no code implementations • NeurIPS 2010 • Yu Zhang, Dit-yan Yeung
In this paper, we first analyze the scatter measures used in the conventional linear discriminant analysis~(LDA) model and note that the formulation is based on the average-case view.
no code implementations • NeurIPS 2010 • Yu Zhang, Dit-yan Yeung, Qian Xu
In this paper, we unify the $l_{1, 2}$ and $l_{1,\infty}$ norms by considering a family of $l_{1, q}$ norms for $1 < q\le\infty$ and study the problem of determining the most appropriate sparsity enforcing norm to use in the context of multi-task feature selection.
no code implementations • 15 Mar 2012 • Yu Zhang, Dit-yan Yeung
In this paper, we propose a regularization formulation for learning the relationships between tasks in multi-task learning.
no code implementations • 17 Dec 2012 • Guoxu Zhou, Andrzej Cichocki, Yu Zhang, Danilo Mandic
Very often data we encounter in practice is a collection of matrices rather than a single matrix.
no code implementations • 24 Aug 2013 • Luca Canzian, Yu Zhang, Mihaela van der Schaar
We present an efficient distributed online learning scheme to classify data captured from distributed, heterogeneous, and dynamic data sources.
no code implementations • 26 Aug 2013 • Yu Zhang, Guoxu Zhou, Jing Jin, Xingyu Wang, Andrzej Cichocki
Canonical correlation analysis (CCA) has been one of the most popular methods for frequency recognition in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs).
no code implementations • 2 Oct 2013 • Vassilis Kekatos, Yu Zhang, Georgios B. Giannakis
The smart grid vision entails advanced information technology and data analytics to enhance the efficiency, sustainability, and economics of the power grid infrastructure.
no code implementations • NeurIPS 2013 • Yu Zhang
In this paper, different from existing methods, we propose local learning methods for multi-task classification and regression problems based on heterogeneous neighborhood which is defined on data points from all tasks.
no code implementations • 16 Jan 2014 • Liyue Zhao, Yu Zhang, Gita Sukthankar
Crowdsourcing platforms offer a practical solution to the problem of affordably annotating large datasets for training supervised classifiers.
no code implementations • 22 Apr 2014 • Yu Zhang, Subbarao Kambhampati
Then, by dividing the problems that require cooperation (referred to as RC problems) into two classes -- problems with heterogeneous and homogeneous agents, we aim to identify all the conditions that can cause RC in these two classes.
no code implementations • CVPR 2014 • Jianxin Wu, Yu Zhang, Weiyao Lin
High dimensional representations such as VLAD or FV have shown excellent accuracy in action recognition.
no code implementations • CVPR 2014 • Yu Zhang, Jianxin Wu, Jianfei Cai
In spite of the popularity of various feature compression methods, this paper argues that feature selection is a better choice than feature compression.
no code implementations • 4 Nov 2014 • Yu Zhang, Subbarao Kambhampati
Thus far, there are two common representations of agent models: MDP based and action based, which are both based on action modeling.
no code implementations • 9 Dec 2014 • Vignesh Narayanan, Yu Zhang, Nathaniel Mendoza, Subbarao Kambhampati
While information asymmetry can be desirable sometimes, it may also lead to the robot choosing improper actions that negatively influence the teaming performance.
no code implementations • 20 Apr 2015 • Yu Zhang, Xiu-Shen Wei, Jianxin Wu, Jianfei Cai, Jiangbo Lu, Viet-Anh Nguyen, Minh N. Do
Most existing works heavily rely on object / part detectors to build the correspondence between object parts by using object or object part annotations inside training images.
no code implementations • CVPR 2016 • Hao Yang, Joey Tianyi Zhou, Yu Zhang, Bin-Bin Gao, Jianxin Wu, Jianfei Cai
With strong labels, our framework is able to achieve state-of-the-art results in both datasets.
Ranked #16 on Multi-Label Classification on PASCAL VOC 2007
no code implementations • CVPR 2015 • Yu Zhang, Xiaowu Chen, Jia Li, Chen Wang, Changqun Xia
Semantic object segmentation in video is an important step for large-scale multimedia analysis.
no code implementations • CVPR 2015 • Mao Ye, Yu Zhang, Ruigang Yang, Dinesh Manocha
We present a novel sensor fusion algorithm that first segments the depth map into different categories such as opaque/transparent/infinity (e. g., too far to measure) and then updates the depth map based on the segmentation outcome.
no code implementations • 29 Aug 2015 • Guoxu Zhou, Qibin Zhao, Yu Zhang, Tülay Adalı, Shengli Xie, Andrzej Cichocki
With the increasing availability of various sensor technologies, we now have access to large amounts of multi-block (also called multi-set, multi-relational, or multi-view) data that need to be jointly analyzed to explore their latent connections.
no code implementations • 30 Oct 2015 • Yu Zhang, Ekapol Chuangsuwanich, James Glass, Dong Yu
In this paper, we investigate the use of prediction-adaptation-correction recurrent neural networks (PAC-RNNs) for low-resource speech recognition.
no code implementations • 30 Oct 2015 • Yu Zhang, Guoguo Chen, Dong Yu, Kaisheng Yao, Sanjeev Khudanpur, James Glass
In this paper, we extend the deep long short-term memory (DLSTM) recurrent neural networks by introducing gated direct connections between memory cells in adjacent layers.
no code implementations • 25 Nov 2015 • Yu Zhang, Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti, Hankz Hankui Zhuo, Subbarao Kambhampati
Hence, for such agents to be helpful, one important requirement is for them to synthesize plans that can be easily understood by humans.
1 code implementation • 19 Feb 2016 • Tianxing He, Yu Zhang, Jasha Droppo, Kai Yu
We propose to train bi-directional neural network language model(NNLM) with noise contrastive estimation(NCE).
no code implementations • 1 Mar 2016 • Yu Zhang, Stephen Wistar, Jia Li, Michael Steinberg, James Z. Wang
In our system, we extract and summarize important visual storm evidence from satellite image sequences in the way that meteorologists interpret the images.
no code implementations • 23 Mar 2016 • Wei-Ning Hsu, Yu Zhang, James Glass
We apply a general recurrent neural network (RNN) encoder framework to community question answering (cQA) tasks.
no code implementations • 20 Apr 2016 • Qingyu Yin, Wei-Nan Zhang, Yu Zhang, Ting Liu
This is because zero pronouns have no descriptive information, which results in difficulty in explicitly capturing their semantic similarities with antecedents.
no code implementations • 7 May 2016 • Wei-Nan Zhang, Ting Liu, Qingyu Yin, Yu Zhang
Dropped pronouns (DPs) are ubiquitous in pro-drop languages like Chinese, Japanese etc.
no code implementations • 24 Jun 2016 • Satya Gautam Vadlamudi, Tathagata Chakraborti, Yu Zhang, Subbarao Kambhampati
Proactive decision support (PDS) helps in improving the decision making experience of human decision makers in human-in-the-loop planning environments.
no code implementations • 13 Sep 2016 • Chi Xu, Lakshmi Narasimhan Govindarajan, Yu Zhang, Li Cheng
Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately.
no code implementations • 10 Oct 2016 • William Chan, Yu Zhang, Quoc Le, Navdeep Jaitly
We present the Latent Sequence Decompositions (LSD) framework.
no code implementations • 10 Oct 2016 • Kaixiang Mo, Shuangyin Li, Yu Zhang, Jiajun Li, Qiang Yang
One way to solve this problem is to consider a collection of multiple users' data as a source domain and an individual user's data as a target domain, and to perform a transfer learning from the source to the target domain.
