposed.

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