Search Results for author: Chao Zhang

Found 148 papers, 49 papers with code

Transferring SLU Models in Novel Domains

no code implementations ICLR 2019 Yaohua Tang, Kaixiang Mo, Qian Xu, Chao Zhang, Qiang Yang

When building models for novel natural language domains, a major challenge is the lack of data in the new domains, no matter whether the data is annotated or not.

Meta-Learning Slot Filling +2

HRFormer: High-Resolution Transformer for Dense Prediction

1 code implementation18 Oct 2021 Yuhui Yuan, Rao Fu, Lang Huang, WeiHong Lin, Chao Zhang, Xilin Chen, Jingdong Wang

We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and computational cost.

Pose Estimation Semantic Segmentation

Self-Training with Differentiable Teacher

no code implementations15 Sep 2021 Simiao Zuo, Yue Yu, Chen Liang, Haoming Jiang, Siawpeng Er, Chao Zhang, Tuo Zhao, Hongyuan Zha

In self-training, the student contributes to the prediction performance, and the teacher controls the training process by generating pseudo-labels.

Named Entity Recognition Weakly Supervised Classification

CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting

1 code implementation15 Sep 2021 Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez, Chao Zhang, B. Aditya Prakash

We use CAMul for multiple domains with varied sources and modalities and show that CAMul outperforms other state-of-art probabilistic forecasting models by over 25\% in accuracy and calibration.

Decision Making Probabilistic Time Series Forecasting +1

Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks

no code implementations13 Sep 2021 Chunzhi Gu, Yan Zhao, Chao Zhang

Human motion prediction, which plays a key role in computer vision, generally requires a past motion sequence as input.

Human motion prediction motion prediction

Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework

no code implementations11 Sep 2021 Yaqing Wang, Haoda Chu, Chao Zhang, Jing Gao

In this work, we study the problem of named entity recognition (NER) in a low resource scenario, focusing on few-shot and zero-shot settings.

Few-Shot Learning Named Entity Recognition +2

Training Algorithm Matters for the Performance of Neural Network Potential

no code implementations8 Sep 2021 Yunqi Shao, Florian M. Dietrich, Carl Nettelblad, Chao Zhang

One hidden yet important issue for developing neural network potentials (NNPs) is the choice of training algorithm.

IEEE BigData 2021 Cup: Soft Sensing at Scale

1 code implementation7 Sep 2021 Sergei Petrov, Chao Zhang, Jaswanth Yella, Yu Huang, Xiaoye Qian, Sthitie Bom

The scope of this challenge is to tackle the task of classifying soft sensing data with machine learning techniques.

Auto-encoder based Model for High-dimensional Imbalanced Industrial Data

no code implementations4 Aug 2021 Chao Zhang, Sthitie Bom

However, the successful applications of deep learning in soft sensing are still not widely integrated in factory control systems, because most of the research on soft sensing do not have access to large scale industrial data which are varied, noisy and incomplete.

Representation Learning Sensor Modeling

Towards Making Deep Learning-based Vulnerability Detectors Robust

1 code implementation2 Aug 2021 Zhen Li, Jing Tang, Deqing Zou, Qian Chen, Shouhuai Xu, Chao Zhang, Yichen Li, Hai Jin

Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention.

Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition

no code implementations29 Jul 2021 Xianrui Zheng, Chao Zhang, Philip C. Woodland

Furthermore, on the AMI corpus, the proposed conversion for language prior probabilities enables BERT to obtain an extra 3% relative WERR, and the combination of BERT, GPT and GPT-2 results in further improvements.

automatic-speech-recognition Speech Recognition

Combining Frame-Synchronous and Label-Synchronous Systems for Speech Recognition

1 code implementation1 Jul 2021 Qiujia Li, Chao Zhang, Philip C. Woodland

Commonly used automatic speech recognition (ASR) systems can be classified into frame-synchronous and label-synchronous categories, based on whether the speech is decoded on a per-frame or per-label basis.

automatic-speech-recognition Speech Recognition

GAN-MDF: A Method for Multi-fidelity Data Fusion in Digital Twins

no code implementations24 Jun 2021 Lixue Liu, Chao Zhang, DaCheng Tao

Multi-fidelity data fusion (MDF) methods aims to use massive LF samples and small amounts of HF samples to develop an accurate and efficient model for describing the system with a reasonable computation burden.

Positive-Unlabeled Data Purification in the Wild for Object Detection

no code implementations CVPR 2021 Jianyuan Guo, Kai Han, Han Wu, Chao Zhang, Xinghao Chen, Chunjing Xu, Chang Xu, Yunhe Wang

In this paper, we present a positive-unlabeled learning based scheme to expand training data by purifying valuable images from massive unlabeled ones, where the original training data are viewed as positive data and the unlabeled images in the wild are unlabeled data.

Knowledge Distillation Object Detection

Image Deformation Estimation via Multi-Objective Optimization

no code implementations8 Jun 2021 Takumi Nakane, Xuequan Lu, Haoran Xie, Chao Zhang

Specifically, by partitioning the template image into several regions and measuring the similarity of each region independently, multiple objectives are built and deformation estimation can thus be realized by solving the MOP with off-the-shelf multi-objective evolutionary algorithms (MOEAs).

When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting

1 code implementation7 Jun 2021 Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez, Chao Zhang, B. Aditya Prakash

We model the forecasting task as a probabilistic generative process and propose a functional neural process model called EPIFNP, which directly models the probability density of the forecast value.

