Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Rui Zhao

Rui Zhao

On Addressing Practical Challenges for RNN-Transducer


May 04, 2021
Rui Zhao, Jian Xue, Jinyu Li, Wenning Wei, Lei He, Yifan Gong

Figure 1 for On Addressing Practical Challenges for RNN-Transducer
Figure 2 for On Addressing Practical Challenges for RNN-Transducer
Figure 3 for On Addressing Practical Challenges for RNN-Transducer
Figure 4 for On Addressing Practical Challenges for RNN-Transducer
* 5 pages 
  Access Paper or Ask Questions

Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification


Apr 27, 2021
Yixiao Ge, Ching Lam Choi, Xiao Zhang, Peipei Zhao, Feng Zhu, Rui Zhao, Hongsheng Li

Figure 1 for Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Figure 2 for Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Figure 3 for Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Figure 4 for Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
* Project Page: https://geyixiao.com/projects/bake 
  Access Paper or Ask Questions

Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval


Mar 29, 2021
Rui Zhao, Kecheng Zheng, Zheng-Jun Zha, Hongtao Xie, Jiebo Luo

Figure 1 for Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval
Figure 2 for Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval
Figure 3 for Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval
Figure 4 for Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval
* Technical Report 
  Access Paper or Ask Questions

Mutual Information State Intrinsic Control


Mar 15, 2021
Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu

Figure 1 for Mutual Information State Intrinsic Control
Figure 2 for Mutual Information State Intrinsic Control
Figure 3 for Mutual Information State Intrinsic Control
Figure 4 for Mutual Information State Intrinsic Control
* Published in International Conference on Learning Representations (ICLR 2021) as Spotlight (top 5%), Link: https://openreview.net/forum?id=OthEq8I5v1. arXiv admin note: text overlap with arXiv:2002.01963 
  Access Paper or Ask Questions

Consensus-Guided Correspondence Denoising


Jan 03, 2021
Chen Zhao, Yixiao Ge, Jiaqi Yang, Feng Zhu, Rui Zhao, Hongsheng Li

Figure 1 for Consensus-Guided Correspondence Denoising
Figure 2 for Consensus-Guided Correspondence Denoising
Figure 3 for Consensus-Guided Correspondence Denoising
Figure 4 for Consensus-Guided Correspondence Denoising

  Access Paper or Ask Questions

Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition


Nov 03, 2020
Zhong Meng, Sarangarajan Parthasarathy, Eric Sun, Yashesh Gaur, Naoyuki Kanda, Liang Lu, Xie Chen, Rui Zhao, Jinyu Li, Yifan Gong

Figure 1 for Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
Figure 2 for Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
Figure 3 for Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
Figure 4 for Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
* 2021 IEEE Spoken Language Technology Workshop (SLT) 
 * 8 pages, 2 figures, SLT 2021 
  Access Paper or Ask Questions

Vulnerability of the Neural Networks Against Adversarial Examples: A Survey


Nov 02, 2020
Rui Zhao

Figure 1 for Vulnerability of the Neural Networks Against Adversarial Examples: A Survey
Figure 2 for Vulnerability of the Neural Networks Against Adversarial Examples: A Survey

  Access Paper or Ask Questions

NTGAN: Learning Blind Image Denoising without Clean Reference


Sep 09, 2020
Rui Zhao, Daniel P. K. Lun, Kin-Man Lam

Figure 1 for NTGAN: Learning Blind Image Denoising without Clean Reference
Figure 2 for NTGAN: Learning Blind Image Denoising without Clean Reference
Figure 3 for NTGAN: Learning Blind Image Denoising without Clean Reference
* BMVC 2020 
  Access Paper or Ask Questions

Transfer Learning Approaches for Streaming End-to-End Speech Recognition System


Aug 17, 2020
Vikas Joshi, Rui Zhao, Rupesh R. Mehta, Kshitiz Kumar, Jinyu Li

Figure 1 for Transfer Learning Approaches for Streaming End-to-End Speech Recognition System
Figure 2 for Transfer Learning Approaches for Streaming End-to-End Speech Recognition System
Figure 3 for Transfer Learning Approaches for Streaming End-to-End Speech Recognition System
Figure 4 for Transfer Learning Approaches for Streaming End-to-End Speech Recognition System