2 code implementations • 10 Oct 2016 • Yu Zhang, William Chan, Navdeep Jaitly
Sequence-to-sequence models have shown success in end-to-end speech recognition.
no code implementations • 16 Nov 2016 • Anagha Kulkarni, Yantian Zha, Tathagata Chakraborti, Satya Gautam Vadlamudi, Yu Zhang, Subbarao Kambhampati
In order to have effective human-AI collaboration, it is necessary to address how the AI agent's behavior is being perceived by the humans-in-the-loop.
no code implementations • COLING 2016 • Salvatore Romeo, Giovanni Da San Martino, Alberto Barr{\'o}n-Cede{\~n}o, Aless Moschitti, ro, Yonatan Belinkov, Wei-Ning Hsu, Yu Zhang, Mitra Mohtarami, James Glass
In real-world data, e. g., from Web forums, text is often contaminated with redundant or irrelevant content, which leads to introducing noise in machine learning algorithms.
no code implementations • 2 Dec 2016 • Yu Zhang, Chi Xu, Li Cheng
This paper focuses on the challenging problem of 3D pose estimation of a diverse spectrum of articulated objects from single depth images.
no code implementations • 15 Dec 2016 • Namhoon Lee, Xinshuo Weng, Vishnu Naresh Boddeti, Yu Zhang, Fares Beainy, Kris Kitani, Takeo Kanade
We introduce the concept of a Visual Compiler that generates a scene specific pedestrian detector and pose estimator without any pedestrian observations.
no code implementations • 11 Jan 2017 • Xiaowei Zhang, Chi Xu, Yu Zhang, Tingshao Zhu, Li Cheng
The implementation of our approach and comparison methods as well as the involved datasets are made publicly available in support of the open-source and reproducible research initiatives.
no code implementations • 28 Jan 2017 • Tathagata Chakraborti, Sarath Sreedharan, Yu Zhang, Subbarao Kambhampati
When AI systems interact with humans in the loop, they are often called on to provide explanations for their plans and behavior.
no code implementations • 24 Feb 2017 • Fei Han, Xue Yang, Yu Zhang, Hao Zhang
Apprenticeship learning has recently attracted a wide attention due to its capability of allowing robots to learn physical tasks directly from demonstrations provided by human experts.
no code implementations • 24 Feb 2017 • Fei Han, Xue Yang, Christopher Reardon, Yu Zhang, Hao Zhang
We formulate FABL as a regression-like optimization problem with structured sparsity-inducing norms to model interrelationships of body parts and features.
no code implementations • 13 Apr 2017 • Wei-Ning Hsu, Yu Zhang, James Glass
In this paper, we apply a convolutional VAE to model the generative process of natural speech.
no code implementations • 8 Jun 2017 • Yu Zhang, Daniel L. Lau, Ying Yu
Structured light illumination is an active 3-D scanning technique based on projecting/capturing a set of striped patterns and measuring the warping of the patterns as they reflect off a target object's surface.
6 code implementations • 8 Jun 2017 • Takaaki Hori, Shinji Watanabe, Yu Zhang, William Chan
The CTC network sits on top of the encoder and is jointly trained with the attention-based decoder.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 8 Jun 2017 • Daniel L. Lau, Yu Zhang, Kai Liu
In the case of phase measuring profilometry (PMP), the projected patterns are composed of a rolling sinusoidal wave, but as a set of time-multiplexed patterns, PMP requires the target surface to remain motionless or for scanning to be performed at such high rates that any movement is small.
no code implementations • CVPR 2017 • Changqun Xia, Jia Li, Xiaowu Chen, Anlin Zheng, Yu Zhang
Finding what is and what is not a salient object can be helpful in developing better features and models in salient object detection (SOD).
no code implementations • 15 Jul 2017 • Tathagata Chakraborti, Subbarao Kambhampati, Matthias Scheutz, Yu Zhang
Among the many anticipated roles for robots in the future is that of being a human teammate.
no code implementations • 19 Jul 2017 • Wei-Ning Hsu, Yu Zhang, James Glass
Research on robust speech recognition can be regarded as trying to overcome this domain mismatch issue.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
1 code implementation • 25 Jul 2017 • Yu Zhang, Qiang Yang
Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks.
no code implementations • SEMEVAL 2017 • Le Qi, Yu Zhang, Ting Liu
We describe a method of calculating the similarity of questions in community QA.
no code implementations • 18 Aug 2017 • Ying Wei, Yu Zhang, Qiang Yang
We establish the L2T framework in two stages: 1) we first learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer for a newly arrived pair of domains by optimizing the reflection function.
no code implementations • EMNLP 2017 • Qingyu Yin, Yu Zhang, Wei-Nan Zhang, Ting Liu
Existing approaches for Chinese zero pronoun resolution typically utilize only syntactical and lexical features while ignoring semantic information.
11 code implementations • EMNLP 2018 • Tao Lei, Yu Zhang, Sida I. Wang, Hui Dai, Yoav Artzi
Common recurrent neural architectures scale poorly due to the intrinsic difficulty in parallelizing their state computations.
Ranked #32 on Question Answering on SQuAD1.1 dev
no code implementations • 13 Sep 2017 • Wenya Zhu, Kaixiang Mo, Yu Zhang, Zhangbin Zhu, Xuezheng Peng, Qiang Yang
Although existing generative question answering (QA) systems can be applied to knowledge grounded conversation, they either have at most one entity in a response or cannot deal with out-of-vocabulary entities.
3 code implementations • NeurIPS 2017 • Wei-Ning Hsu, Yu Zhang, James Glass
We present a factorized hierarchical variational autoencoder, which learns disentangled and interpretable representations from sequential data without supervision.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • ICCV 2017 • Dingwen Zhang, Junwei Han, Yu Zhang
Based on this insight, we combine an intra-image fusion stream and a inter-image fusion stream in the proposed framework to generate the learning curriculum and pseudo ground-truth for supervising the training of the deep salient object detector.
no code implementations • 5 Oct 2017 • Yu Zhang, Srikanta Tirthapura, Graham Cormode
We study Bayesian networks, the workhorse of graphical models, and present a communication-efficient method for continuously learning and maintaining a Bayesian network model over data that is arriving as a distributed stream partitioned across multiple processors.
no code implementations • 9 Nov 2017 • Meng Qu, Xiang Ren, Yu Zhang, Jiawei Han
We propose a novel co-training framework with a distributional module and a pattern module.
no code implementations • 10 Nov 2017 • Weiyan Wang, Yuxiang Wu, Yu Zhang, Zhongqi Lu, Kaixiang Mo, Qiang Yang
Then the built user model is used as a leverage to train the agent model by deep reinforcement learning.
no code implementations • 11 Nov 2017 • Kaixiang Mo, Yu Zhang, Qiang Yang, Pascale Fung
Training a personalized dialogue system requires a lot of data, and the data collected for a single user is usually insufficient.
no code implementations • 17 Nov 2017 • Tiezheng Ge, Liqin Zhao, Guorui Zhou, Keyu Chen, Shuying Liu, Huimin Yi, Zelin Hu, Bochao Liu, Peng Sun, Haoyu Liu, Pengtao Yi, Sui Huang, Zhiqiang Zhang, Xiaoqiang Zhu, Yu Zhang, Kun Gai
So we propose to model user preference jointly with user behavior ID features and behavior images.
30 code implementations • 16 Dec 2017 • Jonathan Shen, Ruoming Pang, Ron J. Weiss, Mike Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, RJ Skerry-Ryan, Rif A. Saurous, Yannis Agiomyrgiannakis, Yonghui Wu
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text.
Ranked #2 on Speech Synthesis on North American English
1 code implementation • ICLR 2018 • Tao Lei, Yu Zhang, Yoav Artzi
Common recurrent neural network architectures scale poorly due to the intrinsic difficulty in parallelizing their state computations.
2 code implementations • 30 Jan 2018 • Xuan Wang, Yu Zhang, Xiang Ren, Yuhao Zhang, Marinka Zitnik, Jingbo Shang, Curtis Langlotz, Jiawei Han
Motivation: State-of-the-art biomedical named entity recognition (BioNER) systems often require handcrafted features specific to each entity type, such as genes, chemicals and diseases.
11 code implementations • ICML 2018 • Yuxuan Wang, Daisy Stanton, Yu Zhang, RJ Skerry-Ryan, Eric Battenberg, Joel Shor, Ying Xiao, Fei Ren, Ye Jia, Rif A. Saurous
In this work, we propose "global style tokens" (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system.
no code implementations • 17 Apr 2018 • GuangNeng Hu, Yu Zhang, Qiang Yang
By modeling content information as local memories, LCMR attentively learns what to exploit with the guidance of user-item interaction.