Time Series Time Series Forecasting

Decision-making Oriented Clustering: Application to Pricing and Power Consumption Scheduling

no code implementations2 Jun 2021 Chao Zhang, Samson Lasaulce, Martin Hennebel, Lucas Saludjian, Patrick Panciatici, H. Vincent Poor

For this purpose, we formulate the framework of decision-making oriented clustering and propose an algorithm providing a decision-based partition of the data space and good representative decisions.

Decision Making

A Federated Learning Framework for Nonconvex-PL Minimax Problems

no code implementations29 May 2021 Jiahao Xie, Chao Zhang, Yunsong Zhang, Zebang Shen, Hui Qian

We consider a general class of nonconvex-PL minimax problems in the cross-device federated learning setting.

Federated Learning

BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition

1 code implementation ACL 2021 Yinghao Li, Pranav Shetty, Lucas Liu, Chao Zhang, Le Song

To address this challenge, we propose a conditional hidden Markov model (CHMM), which can effectively infer true labels from multi-source noisy labels in an unsupervised way.

Named Entity Recognition NER +1

Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model

1 code implementation8 May 2021 Lingwei Peng, Hui Qian, Zhebang Shen, Chao Zhang, Fei Li

Model-free deep reinforcement learning has achieved great success in many domains, such as video games, recommendation systems and robotic control tasks.

Continuous Control Recommendation Systems

DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning

no code implementations23 Apr 2021 Sheldon Fung, Xuequan Lu, Chao Zhang, Chang-Tsun Li

Extensive experiments show that our unsupervised learning method enables comparable detection performance to state-of-the-art supervised techniques, in both the intra- and inter-dataset settings.

Contrastive Learning DeepFake Detection +1

Sketch-based Normal Map Generation with Geometric Sampling

no code implementations23 Apr 2021 Yi He, Haoran Xie, Chao Zhang, Xi Yang, Kazunori Miyata

This paper proposes a deep generative model for generating normal maps from users sketch with geometric sampling.

Real-time Forecast Models for TBM Load Parameters Based on Machine Learning Methods

no code implementations12 Apr 2021 Xianjie Gao, Xueguan Song, Maolin Shi, Chao Zhang, Hongwei Zhang

In this paper, based on in-situ TBM operational data, we use the machine-learning (ML) methods to build the real-time forecast models for TBM load parameters, which can instantaneously provide the future values of the TBM load parameters as long as the current data are collected.

A Riemannian smoothing steepest descent method for non-Lipschitz optimization on submanifolds

no code implementations9 Apr 2021 Chao Zhang, Xiaojun Chen, Shiqian Ma

In this paper, we propose a Riemannian smoothing steepest descent method to minimize a nonconvex and non-Lipschitz function on submanifolds.

Semantic Scene Completion via Integrating Instances and Scene in-the-Loop

no code implementations CVPR 2021 Yingjie Cai, Xuesong Chen, Chao Zhang, Kwan-Yee Lin, Xiaogang Wang, Hongsheng Li

The key insight is that we decouple the instances from a coarsely completed semantic scene instead of a raw input image to guide the reconstruction of instances and the overall scene.

indoor scene understanding Scene Understanding

A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training

no code implementations12 Mar 2021 Adnan Haider, Chao Zhang, Florian L. Kreyssig, Philip C. Woodland

This paper presents a novel natural gradient and Hessian-free (NGHF) optimisation framework for neural network training that can operate efficiently in a distributed manner.

automatic-speech-recognition Speech Recognition

Using Cognitive Models to Train Warm Start Reinforcement Learning Agents for Human-Computer Interactions

no code implementations10 Mar 2021 Chao Zhang, Shihan Wang, Henk Aarts, Mehdi Dastani

Reinforcement learning (RL) agents in human-computer interactions applications require repeated user interactions before they can perform well.

Multi-cell NOMA: Coherent Reconfigurable Intelligent Surfaces Model With Stochastic Geometry

no code implementations3 Mar 2021 Chao Zhang, Wenqiang Yi, Yuanwei Liu, Qiang Wang

Numerical results indicate that 1) although the interference from other cells is enhanced via the RISs, the performance of the RIS-aided user still enhances since the channel quality is strengthened more obviously; and 2) the SIC order can be altered by employing the RISs since the RISs improve the channel quality of the aided user.

Information Theory Information Theory

Self-Adaptive Training: Bridging the Supervised and Self-Supervised Learning

1 code implementation21 Jan 2021 Lang Huang, Chao Zhang, Hongyang Zhang

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training process by model predictions without incurring extra computational cost -- to advance both supervised and self-supervised learning of deep neural networks.

Representation Learning Self-Supervised Learning

Hybrid Quantum-Classical Graph Convolutional Network

no code implementations15 Jan 2021 Samuel Yen-Chi Chen, Tzu-Chieh Wei, Chao Zhang, Haiwang Yu, Shinjae Yoo

This research provides a hybrid quantum-classical graph convolutional network (QGCNN) for learning HEP data.

Quantum Machine Learning

Theory-based Habit Modeling for Enhancing Behavior Prediction

no code implementations5 Jan 2021 Chao Zhang, Joaquin Vanschoren, Arlette van Wissen, Daniel Lakens, Boris de Ruyter, Wijnand A. IJsselsteijn

Psychological theories of habit posit that when a strong habit is formed through behavioral repetition, it can trigger behavior automatically in the same environment.

Quantum Convolutional Neural Networks for High Energy Physics Data Analysis

no code implementations22 Dec 2020 Samuel Yen-Chi Chen, Tzu-Chieh Wei, Chao Zhang, Haiwang Yu, Shinjae Yoo

This work presents a quantum convolutional neural network (QCNN) for the classification of high energy physics events.