  Access Paper or Ask Questions

Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations


Aug 11, 2020
Yongchao Liu, Yue Jin, Yong Chen, Teng Teng, Hang Ou, Rui Zhao, Yao Zhang

Figure 1 for Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations
Figure 2 for Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations
Figure 3 for Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations
Figure 4 for Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations
* 10 pages, 3 figures 
  Access Paper or Ask Questions

Deep Reinforcement Learning Based Mobile Edge Computing for Intelligent Internet of Things


Aug 01, 2020
Rui Zhao, Xinjie Wang, Junjuan Xia, Liseng Fan

Figure 1 for Deep Reinforcement Learning Based Mobile Edge Computing for Intelligent Internet of Things
Figure 2 for Deep Reinforcement Learning Based Mobile Edge Computing for Intelligent Internet of Things
Figure 3 for Deep Reinforcement Learning Based Mobile Edge Computing for Intelligent Internet of Things
Figure 4 for Deep Reinforcement Learning Based Mobile Edge Computing for Intelligent Internet of Things

  Access Paper or Ask Questions

Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability


Jul 30, 2020
Jinyu Li, Rui Zhao, Zhong Meng, Yanqing Liu, Wenning Wei, Sarangarajan Parthasarathy, Vadim Mazalov, Zhenghao Wang, Lei He, Sheng Zhao, Yifan Gong

Figure 1 for Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
Figure 2 for Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
Figure 3 for Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
Figure 4 for Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
* Accepted by Interspeech 2020 
  Access Paper or Ask Questions

Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing


Jul 09, 2020
Rui Zhao, Tianshan Liu, Jun Xiao, Daniel P. K. Lun, Kin-Man Lam

Figure 1 for Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
Figure 2 for Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
Figure 3 for Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
Figure 4 for Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
* ICPR 2020 
  Access Paper or Ask Questions

Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score


Jul 02, 2020
Zhiliang Wu, Yinchong Yang, Yunpu Ma, Yushan Liu, Rui Zhao, Michael Moor, Volker Tresp

Figure 1 for Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score
Figure 2 for Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score
Figure 3 for Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score
Figure 4 for Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score

  Access Paper or Ask Questions

Continual Representation Learning for Biometric Identification


Jun 28, 2020
Bo Zhao, Shixiang Tang, Dapeng Chen, Hakan Bilen, Rui Zhao

Figure 1 for Continual Representation Learning for Biometric Identification
Figure 2 for Continual Representation Learning for Biometric Identification
Figure 3 for Continual Representation Learning for Biometric Identification
Figure 4 for Continual Representation Learning for Biometric Identification

  Access Paper or Ask Questions

Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis


Jun 28, 2020
Rui Zhao, Kin-Man Lam, Daniel P. K. Lun

Figure 1 for Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis
Figure 2 for Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis
Figure 3 for Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis
Figure 4 for Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis
* ICIP 2019 
  Access Paper or Ask Questions

Self-supervising Fine-grained Region Similarities for Large-scale Image Localization


Jun 06, 2020
Yixiao Ge, Haibo Wang, Feng Zhu, Rui Zhao, Hongsheng Li

Figure 1 for Self-supervising Fine-grained Region Similarities for Large-scale Image Localization
Figure 2 for Self-supervising Fine-grained Region Similarities for Large-scale Image Localization
Figure 3 for Self-supervising Fine-grained Region Similarities for Large-scale Image Localization
Figure 4 for Self-supervising Fine-grained Region Similarities for Large-scale Image Localization

  Access Paper or Ask Questions

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID


Jun 04, 2020
Yixiao Ge, Dapeng Chen, Feng Zhu, Rui Zhao, Hongsheng Li

Figure 1 for Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
Figure 2 for Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
Figure 3 for Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
Figure 4 for Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