1 code implementation • 18 Apr 2018 • Guang-Neng Hu, Yu Zhang, Qiang Yang
CoNet enables dual knowledge transfer across domains by introducing cross connections from one base network to another and vice versa.
no code implementations • 20 Apr 2018 • Kaixiang Mo, Yu Zhang, Qiang Yang, Pascale Fung
Also, they depend on either common slots or slot entropy, which are not available when the source and target slots are totally disjoint and no database is available to calculate the slot entropy.
no code implementations • 21 Apr 2018 • Sha Yuan, Yu Zhang, Jie Tang, Juan Bautista Cabotà
Moreover, we use innovative diagrams to clarify several important concepts of ensemble learning, and find that ensemble models with several specific single models can further boosting the performance.
no code implementations • 23 Apr 2018 • Yinghua Zhang, Yu Zhang, Qiang Yang
Unfortunately, the transferability is usually defined as discrete states and it differs with domains and network architectures.
1 code implementation • Thirty-Second AAAI Conference on Artificial Intelligence 2018 • Zheng Li, Ying WEI, Yu Zhang, Qiang Yang
Existing cross-domain sentiment classification meth- ods cannot automatically capture non-pivots, i. e., the domain- specific sentiment words, and pivots, i. e., the domain-shared sentiment words, simultaneously.
1 code implementation • 26 Apr 2018 • Qi Zhu, Xiang Ren, Jingbo Shang, Yu Zhang, Ahmed El-Kishky, Jiawei Han
However, current Open IE systems focus on modeling local context information in a sentence to extract relation tuples, while ignoring the fact that global statistics in a large corpus can be collectively leveraged to identify high-quality sentence-level extractions.
no code implementations • Structural and Multidisciplinary Optimization 2018 • Yu Zhang, Zhong-Hua Han, Ke-Shi Zhang
The efficient global optimization method (EGO) based on kriging surrogate model and expected improvement (EI) has received much attention for optimization of high-fidelity, expensive functions.
no code implementations • 15 May 2018 • Wei Teng, Yu Zhang, Xiaowu Chen, Jia Li, Zhiqiang He
Image co-segmentation is a challenging task in computer vision that aims to segment all pixels of the objects from a predefined semantic category.
no code implementations • NeurIPS 2018 • Yu Zhang, Ying WEI, Qiang Yang
Based on such training set, L2MT first uses a proposed layerwise graph neural network to learn task embeddings for all the tasks in a multitask problem and then learns an estimation function to estimate the relative test error based on task embeddings and the representation of the multitask model based on a unified formulation.
1 code implementation • ACL 2018 • Qingyu Yin, Yu Zhang, Wei-Nan Zhang, Ting Liu, William Yang Wang
In this study, we show how to integrate local and global decision-making by exploiting deep reinforcement learning models.
11 code implementations • NeurIPS 2018 • Ye Jia, Yu Zhang, Ron J. Weiss, Quan Wang, Jonathan Shen, Fei Ren, Zhifeng Chen, Patrick Nguyen, Ruoming Pang, Ignacio Lopez Moreno, Yonghui Wu
Clone a voice in 5 seconds to generate arbitrary speech in real-time
no code implementations • ICML 2018 • Ying WEI, Yu Zhang, Junzhou Huang, Qiang Yang
In transfer learning, what and how to transfer are two primary issues to be addressed, as different transfer learning algorithms applied between a source and a target domain result in different knowledge transferred and thereby the performance improvement in the target domain.
no code implementations • 28 Jul 2018 • Tomoki Hayashi, Shinji Watanabe, Yu Zhang, Tomoki Toda, Takaaki Hori, Ramon Astudillo, Kazuya Takeda
In this paper we propose a novel data augmentation method for attention-based end-to-end automatic speech recognition (E2E-ASR), utilizing a large amount of text which is not paired with speech signals.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
1 code implementation • COLING 2018 • Qingyu Yin, Yu Zhang, Wei-Nan Zhang, Ting Liu, William Yang Wang
Recent neural network methods for zero pronoun resolution explore multiple models for generating representation vectors for zero pronouns and their candidate antecedents.
no code implementations • 30 Aug 2018 • Yu-An Chung, Yuxuan Wang, Wei-Ning Hsu, Yu Zhang, RJ Skerry-Ryan
We demonstrate that the proposed framework enables Tacotron to generate intelligible speech using less than half an hour of paired training data.
no code implementations • 20 Sep 2018 • Yong Zhang, Yu Zhang, Zhao Zhang, Jie Bao, Yunpeng Song
Traditional human activity recognition (HAR) based on time series adopts sliding window analysis method.
1 code implementation • EMNLP 2018 • Zhichun Wang, Qingsong Lv, Xiaohan Lan, Yu Zhang
Embeddings can be learned from both the structural and attribute information of entities, and the results of structure embedding and attribute embedding are combined to get accurate alignments.
Ranked #5 on Entity Alignment on YAGO-WIKI50K
no code implementations • 14 Oct 2018 • Yu Zhang, Yan Zhang
In this paper, we study influence maximization from a game perspective.
2 code implementations • ICLR 2019 • Wei-Ning Hsu, Yu Zhang, Ron J. Weiss, Heiga Zen, Yonghui Wu, Yuxuan Wang, Yuan Cao, Ye Jia, Zhifeng Chen, Jonathan Shen, Patrick Nguyen, Ruoming Pang
This paper proposes a neural sequence-to-sequence text-to-speech (TTS) model which can control latent attributes in the generated speech that are rarely annotated in the training data, such as speaking style, accent, background noise, and recording conditions.
no code implementations • 2 Nov 2018 • Takaaki Hori, Ramon Astudillo, Tomoki Hayashi, Yu Zhang, Shinji Watanabe, Jonathan Le Roux
To solve this problem, this work presents a loss that is based on the speech encoder state sequence instead of the raw speech signal.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 6 Nov 2018 • Sha Yuan, Yu Zhang, Jie Tang, Hua-Wei Shen, Xingxing Wei
Here we propose a deep learning attention mechanism to model the process through which individual items gain their popularity.
no code implementations • 6 Nov 2018 • Sha Yuan, Jie Tang, Yu Zhang, Yifan Wang, Tong Xiao
The rapid evolution of scientific research has been creating a huge volume of publications every year.
Digital Libraries Physics and Society
no code implementations • 8 Nov 2018 • Weichen Dai, Yu Zhang, Ping Li, Zheng Fang, Sebastian Scherer
This method utilizes the correlation between map points to separate points that are part of the static scene and points that are part of different moving objects into different groups.
no code implementations • 14 Nov 2018 • Kui Fu, Jia Li, Yu Zhang, Hongze Shen, Yonghong Tian
After that, the visual saliency knowledge encoded in the most representative paths is selected and aggregated to improve the capability of MM-Net in predicting spatial saliency in aerial scenarios.
1 code implementation • AAAI 2019 2018 • Zheng Li, Ying WEI, Yu Zhang, Xiang Zhang, Xin Li, Qiang Yang
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT).
no code implementations • 22 Nov 2018 • Bo Li, Yu Zhang, Tara Sainath, Yonghui Wu, William Chan
We present two end-to-end models: Audio-to-Byte (A2B) and Byte-to-Audio (B2A), for multilingual speech recognition and synthesis.
no code implementations • 23 Nov 2018 • Jia Li, Junjie Wu, Anlin Zheng, Yafei Song, Yu Zhang, Xiaowu Chen
Segmenting primary objects in a video is an important yet challenging problem in computer vision, as it exhibits various levels of foreground/background ambiguities.
1 code implementation • 8 Dec 2018 • Seyed-Vahid Sanei-Mehri, Yu Zhang, Ahmet Erdem Sariyuce, Srikanta Tirthapura
We consider space-efficient single-pass estimation of the number of butterflies, a fundamental bipartite graph motif, from a massive bipartite graph stream where each edge represents a connection between entities in two different partitions.