Quantum Machine Learning

Partial Gromov-Wasserstein Learning for Partial Graph Matching

no code implementations2 Dec 2020 Weijie Liu, Chao Zhang, Jiahao Xie, Zebang Shen, Hui Qian, Nenggan Zheng

Graph matching finds the correspondence of nodes across two graphs and is a basic task in graph-based machine learning.

Graph Matching

Deep Discriminative Feature Learning for Accent Recognition

1 code implementation25 Nov 2020 Wei Wang, Chao Zhang, Xiaopei Wu

Accent recognition with deep learning framework is a similar work to deep speaker identification, they're both expected to give the input speech an identifiable representation.

Face Recognition Speaker Identification +2

Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis

no code implementations6 Nov 2020 Guanghui Xu, Wei Song, Zhengchen Zhang, Chao Zhang, Xiaodong He, BoWen Zhou

Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into natural and expressive speech.

Sentence Embeddings Speech Synthesis

Emotion recognition by fusing time synchronous and time asynchronous representations

no code implementations27 Oct 2020 Wen Wu, Chao Zhang, Philip C. Woodland

In this paper, a novel two-branch neural network model structure is proposed for multimodal emotion recognition, which consists of a time synchronous branch (TSB) and a time asynchronous branch (TAB).

automatic-speech-recognition Classification +4

Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data

1 code implementation EMNLP 2020 Lingkai Kong, Haoming Jiang, Yuchen Zhuang, Jie Lyu, Tuo Zhao, Chao Zhang

Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization.

Language Modelling Text Classification

Combination of Deep Speaker Embeddings for Diarisation

no code implementations22 Oct 2020 Guangzhi Sun, Chao Zhang, Phil Woodland

Significant progress has recently been made in speaker diarisation after the introduction of d-vectors as speaker embeddings extracted from neural network (NN) speaker classifiers for clustering speech segments.

Action Detection Activity Detection +1

Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction

no code implementations21 Oct 2020 Rui Feng, Jie Yuan, Chao Zhang

We argue that the event extraction models so trained are inherently label-hungry, and can generalize poorly across domains and text genres. We propose a reading comprehension framework for event extraction. Specifically, we formulate event detection as a textual entailment prediction problem, and argument detection as a question answer-ing problem.

Event Detection Event Extraction +2

COSEA: Convolutional Code Search with Layer-wise Attention

no code implementations19 Oct 2020 Hao Wang, Jia Zhang, Yingce Xia, Jiang Bian, Chao Zhang, Tie-Yan Liu

However, most existing studies overlook the code's intrinsic structural logic, which indeed contains a wealth of semantic information, and fails to capture intrinsic features of codes.

Code Search

Text Classification Using Label Names Only: A Language Model Self-Training Approach

1 code implementation EMNLP 2020 Yu Meng, Yunyi Zhang, Jiaxin Huang, Chenyan Xiong, Heng Ji, Chao Zhang, Jiawei Han

In this paper, we explore the potential of only using the label name of each class to train classification models on unlabeled data, without using any labeled documents.

Classification Document Classification +4

Transformer-Based Neural Text Generation with Syntactic Guidance

1 code implementation5 Oct 2020 Yinghao Li, Rui Feng, Isaac Rehg, Chao Zhang

We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation.

Text Generation

SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup

1 code implementation EMNLP 2020 Rongzhi Zhang, Yue Yu, Chao Zhang

Our method, SeqMix, simply augments the queried samples by generating extra labeled sequences in each iteration.

Active Learning Data Augmentation +2

A Spherical Hidden Markov Model for Semantics-Rich Human Mobility Modeling

1 code implementation5 Oct 2020 Wanzheng Zhu, Chao Zhang, Shuochao Yao, Xiaobin Gao, Jiawei Han

We propose SHMM, a multi-modal spherical hidden Markov model for semantics-rich human mobility modeling.

SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization

1 code implementation4 Oct 2020 Yue Yu, Kexin Huang, Chao Zhang, Lucas M. Glass, Jimeng Sun, Cao Xiao

Furthermore, most previous works focus on binary DDI prediction whereas the multi-typed DDI pharmacological effect prediction is a more meaningful but harder task.

Knowledge Graphs

Exploring the Hierarchy in Relation Labels for Scene Graph Generation

no code implementations12 Sep 2020 Yi Zhou, Shuyang Sun, Chao Zhang, Yikang Li, Wanli Ouyang

By assigning each relationship a single label, current approaches formulate the relationship detection as a classification problem.

Graph Generation Scene Graph Generation

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

no code implementations11 Sep 2020 Qi Zhu, Yidan Xu, Haonan Wang, Chao Zhang, Jiawei Han, Carl Yang

Graph neural networks (GNNs) have been shown with superior performance in various applications, but training dedicated GNNs can be costly for large-scale graphs.

Transfer Learning

Continuous Color Transfer

no code implementations31 Aug 2020 Chunzhi Gu, Xuequan Lu, Chao Zhang

In particular, we relate the transferred image with the example image under the Gaussian Mixture Model (GMM) and regard the transferred image color as the GMM centroids.

SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates

2 code implementations ICML 2020 Lingkai Kong, Jimeng Sun, Chao Zhang

We propose a new method for quantifying uncertainties of DNNs from a dynamical system perspective.

A variational quantum algorithm for Hamiltonian diagonalization

no code implementations22 Aug 2020 Jinfeng Zeng, Chenfeng Cao, Chao Zhang, Pengxiang Xu, Bei Zeng

To obtain the full spectrum of the Hamiltonian, we use a quantum imaginary time evolution algorithm with high temperature, which prepares a thermal state with a small correlation length.

