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 Yang Zhang

Yang Zhang

A Lightweight and Accurate Recognition Framework for Signs of X-ray Weld Images


Oct 18, 2021
Moyun Liu, Jingming Xie, Jing Hao, Yang Zhang, Xuzhan Chen, Youping Chen

Figure 1 for A Lightweight and Accurate Recognition Framework for Signs of X-ray Weld Images
Figure 2 for A Lightweight and Accurate Recognition Framework for Signs of X-ray Weld Images
Figure 3 for A Lightweight and Accurate Recognition Framework for Signs of X-ray Weld Images
Figure 4 for A Lightweight and Accurate Recognition Framework for Signs of X-ray Weld Images

  Access Paper or Ask Questions

Revisiting IPA-based Cross-lingual Text-to-speech


Oct 18, 2021
Haitong Zhang, Haoyue Zhan, Yang Zhang, Xinyuan Yu, Yue Lin

Figure 1 for Revisiting IPA-based Cross-lingual Text-to-speech
Figure 2 for Revisiting IPA-based Cross-lingual Text-to-speech
Figure 3 for Revisiting IPA-based Cross-lingual Text-to-speech
Figure 4 for Revisiting IPA-based Cross-lingual Text-to-speech
* Submitted to ICASSP2022 
  Access Paper or Ask Questions

Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech


Oct 14, 2021
Haoyue Zhan, Xinyuan Yu, Haitong Zhang, Yang Zhang, Yue Lin

Figure 1 for Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech
Figure 2 for Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech
Figure 3 for Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech
Figure 4 for Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

Inference Attacks Against Graph Neural Networks


Oct 06, 2021
Zhikun Zhang, Min Chen, Michael Backes, Yun Shen, Yang Zhang

Figure 1 for Inference Attacks Against Graph Neural Networks
Figure 2 for Inference Attacks Against Graph Neural Networks
Figure 3 for Inference Attacks Against Graph Neural Networks
Figure 4 for Inference Attacks Against Graph Neural Networks
* 19 pages, 18 figures. To Appear in the 31st USENIX Security Symposium 
  Access Paper or Ask Questions

Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information


Oct 04, 2021
Yang Zhang, Ashkan Khakzar, Yawei Li, Azade Farshad, Seong Tae Kim, Nassir Navab

Figure 1 for Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
Figure 2 for Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
Figure 3 for Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
Figure 4 for Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
* Accepted in NeurIPS 2021 (Neural Information Processing Systems) 
  Access Paper or Ask Questions

On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis


Oct 04, 2021
Cheng-I Jeff Lai, Erica Cooper, Yang Zhang, Shiyu Chang, Kaizhi Qian, Yi-Lun Liao, Yung-Sung Chuang, Alexander H. Liu, Junichi Yamagishi, David Cox, James Glass

Figure 1 for On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
Figure 2 for On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
Figure 3 for On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
Figure 4 for On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis

  Access Paper or Ask Questions

Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation


Sep 17, 2021
Yang Zhang, Yao Wang, Zhi Han, Xi'ai Chen, Yandong Tang

Figure 1 for Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation
Figure 2 for Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation
Figure 3 for Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation
Figure 4 for Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation

  Access Paper or Ask Questions

Membership Inference Attacks Against Recommender Systems


Sep 16, 2021
Minxing Zhang, Zhaochun Ren, Zihan Wang, Pengjie Ren, Zhumin Chen, Pengfei Hu, Yang Zhang

Figure 1 for Membership Inference Attacks Against Recommender Systems
Figure 2 for Membership Inference Attacks Against Recommender Systems
Figure 3 for Membership Inference Attacks Against Recommender Systems
Figure 4 for Membership Inference Attacks Against Recommender Systems

  Access Paper or Ask Questions

A Unified Transformer-based Framework for Duplex Text Normalization


Aug 23, 2021
Tuan Manh Lai, Yang Zhang, Evelina Bakhturina, Boris Ginsburg, Heng Ji