  Access Paper or Ask Questions

On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition


May 28, 2020
Jinyu Li, Yu Wu, Yashesh Gaur, Chengyi Wang, Rui Zhao, Shujie Liu

Figure 1 for On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition
Figure 2 for On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition
* submitted to Interspeech 2020 
  Access Paper or Ask Questions

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification


May 16, 2020
Shijie Yu, Shihua Li, Dapeng Chen, Rui Zhao, Junjie Yan, Yu Qiao

Figure 1 for COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
Figure 2 for COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
Figure 3 for COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
Figure 4 for COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
* Accepted by CVPR2020 
  Access Paper or Ask Questions

Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition


May 01, 2020
Hu Hu, Rui Zhao, Jinyu Li, Liang Lu, Yifan Gong

Figure 1 for Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition
Figure 2 for Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition
Figure 3 for Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition
Figure 4 for Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition
* Accepted by ICASSP 2020 
  Access Paper or Ask Questions

Learning to Cluster Faces via Confidence and Connectivity Estimation


Apr 03, 2020
Lei Yang, Dapeng Chen, Xiaohang Zhan, Rui Zhao, Chen Change Loy, Dahua Lin

Figure 1 for Learning to Cluster Faces via Confidence and Connectivity Estimation
Figure 2 for Learning to Cluster Faces via Confidence and Connectivity Estimation
Figure 3 for Learning to Cluster Faces via Confidence and Connectivity Estimation
Figure 4 for Learning to Cluster Faces via Confidence and Connectivity Estimation
* 8 pages, 6 figures, CVPR 2020 
  Access Paper or Ask Questions

High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model


Mar 17, 2020
Jinyu Li, Rui Zhao, Eric Sun, Jeremy H. M. Wong, Amit Das, Zhong Meng, Yifan Gong

Figure 1 for High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model
Figure 2 for High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model
Figure 3 for High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model
Figure 4 for High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model
* Accepted by ICASSP 2020 
  Access Paper or Ask Questions

Structured Domain Adaptation for Unsupervised Person Re-identification


Mar 14, 2020
Yixiao Ge, Feng Zhu, Rui Zhao, Hongsheng Li

Figure 1 for Structured Domain Adaptation for Unsupervised Person Re-identification
Figure 2 for Structured Domain Adaptation for Unsupervised Person Re-identification
Figure 3 for Structured Domain Adaptation for Unsupervised Person Re-identification
Figure 4 for Structured Domain Adaptation for Unsupervised Person Re-identification

  Access Paper or Ask Questions

Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning


Feb 05, 2020
Rui Zhao, Volker Tresp, Wei Xu

Figure 1 for Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning
Figure 2 for Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning
Figure 3 for Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning
Figure 4 for Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning
* 12 pages, 8 figures 
  Access Paper or Ask Questions

Towards a computer-interpretable actionable formal model to encode data governance rules


Nov 19, 2019
Rui Zhao, Malcolm Atkinson

Figure 1 for Towards a computer-interpretable actionable formal model to encode data governance rules
Figure 2 for Towards a computer-interpretable actionable formal model to encode data governance rules
Figure 3 for Towards a computer-interpretable actionable formal model to encode data governance rules
Figure 4 for Towards a computer-interpretable actionable formal model to encode data governance rules
* The non-draft version of this paper has been submitted and accepted to BC2DC 19 (at IEEE eScience 2019) 
  Access Paper or Ask Questions

Improving RNN Transducer Modeling for End-to-End Speech Recognition


Sep 26, 2019
Jinyu Li, Rui Zhao, Hu Hu, Yifan Gong

Figure 1 for Improving RNN Transducer Modeling for End-to-End Speech Recognition
Figure 2 for Improving RNN Transducer Modeling for End-to-End Speech Recognition
Figure 3 for Improving RNN Transducer Modeling for End-to-End Speech Recognition
Figure 4 for Improving RNN Transducer Modeling for End-to-End Speech Recognition
* Accepted by IEEE ASRU workshop, 2019 
  Access Paper or Ask Questions