Quantum Physics

Neural Kalman Filtering for Speech Enhancement

no code implementations28 Jul 2020 Wei Xue, Gang Quan, Chao Zhang, Guohong Ding, Xiaodong He, BoWen Zhou

Statistical signal processing based speech enhancement methods adopt expert knowledge to design the statistical models and linear filters, which is complementary to the deep neural network (DNN) based methods which are data-driven.

automatic-speech-recognition Speech Enhancement +1

Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding

1 code implementation18 Jul 2020 Yu Meng, Yunyi Zhang, Jiaxin Huang, Yu Zhang, Chao Zhang, Jiawei Han

Mining a set of meaningful topics organized into a hierarchy is intuitively appealing since topic correlations are ubiquitous in massive text corpora.

Topic Models

Deep Patch-based Human Segmentation

no code implementations11 Jul 2020 Dongbo Zhang, Zheng Fang, Xuequan Lu, Hong Qin, Antonio Robles-Kelly, Chao Zhang, Ying He

3D human segmentation has seen noticeable progress in re-cent years.

STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths

1 code implementation18 Jun 2020 Yue Yu, Yinghao Li, Jiaming Shen, Hao Feng, Jimeng Sun, Chao Zhang

We propose a self-supervised taxonomy expansion model named STEAM, which leverages natural supervision in the existing taxonomy for expansion.

Curating a COVID-19 data repository and forecasting county-level death counts in the United States

1 code implementation16 May 2020 Nick Altieri, Rebecca L. Barter, James Duncan, Raaz Dwivedi, Karl Kumbier, Xiao Li, Robert Netzorg, Briton Park, Chandan Singh, Yan Shuo Tan, Tiffany Tang, Yu Wang, Chao Zhang, Bin Yu

We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.

COVID-19 Tracking Decision Making +2

Partially-Typed NER Datasets Integration: Connecting Practice to Theory

no code implementations1 May 2020 Shi Zhi, Liyuan Liu, Yu Zhang, Shiyin Wang, Qi Li, Chao Zhang, Jiawei Han

While typical named entity recognition (NER) models require the training set to be annotated with all target types, each available datasets may only cover a part of them.

Named Entity Recognition NER

Spherically symmetric static black holes in Einstein-aether theory

no code implementations13 Apr 2020 Chao Zhang, Xiang Zhao, Kai Lin, Shaojun Zhang, Wen Zhao, Anzhong Wang

In particular, we find that, out of the five non-trivial field equations, only three are independent, so the problem is well-posed, as now generically there are only three unknown functions, {$F(r), B(r), A(r)$, where $F$ and $B$ are metric coefficients, and $A$ describes the aether field.}

General Relativity and Quantum Cosmology Astrophysics of Galaxies High Energy Physics - Phenomenology High Energy Physics - Theory

paper2repo: GitHub Repository Recommendation for Academic Papers

no code implementations13 Apr 2020 Huajie Shao, Dachun Sun, Jiahao Wu, Zecheng Zhang, Aston Zhang, Shuochao Yao, Shengzhong Liu, Tianshi Wang, Chao Zhang, Tarek Abdelzaher

Motivated by this trend, we describe a novel item-item cross-platform recommender system, $\textit{paper2repo}$, that recommends relevant repositories on GitHub that match a given paper in an academic search system such as Microsoft Academic.

Recommendation Systems

SHX: Search History Driven Crossover for Real-Coded Genetic Algorithm

no code implementations30 Mar 2020 Takumi Nakane, Xuequan Lu, Chao Zhang

In evolutionary algorithms, genetic operators iteratively generate new offspring which constitute a potentially valuable set of search history.

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

1 code implementation CVPR 2020 Jianyuan Guo, Kai Han, Yunhe Wang, Chao Zhang, Zhaohui Yang, Han Wu, Xinghao Chen, Chang Xu

To this end, we propose a hierarchical trinity search framework to simultaneously discover efficient architectures for all components (i. e. backbone, neck, and head) of object detector in an end-to-end manner.

Image Classification Neural Architecture Search +1

Self-Adaptive Training: beyond Empirical Risk Minimization

2 code implementations NeurIPS 2020 Lang Huang, Chao Zhang, Hongyang Zhang

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially corrupted training data.

General Classification

G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data

no code implementations20 Jan 2020 Chao Zhang, Xuequan Lu, Katsuya Hotta, Xi Yang

The WA data can be naturally obtained in an interactive way for specific tasks, for example, in the case of homography estimation, one can easily annotate points on the same plane/object with a single label by observing the image.

Homography Estimation

Multimodal Intelligence: Representation Learning, Information Fusion, and Applications

no code implementations10 Nov 2019 Chao Zhang, Zichao Yang, Xiaodong He, Li Deng

This review provides a comprehensive analysis of recent works on multimodal deep learning from three perspectives: learning multimodal representations, fusing multimodal signals at various levels, and multimodal applications.

Multimodal Deep Learning Question Answering +4

Improved Large-margin Softmax Loss for Speaker Diarisation

no code implementations10 Nov 2019 Yassir Fathullah, Chao Zhang, Philip C. Woodland

Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers.

Spherical Text Embedding

1 code implementation NeurIPS 2019 Yu Meng, Jiaxin Huang, Guangyuan Wang, Chao Zhang, Honglei Zhuang, Lance Kaplan, Jiawei Han

While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document clustering, which creates a gap between the training stage and usage stage of text embedding.

Riemannian optimization Word Similarity

Discriminative Neural Clustering for Speaker Diarisation

1 code implementation22 Oct 2019 Qiujia Li, Florian L. Kreyssig, Chao Zhang, Philip C. Woodland

In this paper, we propose Discriminative Neural Clustering (DNC) that formulates data clustering with a maximum number of clusters as a supervised sequence-to-sequence learning problem.