Data Structures and Algorithms
1 code implementation • 22 Dec 2018 • Kunjin Chen, Jun Hu, Yu Zhang, Zhanqing Yu, Jinliang He
This paper develops a novel graph convolutional network (GCN) framework for fault location in power distribution networks.
no code implementations • ICCV 2019 • Jinming Su, Jia Li, Yu Zhang, Changqun Xia, Yonghong Tian
In this network, the feature selectivity at boundaries is enhanced by incorporating a boundary localization stream, while the feature invariance at interiors is guaranteed with a complex interior perception stream.
no code implementations • 27 Dec 2018 • Yu Zhang
We consider the first passage percolation model in Z2 with a distribution F for 0 < F (0) < pc.
Probability
no code implementations • 17 Jan 2019 • Mehrdad Zakershahrak, Yu Zhang
Being aware of the human teammates' expectation leads to robot behaviors that better align with human expectation, thus facilitating more efficient and potentially safer teams.
no code implementations • 22 Jan 2019 • Guang-Neng Hu, Yu Zhang, Qiang Yang
Another thread is to transfer knowledge from other source domains such as improving the movie recommendation with the knowledge from the book domain, leading to transfer learning methods.
no code implementations • 2 Feb 2019 • Yu Zhang, Mehrdad Zakershahrak
A progressive explanation improves understanding by limiting the cognitive effort required at each step of making the explanation.
2 code implementations • 21 Feb 2019 • Jonathan Shen, Patrick Nguyen, Yonghui Wu, Zhifeng Chen, Mia X. Chen, Ye Jia, Anjuli Kannan, Tara Sainath, Yuan Cao, Chung-Cheng Chiu, Yanzhang He, Jan Chorowski, Smit Hinsu, Stella Laurenzo, James Qin, Orhan Firat, Wolfgang Macherey, Suyog Gupta, Ankur Bapna, Shuyuan Zhang, Ruoming Pang, Ron J. Weiss, Rohit Prabhavalkar, Qiao Liang, Benoit Jacob, Bowen Liang, HyoukJoong Lee, Ciprian Chelba, Sébastien Jean, Bo Li, Melvin Johnson, Rohan Anil, Rajat Tibrewal, Xiaobing Liu, Akiko Eriguchi, Navdeep Jaitly, Naveen Ari, Colin Cherry, Parisa Haghani, Otavio Good, Youlong Cheng, Raziel Alvarez, Isaac Caswell, Wei-Ning Hsu, Zongheng Yang, Kuan-Chieh Wang, Ekaterina Gonina, Katrin Tomanek, Ben Vanik, Zelin Wu, Llion Jones, Mike Schuster, Yanping Huang, Dehao Chen, Kazuki Irie, George Foster, John Richardson, Klaus Macherey, Antoine Bruguier, Heiga Zen, Colin Raffel, Shankar Kumar, Kanishka Rao, David Rybach, Matthew Murray, Vijayaditya Peddinti, Maxim Krikun, Michiel A. U. Bacchiani, Thomas B. Jablin, Rob Suderman, Ian Williams, Benjamin Lee, Deepti Bhatia, Justin Carlson, Semih Yavuz, Yu Zhang, Ian McGraw, Max Galkin, Qi Ge, Golan Pundak, Chad Whipkey, Todd Wang, Uri Alon, Dmitry Lepikhin, Ye Tian, Sara Sabour, William Chan, Shubham Toshniwal, Baohua Liao, Michael Nirschl, Pat Rondon
Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models.
no code implementations • 7 Mar 2019 • Junde Wu, Xiaoguang Di, Jiehao Huang, Yu Zhang
Recently, end-to-end learning-based methods based on deep neural network (DNN) have been proven effective for blind deblurring.
no code implementations • 11 Mar 2019 • Wei Jiang, Zhenghua Li, Yu Zhang, Min Zhang
The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery.
no code implementations • 15 Mar 2019 • Mehrdad Zakershahrak, Ze Gong, Nikhillesh Sadassivam, Yu Zhang
The new explanation generation methods are based on a model reconciliation setting introduced in our prior work.
5 code implementations • 5 Apr 2019 • Heiga Zen, Viet Dang, Rob Clark, Yu Zhang, Ron J. Weiss, Ye Jia, Zhifeng Chen, Yonghui Wu
This paper introduces a new speech corpus called "LibriTTS" designed for text-to-speech use.
Sound Audio and Speech Processing
no code implementations • 10 Apr 2019 • Kaiwen Yu, Jia Li, Yu Zhang, Yifan Zhao, Long Xu
Along with the development of virtual reality (VR), omnidirectional images play an important role in producing multimedia content with immersive experience.
no code implementations • 12 Apr 2019 • Peizhen Xie, Ke Zuo, Yu Zhang, Fangfang Li, Mingzhu Yin, Kai Lu
For making the classifications reasonable, the visualization of CNN representations is furthermore used to identify cells between melanoma and nevi.
no code implementations • 12 Apr 2019 • Yu Zhang, Xinchao Wang, Xiaojun Bi, DaCheng Tao
In LDTNet, the haze-free image and the transmission map are produced simultaneously.
29 code implementations • 18 Apr 2019 • Daniel S. Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D. Cubuk, Quoc V. Le
On LibriSpeech, we achieve 6. 8% WER on test-other without the use of a language model, and 5. 8% WER with shallow fusion with a language model.
Ranked #1 on Speech Recognition on Hub5'00 SwitchBoard
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 1 May 2019 • Yu Zhang
In this paper, we consider a first step to bridge a gap in coordinating task planning robots.
no code implementations • 10 May 2019 • Xiang Zhang, Lina Yao, Xianzhi Wang, Jessica Monaghan, David Mcalpine, Yu Zhang
Brain-Computer Interface (BCI) bridges the human's neural world and the outer physical world by decoding individuals' brain signals into commands recognizable by computer devices.
no code implementations • SEMEVAL 2019 • Wei Jiang, Zhenghua Li, Yu Zhang, Min Zhang
The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery.
Ranked #1 on UCCA Parsing on SemEval 2019 Task 1
no code implementations • CVPR 2019 • Yu Zhang, Daniel L. Lau, Ying Yu
Structured light illumination is an active 3D scanning technique based on projecting/capturing a set of striped patterns and measuring the warping of the patterns as they reflect off a target object's surface.
no code implementations • CVPR 2019 • Yu Zhang, Dongqing Zou, Jimmy S. Ren, Zhe Jiang, Xiaohao Chen
This paper addresses stereoscopic view synthesis from a single image.