Figure 1 for A Unified Transformer-based Framework for Duplex Text Normalization
Figure 2 for A Unified Transformer-based Framework for Duplex Text Normalization
Figure 3 for A Unified Transformer-based Framework for Duplex Text Normalization
Figure 4 for A Unified Transformer-based Framework for Duplex Text Normalization
* Under Review 
  Access Paper or Ask Questions

Deep Sequence Modeling: Development and Applications in Asset Pricing


Aug 20, 2021
Lin William Cong, Ke Tang, Jingyuan Wang, Yang Zhang


  Access Paper or Ask Questions

Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails


Aug 08, 2021
Yang Zhang, Xin Yu, Xiaobo Lu, Ping Liu

Figure 1 for Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails
Figure 2 for Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails
Figure 3 for Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails
Figure 4 for Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails

  Access Paper or Ask Questions

TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation


Jul 21, 2021
Jiawei Yang, Yao Zhang, Yuan Liang, Yang Zhang, Lei He, Zhiqiang He

Figure 1 for TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation
Figure 2 for TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation
Figure 3 for TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation
Figure 4 for TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation

  Access Paper or Ask Questions

Modality-aware Mutual Learning for Multi-modal Medical Image Segmentation


Jul 21, 2021
Yao Zhang, Jiawei Yang, Jiang Tian, Zhongchao Shi, Cheng Zhong, Yang Zhang, Zhiqiang He

Figure 1 for Modality-aware Mutual Learning for Multi-modal Medical Image Segmentation
Figure 2 for Modality-aware Mutual Learning for Multi-modal Medical Image Segmentation
Figure 3 for Modality-aware Mutual Learning for Multi-modal Medical Image Segmentation
Figure 4 for Modality-aware Mutual Learning for Multi-modal Medical Image Segmentation

  Access Paper or Ask Questions

Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix


Jul 17, 2021
Wenshuo Wang, Chen Wu, Liang Cheng, Yang Zhang

Figure 1 for Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix
Figure 2 for Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix
Figure 3 for Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix

  Access Paper or Ask Questions

Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation


Jul 01, 2021
Qiwei Zhong, Guanxiong Zeng, Danqing Zhu, Yang Zhang, Wangli Lin, Ben Chen, Jiayu Tang

Figure 1 for Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation
Figure 2 for Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation
Figure 3 for Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation
Figure 4 for Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation
* Second Place Solution, Accepted to [email protected] 
  Access Paper or Ask Questions

ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities


Jun 29, 2021
Yixin Wang, Yang Zhang, Yang Liu, Zihao Lin, Jiang Tian, Cheng Zhong, Zhongchao Shi, Jianping Fan, Zhiqiang He

Figure 1 for ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities
Figure 2 for ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities
Figure 3 for ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities
Figure 4 for ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities
* MICCAI 2021 
  Access Paper or Ask Questions

Teacher Model Fingerprinting Attacks Against Transfer Learning


Jun 23, 2021
Yufei Chen, Chao Shen, Cong Wang, Yang Zhang

Figure 1 for Teacher Model Fingerprinting Attacks Against Transfer Learning
Figure 2 for Teacher Model Fingerprinting Attacks Against Transfer Learning
Figure 3 for Teacher Model Fingerprinting Attacks Against Transfer Learning
Figure 4 for Teacher Model Fingerprinting Attacks Against Transfer Learning

  Access Paper or Ask Questions

Confidence-Guided Radiology Report Generation


Jun 22, 2021
Yixin Wang, Zihao Lin, Jiang Tian, Zhongchao Shi, Yang Zhang, Jianping Fan, Zhiqiang He

Figure 1 for Confidence-Guided Radiology Report Generation
Figure 2 for Confidence-Guided Radiology Report Generation
Figure 3 for Confidence-Guided Radiology Report Generation
Figure 4 for Confidence-Guided Radiology Report Generation
* 16 pages 
  Access Paper or Ask Questions

AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media


Jun 21, 2021
Lanyu Shang, Yang Zhang, Yuheng Zha, Yingxi Chen, Christina Youn, Dong Wang