Data Augmentation

Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification

1 code implementation ICCV 2019 Jianyuan Guo, Yuhui Yuan, Lang Huang, Chao Zhang, Jinge Yao, Kai Han

On the other hand, there still exist many useful contextual cues that do not fall into the scope of predefined human parts or attributes.

Human Parsing Person Re-Identification

Efficient Projection-Free Online Methods with Stochastic Recursive Gradient

no code implementations21 Oct 2019 Jiahao Xie, Zebang Shen, Chao Zhang, Boyu Wang, Hui Qian

This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems.

Aggregated Gradient Langevin Dynamics

no code implementations21 Oct 2019 Chao Zhang, Jiahao Xie, Zebang Shen, Peilin Zhao, Tengfei Zhou, Hui Qian

In this paper, we explore a general Aggregated Gradient Langevin Dynamics framework (AGLD) for the Markov Chain Monte Carlo (MCMC) sampling.

FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams

1 code implementation10 Oct 2019 Wanzheng Zhu, Hongyu Gong, Jiaming Shen, Chao Zhang, Jingbo Shang, Suma Bhat, Jiawei Han

In this paper, we study the task of multi-faceted set expansion, which aims to capture all semantic facets in the seed set and return multiple sets of entities, one for each semantic facet.

Language Modelling

On Dimension-free Tail Inequalities for Sums of Random Matrices and Applications

no code implementations8 Oct 2019 Chao Zhang, Min-Hsiu Hsieh, DaCheng Tao

We also develop the tail inequalities for matrix random series and matrix martingale difference sequence.

PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials

1 code implementation8 Oct 2019 Yunqi Shao, Matti Hellström, Pavlin D. Mitev, Lisanne Knijff, Chao Zhang

Atomic neural networks (ANNs) constitute a class of machine learning methods for predicting potential energy surfaces and physico-chemical properties of molecules and materials.

Computational Physics Disordered Systems and Neural Networks Chemical Physics

Device-independent verification of Einstein-Podolsky-Rosen steering

no code implementations30 Sep 2019 Yuan-Yuan Zhao, Chao Zhang, Shuming Cheng, Xinhui Li, Yu Guo, Bi-Heng Liu, Huan-Yu Ku, Shin-Liang Chen, Qiaoyan Wen, Yun-Feng Huang, Guo-Yong Xiang, Chuan-Feng Li, Guang-Can Guo

If entanglement could be verified without any trust in the devices of observers, i. e., in a device-independent (DI) way, then unconditional security can be guaranteed for various quantum information tasks.

Quantum Physics

Decision Set Optimization and Energy-Efficient MIMO Communications

no code implementations16 Sep 2019 Hang Zou, Chao Zhang, Samson Lasaulce, Lucas Saludjian, Patrick Panciatici

We propose a framework to find a good (finite) decision set which induces a minimal performance loss w. r. t.

Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition

no code implementations14 Sep 2019 Qiujia Li, Chao Zhang, Philip C. Woodland

This paper proposes a novel automatic speech recognition (ASR) framework called Integrated Source-Channel and Attention (ISCA) that combines the advantages of traditional systems based on the noisy source-channel model (SC) and end-to-end style systems using attention-based sequence-to-sequence models.

automatic-speech-recognition Speech Recognition

Discriminative Topic Mining via Category-Name Guided Text Embedding

1 code implementation20 Aug 2019 Yu Meng, Jiaxin Huang, Guangyuan Wang, Zihan Wang, Chao Zhang, Yu Zhang, Jiawei Han

We propose a new task, discriminative topic mining, which leverages a set of user-provided category names to mine discriminative topics from text corpora.

Document Classification General Classification +3

Orientation-aware Semantic Segmentation on Icosahedron Spheres

1 code implementation ICCV 2019 Chao Zhang, Stephan Liwicki, William Smith, Roberto Cipolla

For the spherical domain, several methods recently adopt an icosahedron mesh, but systems are typically rotation invariant or require significant memory and parameters, thus enabling execution only at very low resolutions.

Autonomous Driving Semantic Segmentation

Multi-scale Template Matching with Scalable Diversity Similarity in an Unconstrained Environment

no code implementations2 Jul 2019 Yi Zhang, Chao Zhang, Takuya Akashi

We propose a novel multi-scale template matching method which is robust against both scaling and rotation in unconstrained environments.

Template Matching

Accelerating Primal Solution Findings for Mixed Integer Programs Based on Solution Prediction

no code implementations23 Jun 2019 Jian-Ya Ding, Chao Zhang, Lei Shen, Shengyin Li, Bing Wang, Yinghui Xu, Le Song

In many applications, a similar MIP model is solved on a regular basis, maintaining remarkable similarities in model structures and solution appearances but differing in formulation coefficients.

Combinatorial Optimization

Multi-Span Acoustic Modelling using Raw Waveform Signals

no code implementations21 Jun 2019 Patrick von Platen, Chao Zhang, Philip Woodland

This paper proposes a novel multi-span structure for acoustic modelling based on the raw waveform with multiple streams of CNN input layers, each processing a different span of the raw waveform signal.

Acoustic Modelling automatic-speech-recognition +1

ADA-Tucker: Compressing Deep Neural Networks via Adaptive Dimension Adjustment Tucker Decomposition

no code implementations18 Jun 2019 Zhisheng Zhong, Fangyin Wei, Zhouchen Lin, Chao Zhang

Furthermore, we propose that weight tensors in networks with proper order and balanced dimension are easier to be compressed.

A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization

no code implementations8 Jun 2019 Yu-cheng Chen, Matus Telgarsky, Chao Zhang, Bolton Bailey, Daniel Hsu, Jian Peng

This paper provides a simple procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs).