no code implementations • 3 Jun 2019 • M. Ablikim, M. N. Achasov, S. Ahmed, M. Albrecht, M. Alekseev, A. Amoroso, F. F. An, Q. An, Y. Bai, O. Bakina, R. Baldini Ferroli, Y. Ban, K. Begzsuren, D. W. Bennett, J. V. Bennett, N. Berger, M. Bertani, D. Bettoni, F. Bianchi, E. Boger, I. Boyko, R. A. Briere, H. Cai, X. Cai, A. Calcaterra, G. F. Cao, S. A. Cetin, J. Chai, J. F. Chang, W. L. Chang, G. Chelkov, G. Chen, H. S. Chen, J. C. Chen, M. L. Chen, P. L. Chen, S. J. Chen, X. R. Chen, Y. B. Chen, W. Cheng, X. K. Chu, G. Cibinetto, F. Cossio, H. L. Dai, J. P. Dai, A. Dbeyssi, D. Dedovich, Z. Y. Deng, A. Denig, I. Denysenko, M. Destefanis, F. DeMori, Y. Ding, C. Dong, J. Dong, L. Y. Dong, M. Y. Dong, Z. L. Dou, S. X. Du, P. F. Duan, J. Fang, S. S. Fang, Y. Fang, R. Farinelli, L. Fava, F. Feldbauer, G. Felici, C. Q. Feng, M. Fritsch, C. D. Fu, Q. Gao, X. L. Gao, Y. Gao, Y. G. Gao, Z. Gao, B. Garillon, I. Garzia, A. Gilman, K. Goetzen, L. Gong, W. X. Gong, W. Gradl, M. Greco, L. M. Gu, M. H. Gu, Y. T. Gu, A. Q. Guo, L. B. Guo, R. P. Guo, Y. P. Guo, A. Guskov, Z. Haddadi, S. Han, X. Q. Hao, F. A. Harris, K. L. He, F. H. Heinsius, T. Held, Y. K. Heng, Z. L. Hou, H. M. Hu, J. F. Hu, T. Hu, Y. Hu, G. S. Huang, J. S. Huang, X. T. Huang, X. Z. Huang, Z. L. Huang, T. Hussain, W. Ikegami Andersson, M. Irshad, Q. Ji, Q. P. Ji, X. B. Ji, X. L. Ji, H. L. Jiang, X. S. Jiang, X. Y. Jiang, J. B. Jiao, Z. Jiao, D. P. Jin, S. Jin, Y. Jin, T. Johansson, A. Julin, N. Kalantar-Nayestanaki, X. S. Kang, M. Kavatsyuk, B. C. Ke, I. K. Keshk, T. Khan, A. Khoukaz, P. Kiese, R. Kiuchi, R. Kliemt, L. Koch, O. B. Kolcu, B. Kopf, M. Kuemmel, M. Kuessner, A. Kupsc, M. Kurth, W. Kühn, J. S. Lange, P. Larin, L. Lavezzi, S. Leiber, H. Leithoff, C. Li, Cheng Li, D. M. Li, F. Li, F. Y. Li, G. Li, H. B. Li, H. J. Li, J. C. Li, J. W. Li, K. J. Li, Kang Li, Ke Li, Lei LI, P. L. Li, P. R. Li, Q. Y. Li, T. Li, W. D. Li, W. G. Li, X. L. Li, X. N. Li, X. Q. Li, Z. B. Li, H. Liang, Y. F. Liang, Y. T. Liang, G. R. Liao, L. Z. Liao, J. Libby, C. X. Lin, D. X. Lin, B. Liu, B. J. Liu, C. X. Liu, D. Liu, D. Y. Liu, F. H. Liu, Fang Liu, Feng Liu, H. B. Liu, H. L. Liu, H. M. Liu, Huanhuan Liu, Huihui Liu, J. B. Liu, J. Y. Liu, K. Y. Liu, Ke Liu, L. D. Liu, Q. Liu, S. B. Liu, X. Liu, Y. B. Liu, Z. A. Liu, Zhiqing Liu, Y. F. Long, X. C. Lou, H. J. Lu, J. G. Lu, Y. Lu, Y. P. Lu, C. L. Luo, M. X. Luo, P. W. Luo, T. Luo, X. L. Luo, S. Lusso, X. R. Lyu, F. C. Ma, H. L. Ma, L. L. Ma, M. M. Ma, Q. M. Ma, X. N. Ma, X. Y. Ma, Y. M. Ma, F. E. Maas, M. Maggiora, S. Maldaner, Q. A. Malik, A. Mangoni, Y. J. Mao, Z. P. Mao, S. Marcello, Z. X. Meng, J. G. Messchendorp, G. Mezzadri, J. Min, T. J. Min, R. E. Mitchell, X. H. Mo, Y. J. Mo, C. Morales Morales, N. Yu. Muchnoi, H. Muramatsu, A. Mustafa, S. Nakhoul, Y. Nefedov, F. Nerling, I. B. Nikolaev, Z. Ning, S. Nisar, S. L. Niu, X. Y. Niu, S. L. Olsen, Q. Ouyang, S. Pacetti, Y. Pan, M. Papenbrock, P. Patteri, M. Pelizaeus, J. Pellegrino, H. P. Peng, Z. Y. Peng, K. Peters, J. Pettersson, J. L. Ping, R. G. Ping, A. Pitka, R. Poling, V. Prasad, H. R. Qi, M. Qi, T. Y. Qi, S. Qian, C. F. Qiao, N. Qin, X. S. Qin, Z. H. Qin, J. F. Qiu, S. Q. Qu, K. H. Rashid, C. F. Redmer, M. Richter, M. Ripka, A. Rivetti, M. Rolo, G. Rong, Ch. Rosner, A. Sarantsev, M. Savrié, K. Schoenning, W. Shan, X. Y. Shan, M. Shao, C. P. Shen, P. X. Shen, X. Y. Shen, H. Y. Sheng, X. Shi, J. J. Song, W. M. Song, X. Y. Song, S. Sosio, C. Sowa, S. Spataro, F. F. Sui, G. X. Sun, J. F. Sun, L. Sun, S. S. Sun, X. H. Sun, Y. J. Sun, Y. K Sun, Y. Z. Sun, Z. J. Sun, Z. T. Sun, Y. T Tan, C. J. Tang, G. Y. Tang, X. Tang, M. Tiemens, B. Tsednee, I. Uman, B. Wang, B. L. Wang, C. W. Wang, D. Wang, D. Y. Wang, Dan Wang, H. H. Wang, K. Wang, L. L. Wang, L. S. Wang, M. Wang, Meng Wang, P. Wang, P. L. Wang, W. P. Wang, X. F. Wang, Y. Wang, Y. F. Wang, Z. Wang, Z. G. Wang, Z. Y. Wang, Zongyuan Wang, T. Weber, D. H. Wei, P. Weidenkaff, S. P. Wen, U. Wiedner, M. Wolke, L. H. Wu, L. J. Wu, Z. Wu, L. Xia, X. Xia, Y. Xia, D. Xiao, Y. J. Xiao, Z. J. Xiao, Y. G. Xie, Y. H. Xie, X. A. Xiong, Q. L. Xiu, G. F. Xu, J. J. Xu, L. Xu, Q. J. Xu, X. P. Xu, F. Yan, L. Yan, W. B. Yan, W. C. Yan, Y. H. Yan, H. J. Yang, H. X. Yang, L. Yang, R. X. Yang, S. L. Yang, Y. H. Yang, Y. X. Yang, Yifan Yang, Z. Q. Yang, M. Ye, M. H. Ye, J. H. Yin, Z. Y. You, B. X. Yu, C. X. Yu, J. S. Yu, C. Z. Yuan, Y. Yuan, A. Yuncu, A. A. Zafar, Y. Zeng, B. X. Zhang, B. Y. Zhang, C. C. Zhang, D. H. Zhang, H. H. Zhang, H. Y. Zhang, J. Zhang, J. L. Zhang, J. Q. Zhang, J. W. Zhang, J. Y. Zhang, J. Z. Zhang, K. Zhang, L. Zhang, S. F. Zhang, T. J. Zhang, X. Y. Zhang, Y. Zhang, Y. H. Zhang, Y. T. Zhang, Yang Zhang, YaoZ hang, Yu Zhang, Z. H. Zhang, Z. P. Zhang, Z. Y. Zhang, G. Zhao, J. W. Zhao, J. Y. Zhao, J. Z. Zhao, Lei Zhao, Ling Zhao, M. G. Zhao, Q. Zhao, S. J. Zhao, T. C. Zhao, Y. B. Zhao, Z. G. Zhao, A. Zhemchugov, B. Zheng, J. P. Zheng, W. J. Zheng, Y. H. Zheng, B. Zhong, L. Zhou, Q. Zhou, X. Zhou, X. K. Zhou, X. R. Zhou, X. Y. Zhou, Xiaoyu Zhou, Xu Zhou, A. N. Zhu, J. Zhu, K. Zhu, K. J. Zhu, S. Zhu, S. H. Zhu, X. L. Zhu, Y. C. Zhu, Y. S. Zhu, Z. A. Zhu, J. Zhuang, B. S. Zou, J. H. Zou
We study $e^{+}e^{-}$ collisions with a $\pi^{+}\pi^{-}\pi^{0}\eta_{c}$ final state using data samples collected with the BESIII detector at center-of-mass energies $\sqrt{s}=4. 226$, $4. 258$, $4. 358$, $4. 416$, and $4. 600$ GeV.
High Energy Physics - Experiment
no code implementations • 3 Jun 2019 • Feng Liao, Hankz Hankui Zhuo, Xiaoling Huang, Yu Zhang
Online media outlets adopt clickbait techniques to lure readers to click on articles in a bid to expand their reach and subsequently increase revenue through ad monetization.
