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 Yi Zhang

Yi Zhang

Rethinking Noise Synthesis and Modeling in Raw Denoising


Oct 10, 2021
Yi Zhang, Hongwei Qin, Xiaogang Wang, Hongsheng Li

Figure 1 for Rethinking Noise Synthesis and Modeling in Raw Denoising
Figure 2 for Rethinking Noise Synthesis and Modeling in Raw Denoising
Figure 3 for Rethinking Noise Synthesis and Modeling in Raw Denoising
Figure 4 for Rethinking Noise Synthesis and Modeling in Raw Denoising
* ICCV2021 
  Access Paper or Ask Questions

An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design


Oct 10, 2021
Yi Zhang

Figure 1 for An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
Figure 2 for An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
Figure 3 for An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
Figure 4 for An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
* 26 pages, 6 figures, 3 tables, 253 references 
  Access Paper or Ask Questions

Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings


Oct 06, 2021
Sawsan Alqahtani, Garima Lalwani, Yi Zhang, Salvatore Romeo, Saab Mansour

Figure 1 for Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
Figure 2 for Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
Figure 3 for Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
Figure 4 for Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
* EMNLP 2021 
  Access Paper or Ask Questions

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System


Sep 29, 2021
Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, Yi Zhang

Figure 1 for Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Figure 2 for Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Figure 3 for Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Figure 4 for Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

  Access Paper or Ask Questions

Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder


Sep 09, 2021
Elman Mansimov, Yi Zhang

Figure 1 for Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder
Figure 2 for Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder
Figure 3 for Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder
Figure 4 for Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder

  Access Paper or Ask Questions

End to end hyperspectral imaging system with coded compression imaging process


Sep 06, 2021
Hui Xie, Zhuang Zhao, Jing Han, Yi Zhang, Lianfa Bai, Jun Lu

Figure 1 for End to end hyperspectral imaging system with coded compression imaging process
Figure 2 for End to end hyperspectral imaging system with coded compression imaging process
Figure 3 for End to end hyperspectral imaging system with coded compression imaging process
Figure 4 for End to end hyperspectral imaging system with coded compression imaging process

  Access Paper or Ask Questions

DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising


Aug 24, 2021
Zhizhong Huang, Junping Zhang, Yi Zhang, Hongming Shan

Figure 1 for DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
Figure 2 for DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
Figure 3 for DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
Figure 4 for DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising

  Access Paper or Ask Questions

SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity Recognition


Aug 17, 2021
Ling Chen, Yi Zhang, Sirou Zhu, Shenghuan Miao, Liangying Peng, Rong Hu, Mingqi Lv

Figure 1 for SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity Recognition
Figure 2 for SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity Recognition
Figure 3 for SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity Recognition
Figure 4 for SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity Recognition

  Access Paper or Ask Questions

Team Power and Hierarchy: Understanding Team Success


Aug 09, 2021
Huimin Xu, Yi Bu, Meijun Liu, Chenwei Zhang, Mengyi Sun, Yi Zhang, Eric Meyer, Eduardo Salas, Ying Ding

Figure 1 for Team Power and Hierarchy: Understanding Team Success
Figure 2 for Team Power and Hierarchy: Understanding Team Success
Figure 3 for Team Power and Hierarchy: Understanding Team Success
Figure 4 for Team Power and Hierarchy: Understanding Team Success

  Access Paper or Ask Questions

DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning


Jul 25, 2021
Haoyi Niu, Jianming Hu, Zheyu Cui, Yi Zhang

Figure 1 for DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning
Figure 2 for DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning
Figure 3 for DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning
Figure 4 for DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning
* 8 pages, 7 figures 
  Access Paper or Ask Questions

ASOD60K: Audio-Induced Salient Object Detection in Panoramic Videos


Jul 24, 2021
Yi Zhang, Fang-Yi Chao, Ge-Peng Ji, Deng-Ping Fan, Lu Zhang, Ling Shao