Fragmentation of shells: An analogy with the crack formation in tree bark

no code implementations6 Jun 2019 Chuang-Shi Shen, Chao Zhang, Xiaosheng Gao, Yulong Li

We recognize that the fragmentation problem in shells is analogous to the cracking behavior of tree bark, and closed form solutions is obtained to describe the relationship between the expansion velocity and the number of necks with consideration of the strain rate dependent strength of the shell material.

Soft Condensed Matter Applied Physics

Decision-Oriented Communications: Application to Energy-Efficient Resource Allocation

no code implementations17 May 2019 Hang Zou, Chao Zhang, Samson Lasaulce, Lucas Saludjian, Patrick Panciatici

In this paper, we introduce the problem of decision-oriented communications, that is, the goal of the source is to send the right amount of information in order for the intended destination to execute a task.

FrameRank: A Text Processing Approach to Video Summarization

no code implementations11 Apr 2019 Zhuo Lei, Chao Zhang, Qian Zhang, Guoping Qiu

In constructing the dataset, because of the subjectivity of user-generated video summarization, we manually annotate 25 summaries for each video, which are in total 1300 summaries.

Unsupervised Video Summarization

C3AE: Exploring the Limits of Compact Model for Age Estimation

1 code implementation CVPR 2019 Chao Zhang, Shuaicheng Liu, Xun Xu, Ce Zhu

Recently, MobileNets and ShuffleNets have been proposed to reduce the number of parameters, yielding lightweight models.

Age Estimation

Task Oriented Channel State Information Quantization

no code implementations2 Apr 2019 Hang Zou, Chao Zhang, Samson Lasaulce

The proposed point of view is fully relevant for a receiver which has to send a quantized version of the channel state to the transmitter.


A Probabilistic Bitwise Genetic Algorithm for B-Spline based Image Deformation Estimation

no code implementations26 Mar 2019 Takumi Nakane, Takuya Akashi, Xuequan Lu, Chao Zhang

We propose a novel genetic algorithm to solve the image deformation estimation problem by preserving the genetic diversity.

Blur Removal via Blurred-Noisy Image Pair

no code implementations26 Mar 2019 Chunzhi Gu, Xuequan Lu, Ying He, Chao Zhang

Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images.

Deblurring Optical Flow Estimation

Combined Neyman-Pearson Chi-square: An Improved Approximation to the Poisson-likelihood Chi-square

1 code implementation17 Mar 2019 Xiangpan Ji, Wenqiang Gu, Xin Qian, Hanyu Wei, Chao Zhang

We describe an approximation to the widely-used Poisson-likelihood chi-square using a linear combination of Neyman's and Pearson's chi-squares, namely "combined Neyman-Pearson chi-square" ($\chi^2_{\mathrm{CNP}}$).

Data Analysis, Statistics and Probability High Energy Physics - Experiment Nuclear Experiment

Speaker diarisation using 2D self-attentive combination of embeddings

no code implementations8 Feb 2019 Guangzhi Sun, Chao Zhang, Phil Woodland

This combination uses a 2-dimensional (2D) self-attentive structure, which extends the standard self-attentive layer by averaging not only across time but also across different types of embeddings.

Attribute-Aware Attention Model for Fine-grained Representation Learning

1 code implementation2 Jan 2019 Kai Han, Jianyuan Guo, Chao Zhang, Mingjian Zhu

Based on the considerations above, we propose a novel Attribute-Aware Attention Model ($A^3M$), which can learn local attribute representation and global category representation simultaneously in an end-to-end manner.

Fine-Grained Image Classification Image Retrieval +2

Weakly-Supervised Hierarchical Text Classification

1 code implementation29 Dec 2018 Yu Meng, Jiaming Shen, Chao Zhang, Jiawei Han

During the training process, our model features a hierarchical neural structure, which mimics the given hierarchy and is capable of determining the proper levels for documents with a blocking mechanism.

Classification Feature Engineering +2

TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering

1 code implementation22 Dec 2018 Chao Zhang, Fangbo Tao, Xiusi Chen, Jiaming Shen, Meng Jiang, Brian Sadler, Michelle Vanni, Jiawei Han

Our method, TaxoGen, uses term embeddings and hierarchical clustering to construct a topic taxonomy in a recursive fashion.


Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN

1 code implementation NeurIPS 2018 Shupeng Su, Chao Zhang, Kai Han, Yonghong Tian

To convert the input into binary code, hashing algorithm has been widely used for approximate nearest neighbor search on large-scale image sets due to its computation and storage efficiency.

Cross-domain Deep Feature Combination for Bird Species Classification with Audio-visual Data

no code implementations26 Nov 2018 Bold Naranchimeg, Chao Zhang, Takuya Akashi

In recent decade, many state-of-the-art algorithms on image classification as well as audio classification have achieved noticeable successes with the development of deep convolutional neural network (CNN).

Audio Classification Bird Species Classification With Audio-Visual Data +4

T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction

7 code implementations12 Nov 2018 Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, Haifeng Li

However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence.

Traffic Prediction

Generalization Bounds for Vicinal Risk Minimization Principle

no code implementations11 Nov 2018 Chao Zhang, Min-Hsiu Hsieh, DaCheng Tao

First, we prove that the complexity of function classes convolving with vicinal functions can be controlled by that of the original function classes under the assumption that the function class is composed of Lipschitz-continuous functions.

Generalization Bounds

Sparse DNNs with Improved Adversarial Robustness

no code implementations NeurIPS 2018 Yiwen Guo, Chao Zhang, Chang-Shui Zhang, Yurong Chen

Deep neural networks (DNNs) are computationally/memory-intensive and vulnerable to adversarial attacks, making them prohibitive in some real-world applications.