1 code implementation • 17 Jun 2019 • Zhen Zhou, Xiaobo Chen, Yu Zhang, Lishan Qiao, Renping Yu, Gang Pan, Han Zhang, Dinggang Shen
The goal of this work is to introduce a toolbox namely "Brain Network Construction and Classification" (BrainNetClass) to the field to promote more advanced brain network construction methods.
no code implementations • 25 Jun 2019 • Long Yang, Yu Zhang, Jun Wen, Qian Zheng, Pengfei Li, Gang Pan
In this paper, for reducing the variance, we introduce control variate technique to $\mathtt{Expected}$ $\mathtt{Sarsa}$($\lambda$) and propose a tabular $\mathtt{ES}$($\lambda$)-$\mathtt{CV}$ algorithm.
no code implementations • 25 Jun 2019 • Long Yang, Yu Zhang, Gang Zheng, Qian Zheng, Pengfei Li, Jianhang Huang, Jun Wen, Gang Pan
Improving sample efficiency has been a longstanding goal in reinforcement learning.
4 code implementations • 9 Jul 2019 • Yu Zhang, Ron J. Weiss, Heiga Zen, Yonghui Wu, Zhifeng Chen, RJ Skerry-Ryan, Ye Jia, Andrew Rosenberg, Bhuvana Ramabhadran
We present a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages.
1 code implementation • 20 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.
no code implementations • 23 Aug 2019 • Weichen Dai, Yu Zhang, Donglei Sun, Naira Hovakimyan, Ping Li
Moreover, the proposed method can also provide a metric 3D reconstruction in semi-dense density with multi-spectral information, which is not available from existing multi-spectral methods.
no code implementations • 28 Aug 2019 • Yuan Yao, Yu Zhang, Xutao Li, Yunming Ye
Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain.
no code implementations • 6 Sep 2019 • Long Yang, Yu Zhang, Qian Zheng, Pengfei Li, Gang Pan
To address above problem, we propose a GQ$(\sigma,\lambda)$ that extends tabular Q$(\sigma,\lambda)$ with linear function approximation.
no code implementations • NeurIPS Workshop Neuro_AI 2019 • Yu Zhang, Pierre Bellec
In this project, we applied graph convolutional networks (GCN) to decode brain activity over short time windows in a task fMRI dataset, i. e. associate a given window of fMRI time series with the task used.
1 code implementation • 18 Sep 2019 • Xiang Zhang, Lina Yao, Manqing Dong, Zhe Liu, Yu Zhang, Yong Li
Furthermore, to enhance the explainability, we develop an attention mechanism to automatically learn the importance of each EEG channels in the seizure diagnosis procedure.
no code implementations • 25 Sep 2019 • Andrew Rosenberg, Yu Zhang, Bhuvana Ramabhadran, Ye Jia, Pedro Moreno, Yonghui Wu, Zelin Wu
Recent success of the Tacotron speech synthesis architecture and its variants in producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of replacing expensive, manually transcribed, domain-specific, human speech that is used to train speech recognizers.
no code implementations • 8 Oct 2019 • Gustavo Aguilar, Yuan Ling, Yu Zhang, Benjamin Yao, Xing Fan, Chenlei Guo
In this paper, we propose to distill the internal representations of a large model such as BERT into a simplified version of it.
no code implementations • 15 Oct 2019 • Yin Zhou, Pei Sun, Yu Zhang, Dragomir Anguelov, Jiyang Gao, Tom Ouyang, James Guo, Jiquan Ngiam, Vijay Vasudevan
In this paper, we aim to synergize the birds-eye view and the perspective view and propose a novel end-to-end multi-view fusion (MVF) algorithm, which can effectively learn to utilize the complementary information from both.
1 code implementation • 15 Oct 2019 • Yu Zhang, Muhammad Alrabeiah, Ahmed Alkhateeb
This leads to the interesting, and \textit{counter-intuitive}, observation that when more antennas are employed by the massive MIMO base station, our proposed deep learning approach achieves better channel estimation performance, for the same pilot sequence length.
Information Theory Signal Processing Information Theory
2 code implementations • 16 Oct 2019 • Yu Zhang, Frank F. Xu, Sha Li, Yu Meng, Xuan Wang, Qi Li, Jiawei Han
With the massive number of repositories available, there is a pressing need for topic-based search.
3 code implementations • 24 Oct 2019 • Tomoki Hayashi, Ryuichi Yamamoto, Katsuki Inoue, Takenori Yoshimura, Shinji Watanabe, Tomoki Toda, Kazuya Takeda, Yu Zhang, Xu Tan
Furthermore, the unified design enables the integration of ASR functions with TTS, e. g., ASR-based objective evaluation and semi-supervised learning with both ASR and TTS models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 27 Oct 2019 • Zhengxuan Ling, Xinyu Tao, Yu Zhang, Xi Chen
Based on samples of a 10 city TSP, a fully convolutional network (FCN) is used to learn the mapping from a feasible region to an optimal solution.
1 code implementation • IJCNLP 2019 • Zheng Li, Xin Li, Ying WEI, Lidong Bing, Yu Zhang, Qiang Yang
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • 5 Nov 2019 • Xin Wang, Junichi Yamagishi, Massimiliano Todisco, Hector Delgado, Andreas Nautsch, Nicholas Evans, Md Sahidullah, Ville Vestman, Tomi Kinnunen, Kong Aik Lee, Lauri Juvela, Paavo Alku, Yu-Huai Peng, Hsin-Te Hwang, Yu Tsao, Hsin-Min Wang, Sebastien Le Maguer, Markus Becker, Fergus Henderson, Rob Clark, Yu Zhang, Quan Wang, Ye Jia, Kai Onuma, Koji Mushika, Takashi Kaneda, Yuan Jiang, Li-Juan Liu, Yi-Chiao Wu, Wen-Chin Huang, Tomoki Toda, Kou Tanaka, Hirokazu Kameoka, Ingmar Steiner, Driss Matrouf, Jean-Francois Bonastre, Avashna Govender, Srikanth Ronanki, Jing-Xuan Zhang, Zhen-Hua Ling
Spoofing attacks within a logical access (LA) scenario are generated with the latest speech synthesis and voice conversion technologies, including state-of-the-art neural acoustic and waveform model techniques.
no code implementations • 6 Nov 2019 • Chung-Cheng Chiu, Wei Han, Yu Zhang, Ruoming Pang, Sergey Kishchenko, Patrick Nguyen, Arun Narayanan, Hank Liao, Shuyuan Zhang, Anjuli Kannan, Rohit Prabhavalkar, Zhifeng Chen, Tara Sainath, Yonghui Wu
In this paper, we both investigate and improve the performance of end-to-end models on long-form transcription.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 17 Nov 2019 • Kunjin Chen, Yu Zhang, Qin Wang, Jun Hu, Hang Fan, Jinliang He
Non-intrusive load monitoring addresses the challenging task of decomposing the aggregate signal of a household's electricity consumption into appliance-level data without installing dedicated meters.
no code implementations • 18 Nov 2019 • Ke He, Bo Liu, Yu Zhang, Andrew Ling, Dian Gu
In this paper, we firstly propose the FeCaffe, i. e. FPGA-enabled Caffe, a hierarchical software and hardware design methodology based on the Caffe to enable FPGA to support mainline deep learning development features, e. g. training and inference with Caffe.
no code implementations • 21 Nov 2019 • Zhiyun Lu, Liangliang Cao, Yu Zhang, Chung-Cheng Chiu, James Fan
In this paper, we propose to use pre-trained features from end-to-end ASR models to solve speech sentiment analysis as a down-stream task.