Figure 1 for AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media
Figure 2 for AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media
Figure 3 for AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media
Figure 4 for AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media

  Access Paper or Ask Questions

Global Rhythm Style Transfer Without Text Transcriptions


Jun 16, 2021
Kaizhi Qian, Yang Zhang, Shiyu Chang, Jinjun Xiong, Chuang Gan, David Cox, Mark Hasegawa-Johnson

Figure 1 for Global Rhythm Style Transfer Without Text Transcriptions
Figure 2 for Global Rhythm Style Transfer Without Text Transcriptions
Figure 3 for Global Rhythm Style Transfer Without Text Transcriptions
Figure 4 for Global Rhythm Style Transfer Without Text Transcriptions

  Access Paper or Ask Questions

Voting for the right answer: Adversarial defense for speaker verification


Jun 15, 2021
Haibin Wu, Yang Zhang, Zhiyong Wu, Dong Wang, Hung-yi Lee

Figure 1 for Voting for the right answer: Adversarial defense for speaker verification
Figure 2 for Voting for the right answer: Adversarial defense for speaker verification
Figure 3 for Voting for the right answer: Adversarial defense for speaker verification
Figure 4 for Voting for the right answer: Adversarial defense for speaker verification
* Accepted by Interspeech 2021. Code is available at https://github.com/thuhcsi/adsv_voting 
  Access Paper or Ask Questions

Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators


Jun 11, 2021
Yonggan Fu, Yongan Zhang, Yang Zhang, David Cox, Yingyan Lin

Figure 1 for Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
Figure 2 for Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
Figure 3 for Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
Figure 4 for Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
* Accepted at ICML 2021 
  Access Paper or Ask Questions

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition


Jun 10, 2021
Cheng-I Jeff Lai, Yang Zhang, Alexander H. Liu, Shiyu Chang, Yi-Lun Liao, Yung-Sung Chuang, Kaizhi Qian, Sameer Khurana, David Cox, James Glass

Figure 1 for PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
Figure 2 for PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
Figure 3 for PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
Figure 4 for PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition

  Access Paper or Ask Questions

Conversational Question Answering: A Survey


Jun 03, 2021
Munazza Zaib, Wei Emma Zhang, Quan Z. Sheng, Adnan Mahmood, Yang Zhang

Figure 1 for Conversational Question Answering: A Survey
Figure 2 for Conversational Question Answering: A Survey
Figure 3 for Conversational Question Answering: A Survey
Figure 4 for Conversational Question Answering: A Survey

  Access Paper or Ask Questions

SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services


May 17, 2021
Yang Zhang, Vahid Noroozi, Evelina Bakhturina, Boris Ginsburg

Figure 1 for SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services
Figure 2 for SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services
Figure 3 for SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services
Figure 4 for SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services

  Access Paper or Ask Questions

Causal Intervention for Leveraging Popularity Bias in Recommendation


May 13, 2021
Yang Zhang, Fuli Feng, Xiangnan He, Tianxin Wei, Chonggang Song, Guohui Ling, Yongdong Zhang

Figure 1 for Causal Intervention for Leveraging Popularity Bias in Recommendation
Figure 2 for Causal Intervention for Leveraging Popularity Bias in Recommendation
Figure 3 for Causal Intervention for Leveraging Popularity Bias in Recommendation
Figure 4 for Causal Intervention for Leveraging Popularity Bias in Recommendation
* Appear in SIGIR 2021 
  Access Paper or Ask Questions

NeMo Inverse Text Normalization: From Development To Production


Apr 11, 2021
Yang Zhang, Evelina Bakhturina, Kyle Gorman, Boris Ginsburg

Figure 1 for NeMo Inverse Text Normalization: From Development To Production
Figure 2 for NeMo Inverse Text Normalization: From Development To Production
Figure 3 for NeMo Inverse Text Normalization: From Development To Production
Figure 4 for NeMo Inverse Text Normalization: From Development To Production

  Access Paper or Ask Questions