General Classification

Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution

no code implementations NeurIPS 2018 Zhisheng Zhong, Tiancheng Shen, Yibo Yang, Zhouchen Lin, Chao Zhang

To solve these problems, we propose the Super-Resolution CliqueNet (SRCliqueNet) to reconstruct the high resolution (HR) image with better textural details in the wavelet domain.

Image Super-Resolution

Blur-Countering Keypoint Detection via Eigenvalue Asymmetry

no code implementations5 Sep 2018 Chao Zhang, Xuequan Lu, Takuya Akashi

To settle this issue, we propose a blur-countering method for detecting valid keypoints for various types and degrees of blurred images.

Keypoint Detection

OCNet: Object Context Network for Scene Parsing

8 code implementations4 Sep 2018 Yuhui Yuan, Lang Huang, Jianyuan Guo, Chao Zhang, Xilin Chen, Jingdong Wang

To capture richer context information, we further combine our interlaced sparse self-attention scheme with the conventional multi-scale context schemes including pyramid pooling~\citep{zhao2017pyramid} and atrous spatial pyramid pooling~\citep{chen2018deeplab}.

Scene Parsing Semantic Segmentation

Weakly-Supervised Neural Text Classification

1 code implementation2 Sep 2018 Yu Meng, Jiaming Shen, Chao Zhang, Jiawei Han

Although many semi-supervised and weakly-supervised text classification models exist, they cannot be easily applied to deep neural models and meanwhile support limited supervision types.

Classification Feature Engineering +2

Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks

1 code implementation10 Jul 2018 Yu Shi, Qi Zhu, Fang Guo, Chao Zhang, Jiawei Han

To cope with the challenges in the comprehensive transcription of HINs, we propose the HEER algorithm, which embeds HINs via edge representations that are further coupled with properly-learned heterogeneous metrics.

Feature Engineering Network Embedding

Semi-tied Units for Efficient Gating in LSTM and Highway Networks

no code implementations18 Jun 2018 Chao Zhang, Philip Woodland

Gating is a key technique used for integrating information from multiple sources by long short-term memory (LSTM) models and has recently also been applied to other models such as the highway network.

Speech Recognition

Image Ordinal Classification and Understanding: Grid Dropout with Masking Label

no code implementations8 May 2018 Chao Zhang, Ce Zhu, Jimin Xiao, Xun Xu, Yipeng Liu

Finally we demonstrate the effectiveness of both approaches by visualizing the Class Activation Map (CAM) and discover that grid dropout is more aware of the whole facial areas and more robust than neuron dropout for small training dataset.

Age Estimation Classification +2

High Order Recurrent Neural Networks for Acoustic Modelling

no code implementations22 Feb 2018 Chao Zhang, Philip Woodland

Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells.

Acoustic Modelling Speech Recognition

The Importance of Norm Regularization in Linear Graph Embedding: Theoretical Analysis and Empirical Demonstration

no code implementations ICLR 2019 Yihan Gao, Chao Zhang, Jian Peng, Aditya Parameswaran

Both theoretical and empirical evidence are provided to support this argument: (a) we prove that the generalization error of these methods can be bounded by limiting the norm of vectors, regardless of the embedding dimension; (b) we show that the generalization performance of linear graph embedding methods is correlated with the norm of embedding vectors, which is small due to the early stopping of SGD and the vanishing gradients.

Graph Embedding

Binary output layer of feedforward neural networks for solving multi-class classification problems

no code implementations22 Jan 2018 Sibo Yang, Chao Zhang, Wei Wu

Considered in this short note is the design of output layer nodes of feedforward neural networks for solving multi-class classification problems with r (bigger than or equal to 3) classes of samples.

General Classification Multi-class Classification

AutoEncoder Inspired Unsupervised Feature Selection

1 code implementation23 Oct 2017 Kai Han, Yunhe Wang, Chao Zhang, Chao Li, Chao Xu

High-dimensional data in many areas such as computer vision and machine learning tasks brings in computational and analytical difficulty.

Feature Selection

RDeepSense: Reliable Deep Mobile Computing Models with Uncertainty Estimations

no code implementations9 Sep 2017 Shuochao Yao, Yiran Zhao, Huajie Shao, Aston Zhang, Chao Zhang, Shen Li, Tarek Abdelzaher

Recent advances in deep learning have led various applications to unprecedented achievements, which could potentially bring higher intelligence to a broad spectrum of mobile and ubiquitous applications.

Bridging Collaborative Filtering and Semi-Supervised Learning: A Neural Approach for POI Recommendation

no code implementations1 Aug 2017 Carl Yang, Lanxiao Bai, Chao Zhang, Quan Yuan, J. Han profile

In this work, we propose to devise a general and principled SSL (semi-supervised learning) framework, to alleviate data scarcity via smoothing among neighboring users and POIs, and treat various context by regularizing user preference based on context graphs.

Collaborative Filtering Recommendation Systems

Feature Incay for Representation Regularization

no code implementations ICLR 2018 Yuhui Yuan, Kuiyuan Yang, Chao Zhang

Thus, we propose feature incay to also regularize representation learning, which favors feature vectors with large norm when the samples can be correctly classified.

Multi-class Classification Representation Learning

Robust Spatial Filtering with Graph Convolutional Neural Networks

1 code implementation2 Mar 2017 Felipe Petroski Such, Shagan Sah, Miguel Dominguez, Suhas Pillai, Chao Zhang, Andrew Michael, Nathan Cahill, Raymond Ptucha

Graph-CNNs can handle both heterogeneous and homogeneous graph data, including graphs having entirely different vertex or edge sets.