8 code implementations • CVPR 2020 • Pei Sun, Henrik Kretzschmar, Xerxes Dotiwalla, Aurelien Chouard, Vijaysai Patnaik, Paul Tsui, James Guo, Yin Zhou, Yuning Chai, Benjamin Caine, Vijay Vasudevan, Wei Han, Jiquan Ngiam, Hang Zhao, Aleksei Timofeev, Scott Ettinger, Maxim Krivokon, Amy Gao, Aditya Joshi, Sheng Zhao, Shuyang Cheng, Yu Zhang, Jonathon Shlens, Zhifeng Chen, Dragomir Anguelov
In an effort to help align the research community's contributions with real-world self-driving problems, we introduce a new large scale, high quality, diverse dataset.
no code implementations • 11 Dec 2019 • Daniel S. Park, Yu Zhang, Chung-Cheng Chiu, Youzheng Chen, Bo Li, William Chan, Quoc V. Le, Yonghui Wu
Recently, SpecAugment, an augmentation scheme for automatic speech recognition that acts directly on the spectrogram of input utterances, has shown to be highly effective in enhancing the performance of end-to-end networks on public datasets.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 6 Feb 2020 • Guangzhi Sun, Yu Zhang, Ron J. Weiss, Yuan Cao, Heiga Zen, Yonghui Wu
This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model.
no code implementations • 6 Feb 2020 • Guangzhi Sun, Yu Zhang, Ron J. Weiss, Yuan Cao, Heiga Zen, Andrew Rosenberg, Bhuvana Ramabhadran, Yonghui Wu
Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 7 Feb 2020 • Yu Zhang, Tao Gu, Xi Zhang
Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning for personal mobile sensing applications.
1 code implementation • 12 Feb 2020 • Pengxin Guo, Chang Deng, Linjie Xu, Xiaonan Huang, Yu Zhang
The proposed feature augmentation strategy can be used in many deep multi-task learning models.
no code implementations • 12 Feb 2020 • Yi Zhang, Yu Zhang, Wei Wang
The GTTN is defined as a convex combination of matrix trace norms of all possible tensor flattenings and hence it can discover all the possible low-rank structures.
no code implementations • 12 Feb 2020 • Sicong Liang, Yu Zhang
In multi-task learning, difficulty levels of different tasks are varying.
no code implementations • 18 Feb 2020 • Yu Zhang, Xin Sun, Junyu Dong, Changrui Chen, Yue Shen
The network first introduces a High-Order Representation module to extract the contextual high-order information from all stages of the backbone.
1 code implementation • 24 Feb 2020 • Haowei Deng, Yu Zhang, Quanxi Li
Quantum computing devices in the NISQ era share common features and challenges like limited connectivity between qubits.
Quantum Physics
1 code implementation • 25 Feb 2020 • Yu Zhang, Muhammad Alrabeiah, Ahmed Alkhateeb
This leads to high beam training overhead and loss in the achievable beamforming gains.
Information Theory Signal Processing Information Theory
1 code implementation • 26 Feb 2020 • Yu Zhang, Xiaoguang Di, Bin Zhang, Chunhui Wang
We introduce a constraint that the maximum channel of the reflectance conforms to the maximum channel of the low light image and its entropy should be largest in our model to achieve self-supervised learning.
no code implementations • 27 Feb 2020 • Yu Zhang, Gongbo Liang, Tawfiq Salem, Nathan Jacobs
Despite remarkable performance across a broad range of tasks, neural networks have been shown to be vulnerable to adversarial attacks.
no code implementations • 27 Feb 2020 • Gongbo Liang, Xiaoqin Wang, Yu Zhang, Xin Xing, Hunter Blanton, Tawfiq Salem, Nathan Jacobs
Breast cancer is the malignant tumor that causes the highest number of cancer deaths in females.
no code implementations • 27 Feb 2020 • Yu Zhang, Xiaoqin Wang, Hunter Blanton, Gongbo Liang, Xin Xing, Nathan Jacobs
Automated methods for breast cancer detection have focused on 2D mammography and have largely ignored 3D digital breast tomosynthesis (DBT), which is frequently used in clinical practice.
3 code implementations • 27 Feb 2020 • Quan Tang, Fagui Liu, Tong Zhang, Jun Jiang, Yu Zhang
The way features propagate in Fully Convolutional Networks is of momentous importance to capture multi-scale contexts for obtaining precise segmentation masks.
Ranked #23 on Semantic Segmentation on SUN-RGBD (using extra training data)
no code implementations • 2 Mar 2020 • Yu Zhang, Gongbo Liang, Nathan Jacobs, Xiaoqin Wang
Generalization is one of the key challenges in the clinical validation and application of deep learning models to medical images.
1 code implementation • 6 Mar 2020 • Houquan Zhou, Yu Zhang, Zhenghua Li, Min Zhang
In the pre deep learning era, part-of-speech tags have been considered as indispensable ingredients for feature engineering in dependency parsing.
1 code implementation • 12 Mar 2020 • Yinghua Zhang, Yu Zhang, Ying WEI, Kun Bai, Yangqiu Song, Qiang Yang
Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance.
no code implementations • 23 Mar 2020 • Zhenyuan Ning, Ke Wang, Shengzhou Zhong, Qianjin Feng, Yu Zhang
Breast ultrasound (BUS) image segmentation plays a crucial role in a computer-aided diagnosis system, which is regarded as a useful tool to help increase the accuracy of breast cancer diagnosis.
no code implementations • 28 Mar 2020 • Tara N. Sainath, Yanzhang He, Bo Li, Arun Narayanan, Ruoming Pang, Antoine Bruguier, Shuo-Yiin Chang, Wei Li, Raziel Alvarez, Zhifeng Chen, Chung-Cheng Chiu, David Garcia, Alex Gruenstein, Ke Hu, Minho Jin, Anjuli Kannan, Qiao Liang, Ian McGraw, Cal Peyser, Rohit Prabhavalkar, Golan Pundak, David Rybach, Yuan Shangguan, Yash Sheth, Trevor Strohman, Mirko Visontai, Yonghui Wu, Yu Zhang, Ding Zhao
Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i. e., word error rate (WER), and latency, i. e., the time the hypothesis is finalized after the user stops speaking.
1 code implementation • 1 Apr 2020 • Carl Yang, Yuxin Xiao, Yu Zhang, Yizhou Sun, Jiawei Han
Since there has already been a broad body of HNE algorithms, as the first contribution of this work, we provide a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms.
no code implementations • 12 Apr 2020 • Xiaocong Chen, Lina Yao, Yu Zhang
The novel coronavirus disease 2019 (COVID-19) has been spreading rapidly around the world and caused significant impact on the public health and economy.
no code implementations • CVPR 2020 • Zhe Jiang, Yu Zhang, Dongqing Zou, Jimmy Ren, Jiancheng Lv, Yebin Liu
Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process.
Ranked #28 on Image Deblurring on GoPro (using extra training data)
no code implementations • 16 Apr 2020 • Mehrdad Zakershahrak, Shashank Rao Marpally, Akshay Sharma, Ze Gong, Yu Zhang
Given this sequential process, a formulation based on goal-based MDP for generating progressive explanations is presented.
1 code implementation • 22 Apr 2020 • Qingxu Fu, Xiaoguang Di, Yu Zhang
Furthermore, those tests illustrate that the proposed method is able to adaptively control the global image brightness according to the content of the image scene.
no code implementations • 1 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.
no code implementations • LREC 2020 • Eric Chen, Zhiyun Lu, Hao Xu, Liangliang Cao, Yu Zhang, James Fan
We present a multimodal corpus for sentiment analysis based on the existing Switchboard-1 Telephone Speech Corpus released by the Linguistic Data Consortium.
1 code implementation • 1 May 2020 • Yu Zhang, Yu Meng, Jiaxin Huang, Frank F. Xu, Xuan Wang, Jiawei Han
Then, based on the same generative process, we synthesize training samples to address the bottleneck of label scarcity.
2 code implementations • ACL 2020 • Yu Zhang, Zhenghua Li, Min Zhang
Experiments and analysis on 27 datasets from 13 languages clearly show that techniques developed before the DL era, such as structural learning (global TreeCRF loss) and high-order modeling are still useful, and can further boost parsing performance over the state-of-the-art biaffine parser, especially for partially annotated training data.
Ranked #1 on Dependency Parsing on CoNLL-2009
6 code implementations • 7 May 2020 • Wei Han, Zhengdong Zhang, Yu Zhang, Jiahui Yu, Chung-Cheng Chiu, James Qin, Anmol Gulati, Ruoming Pang, Yonghui Wu
We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2. 1%/4. 6% without external language model (LM), 1. 9%/4. 1% with LM and 2. 9%/7. 0% with only 10M parameters on the clean/noisy LibriSpeech test sets.