General Classification

Hard-Aware Deeply Cascaded Embedding

1 code implementation ICCV 2017 Yuhui Yuan, Kuiyuan Yang, Chao Zhang

This motivates us to ensemble a set of models with different complexities in cascaded manner and mine hard examples adaptively, a sample is judged by a series of models with increasing complexities and only updates models that consider the sample as a hard case.

Metric Learning

Accelerated Variance Reduced Block Coordinate Descent

no code implementations13 Nov 2016 Zebang Shen, Hui Qian, Chao Zhang, Tengfei Zhou

Algorithms with fast convergence, small number of data access, and low per-iteration complexity are particularly favorable in the big data era, due to the demand for obtaining \emph{highly accurate solutions} to problems with \emph{a large number of samples} in \emph{ultra-high} dimensional space.

pg-Causality: Identifying Spatiotemporal Causal Pathways for Air Pollutants with Urban Big Data

no code implementations22 Oct 2016 Julie Yixuan Zhu, Chao Zhang, Huichu Zhang, Shi Zhi, Victor O. K. Li, Jiawei Han, Yu Zheng

Therefore, we present \emph{p-Causality}, a novel pattern-aided causality analysis approach that combines the strengths of \emph{pattern mining} and \emph{Bayesian learning} to efficiently and faithfully identify the \emph{ST causal pathways}.

Functional Faces: Groupwise Dense Correspondence Using Functional Maps

no code implementations CVPR 2016 Chao Zhang, William A. P. Smith, Arnaud Dessein, Nick Pears, Hang Dai

In this paper we present a method for computing dense correspondence between a set of 3D face meshes using functional maps.

Engineering Deep Representations for Modeling Aesthetic Perception

no code implementations25 May 2016 Yanxiang Chen, Yuxing Hu, Luming Zhang, Ping Li, Chao Zhang

To remedy these problems, we develop a deep architecture to learn aesthetically-relevant visual attributes from Flickr1, which are localized by multiple textual attributes in a weakly-supervised setting.

Completing Low-Rank Matrices with Corrupted Samples from Few Coefficients in General Basis

no code implementations25 Jun 2015 Hongyang Zhang, Zhouchen Lin, Chao Zhang

As an application, we also find that the solutions to extended robust Low-Rank Representation and to our extended robust MC are mutually expressible, so both our theory and algorithm can be applied to the subspace clustering problem with missing values under certain conditions.

Matrix Completion

Discrete Hyper-Graph Matching

no code implementations CVPR 2015 Junchi Yan, Chao Zhang, Hongyuan Zha, Wei Liu, Xiaokang Yang, Stephen M. Chu

Evaluations on both synthetic and real-world data corroborate the efficiency of our method.

Graph Matching

Unsupervised Feature Learning for Dense Correspondences across Scenes

1 code implementation4 Jan 2015 Chao Zhang, Chunhua Shen, Tingzhi Shen

We experimentally demonstrate that the learned features, together with our matching model, outperforms state-of-the-art methods such as the SIFT flow, coherency sensitive hashing and the recent deformable spatial pyramid matching methods both in terms of accuracy and computation efficiency.

Dictionary Learning

Relations among Some Low Rank Subspace Recovery Models

no code implementations6 Dec 2014 Hongyang Zhang, Zhouchen Lin, Chao Zhang, Junbin Gao

More specifically, we discover that once a solution to one of the models is obtained, we can obtain the solutions to other models in closed-form formulations.

Task-group Relatedness and Generalization Bounds for Regularized Multi-task Learning

no code implementations28 Aug 2014 Chao Zhang, DaCheng Tao, Tao Hu, Xiang Li

We are mainly concerned with two theoretical questions: 1) under what conditions does RMTL perform better with a smaller task sample size than STL?

Generalization Bounds Multi-Task Learning

A Study on Cross-Population Age Estimation

no code implementations CVPR 2014 Guodong Guo, Chao Zhang

Further, we study the amount of data needed in the target population to learn a cross-population age estimator.

Age Estimation

A Parallel Way to Select the Parameters of SVM Based on the Ant Optimization Algorithm

no code implementations19 May 2014 Chao Zhang, Hong-cen Mei, Hao Yang

A large number of experimental data shows that Support Vector Machine (SVM) algorithm has obvious advantages in text classification, handwriting recognition, image classification, bioinformatics, and some other fields.

Classification General Classification +3

Generalization Bounds for Representative Domain Adaptation

no code implementations2 Jan 2014 Chao Zhang, Lei Zhang, Wei Fan, Jieping Ye

Finally, we analyze the asymptotic convergence and the rate of convergence of the learning process for representative domain adaptation.

Domain Adaptation Generalization Bounds

Bennett-type Generalization Bounds: Large-deviation Case and Faster Rate of Convergence

no code implementations26 Sep 2013 Chao Zhang

samples, and then show that the generalization bounds have a faster rate of convergence than the traditional results.

Generalization Bounds

A Counterexample for the Validity of Using Nuclear Norm as a Convex Surrogate of Rank

no code implementations23 Apr 2013 Hongyang Zhang, Zhouchen Lin, Chao Zhang

For several rank minimization problems, such a replacement has been theoretically proven to be valid, i. e., the solution to nuclear norm minimization problem is also the solution to rank minimization problem.

Generalization Bounds for Domain Adaptation

no code implementations NeurIPS 2012 Chao Zhang, Lei Zhang, Jieping Ye

Afterwards, we analyze the asymptotic convergence and the rate of convergence of the learning process for such kind of domain adaptation.

Domain Adaptation Generalization Bounds

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