Ranked #12 on Speech Recognition on LibriSpeech test-clean
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 7 May 2020 • Chung-Cheng Chiu, Arun Narayanan, Wei Han, Rohit Prabhavalkar, Yu Zhang, Navdeep Jaitly, Ruoming Pang, Tara N. Sainath, Patrick Nguyen, Liangliang Cao, Yonghui Wu
On a long-form YouTube test set, when the nonstreaming RNN-T model is trained with shorter segments of data, the proposed combination improves word error rate (WER) from 22. 3% to 14. 8%; when the streaming RNN-T model trained on short Search queries, the proposed techniques improve WER on the YouTube set from 67. 0% to 25. 3%.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
24 code implementations • 16 May 2020 • Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, Ruoming Pang
Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs).
Ranked #12 on Speech Recognition on LibriSpeech test-other (using extra training data)
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 19 May 2020 • Daniel S. Park, Yu Zhang, Ye Jia, Wei Han, Chung-Cheng Chiu, Bo Li, Yonghui Wu, Quoc V. Le
Noisy student training is an iterative self-training method that leverages augmentation to improve network performance.
Ranked #5 on Speech Recognition on LibriSpeech test-clean
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 27 May 2020 • Sha Yuan, Zhou Shao, Yu Zhang, Xingxing Wei, Tong Xiao, Yifan Wang, Jie Tang
In the progress of science, the previously discovered knowledge principally inspires new scientific ideas, and citation is a reasonably good reflection of this cumulative nature of scientific research.
1 code implementation • 1 Jun 2020 • Tao Zhou, Huazhu Fu, Yu Zhang, Changqing Zhang, Xiankai Lu, Jianbing Shen, Ling Shao
Then, we use a modality-specific network to extract implicit and high-level features from different MR scans.
no code implementations • 13 Jun 2020 • Qiao Xiao, Yu Zhang
Transfer learning, which is to improve the learning performance in the target domain by leveraging useful knowledge from the source domain, often requires that those two domains are very close, which limits its application scope.
no code implementations • 16 Jun 2020 • Xiaocong Chen, Lina Yao, Tao Zhou, Jinming Dong, Yu Zhang
Diagnosis from chest CT images is a promising direction.
1 code implementation • 25 Jun 2020 • Muhammad Alrabeiah, Yu Zhang, Ahmed Alkhateeb
To overcome these limitations, this paper develops an efficient online machine learning framework that learns how to adapt the codebook beam patterns to the specific deployment, surrounding environment, user distribution, and hardware characteristics.
1 code implementation • 28 Jun 2020 • Brian Liu, Xianchao Xu, Yu Zhang
Deep learning based methods have been dominating the text recognition tasks in different and multilingual scenarios.
1 code implementation • 1 Jul 2020 • Weichen Dai, Yu Zhang, Shenzhou Chen, Donglei Sun, Da Kong
The multi-spectral images, including both color and thermal images in full sensor resolution (640 x 480), are obtained from a standard and a long-wave infrared camera at 32Hz with hardware-synchronization.
no code implementations • 1 Jul 2020 • Zakk Giacometti, Yu Zhang
We referred to this new problem as the multi-robot task allocation problem with task variants.
no code implementations • 4 Jul 2020 • Yue Sun, Kun Gao, Zhengwang Wu, Zhihao Lei, Ying WEI, Jun Ma, Xiaoping Yang, Xue Feng, Li Zhao, Trung Le Phan, Jitae Shin, Tao Zhong, Yu Zhang, Lequan Yu, Caizi Li, Ramesh Basnet, M. Omair Ahmad, M. N. S. Swamy, Wenao Ma, Qi Dou, Toan Duc Bui, Camilo Bermudez Noguera, Bennett Landman, Ian H. Gotlib, Kathryn L. Humphreys, Sarah Shultz, Longchuan Li, Sijie Niu, Weili Lin, Valerie Jewells, Gang Li, Dinggang Shen, Li Wang
Deep learning-based methods have achieved state-of-the-art performance; however, one of major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners.
1 code implementation • 18 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.
Ranked #1 on Topic Models on Arxiv HEP-TH citation graph
1 code implementation • ECCV 2020 • Junjie Zhao, Donghuan Lu, Kai Ma, Yu Zhang, Yefeng Zheng
In this paper, we propose a novel deep image clustering framework to learn a category-style latent representation in which the category information is disentangled from image style and can be directly used as the cluster assignment.
no code implementations • 23 Jul 2020 • Hongyu Li, Jihe Wang, Yu Zhang, Zi-Rui Wang, Tiejun Wang
In CovEval, a different matching process based on the idea of covering box matching is adopted for this issue.
no code implementations • 28 Jul 2020 • Zhuoyi Lin, Lei Feng, Xingzhi Guo, Yu Zhang, Rui Yin, Chee Keong Kwoh, Chi Xu
In this paper, we propose a novel representation learning-based model called COMET (COnvolutional diMEnsion inTeraction), which simultaneously models the high-order interaction patterns among historical interactions and embedding dimensions.
1 code implementation • 6 Aug 2020 • Yuan Yao, Xutao Li, Yu Zhang, Yunming Ye
In reality, however, it is not uncommon to obtain samples from multiple heterogeneous domains.
1 code implementation • 7 Aug 2020 • Wentao Ouyang, Xiuwu Zhang, Lei Zhao, Jinmei Luo, Yu Zhang, Heng Zou, Zhaojie Liu, Yanlong Du
Our study is based on UC Toutiao (a news feed service integrated with the UC Browser App, serving hundreds of millions of users daily), where the source domain is the news and the target domain is the ad.
2 code implementations • IJCAI 2020 • Yu Zhang, Houquan Zhou, Zhenghua Li
Estimating probability distribution is one of the core issues in the NLP field.
Ranked #1 on Constituency Parsing on CTB7
1 code implementation • 26 Aug 2020 • Yu Zhang, Xiaoguang Di, Bin Zhang, Ruihang Ji, Chunhui Wang
The network takes low light images as input and the enhanced V channel as condition, then it can re-enhance the contrast and brightness of the low light image and at the same time reduce noise and color distortion.
no code implementations • 26 Aug 2020 • Chunhui Li, Xingshu Chen, Haizhou Wang, Yu Zhang, Peiming Wang
Firstly, we train CAPTCHA synthesizers based on the cycle-GAN to generate some fake samples.
7 code implementations • ICLR 2021 • Nanxin Chen, Yu Zhang, Heiga Zen, Ron J. Weiss, Mohammad Norouzi, William Chan
This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density.
no code implementations • 5 Sep 2020 • Jinren Yao, Hantao Wang, Huajun Zhang, Jiandong Cai, Mingyuan Ren, Yu Zhang, Olga Korotkova
In particular, for natural water turbulence several models for the spatial power spectra have been developed based on the classic, Kolmogorov postulates.
Atmospheric and Oceanic Physics Optics
no code implementations • 9 Sep 2020 • Yafei Xu, Tian Xie, Yu Zhang
Secondly, based on the sub-modular optimization theory and the DMC pool by DMCNet, the generated combined multiple DMCs are ranked with respect to their revenue generation strength then the top three ranked campaigns are returned to the sellers' back-end management system, so that retailers can set combined multiple DMCs for their online shops just in one-shot.
no code implementations • 9 Sep 2020 • Gongbo Liang, Yu Zhang, Xiaoqin Wang, Nathan Jacobs
Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain.
no code implementations • 17 Sep 2020 • Po Li, Lei LI, Yan Fu, Jun Rong, Yu Zhang
At top of the MoE layer, we deploy a transformer layer for each task as task tower to learn task-specific information.
no code implementations • 6 Oct 2020 • Gongbo Liang, Connor Greenwell, Yu Zhang, Xiaoqin Wang, Ramakanth Kavuluru, Nathan Jacobs
A key challenge in training neural networks for a given medical imaging task is often the difficulty of obtaining a sufficient number of manually labeled examples.