Figure 1 for ASOD60K: Audio-Induced Salient Object Detection in Panoramic Videos
Figure 2 for ASOD60K: Audio-Induced Salient Object Detection in Panoramic Videos
Figure 3 for ASOD60K: Audio-Induced Salient Object Detection in Panoramic Videos
Figure 4 for ASOD60K: Audio-Induced Salient Object Detection in Panoramic Videos
* 22 pages, 17 figures, 7 tables (Project Page: https://github.com/PanoAsh/ASOD60K) 
  Access Paper or Ask Questions

Semi-Supervised Learning with Multi-Head Co-Training


Jul 10, 2021
Mingcai Chen, Yuntao Du, Yi Zhang, Shuwei Qian, Chongjun Wang

Figure 1 for Semi-Supervised Learning with Multi-Head Co-Training
Figure 2 for Semi-Supervised Learning with Multi-Head Co-Training
Figure 3 for Semi-Supervised Learning with Multi-Head Co-Training
Figure 4 for Semi-Supervised Learning with Multi-Head Co-Training

  Access Paper or Ask Questions

Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning


Jun 28, 2021
Yi Zhang, Sheng Huang, Xi Peng, Dan Yang

Figure 1 for Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
Figure 2 for Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
Figure 3 for Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
Figure 4 for Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
* 13 pages 
  Access Paper or Ask Questions

Novelty Detection via Contrastive Learning with Negative Data Augmentation


Jun 18, 2021
Chengwei Chen, Yuan Xie, Shaohui Lin, Ruizhi Qiao, Jian Zhou, Xin Tan, Yi Zhang, Lizhuang Ma

Figure 1 for Novelty Detection via Contrastive Learning with Negative Data Augmentation
Figure 2 for Novelty Detection via Contrastive Learning with Negative Data Augmentation
Figure 3 for Novelty Detection via Contrastive Learning with Negative Data Augmentation
Figure 4 for Novelty Detection via Contrastive Learning with Negative Data Augmentation
* IJCAI2021 
  Access Paper or Ask Questions

Salient Object Ranking with Position-Preserved Attention


Jun 10, 2021
Hao Fang, Daoxin Zhang, Yi Zhang, Minghao Chen, Jiawei Li, Yao Hu, Deng Cai, Xiaofei He

Figure 1 for Salient Object Ranking with Position-Preserved Attention
Figure 2 for Salient Object Ranking with Position-Preserved Attention
Figure 3 for Salient Object Ranking with Position-Preserved Attention
Figure 4 for Salient Object Ranking with Position-Preserved Attention

  Access Paper or Ask Questions

SHD360: A Benchmark Dataset for Salient Human Detection in 360° Videos


Jun 04, 2021
Yi Zhang, Lu Zhang, Jing Zhang, Kang Wang, Wassim Hamidouche, Olivier Deforges

Figure 1 for SHD360: A Benchmark Dataset for Salient Human Detection in 360° Videos
Figure 2 for SHD360: A Benchmark Dataset for Salient Human Detection in 360° Videos
Figure 3 for SHD360: A Benchmark Dataset for Salient Human Detection in 360° Videos
Figure 4 for SHD360: A Benchmark Dataset for Salient Human Detection in 360° Videos
* 5 pages 
  Access Paper or Ask Questions

Visual Question Rewriting for Increasing Response Rate


Jun 04, 2021
Jiayi Wei, Xilian Li, Yi Zhang, Xin Wang

Figure 1 for Visual Question Rewriting for Increasing Response Rate
Figure 2 for Visual Question Rewriting for Increasing Response Rate
Figure 3 for Visual Question Rewriting for Increasing Response Rate
Figure 4 for Visual Question Rewriting for Increasing Response Rate

  Access Paper or Ask Questions

Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge


May 31, 2021
Yi Zhang, Lei Li, Yunfang Wu, Qi Su, Xu Sun

Figure 1 for Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge
Figure 2 for Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge
Figure 3 for Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge
Figure 4 for Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge

  Access Paper or Ask Questions

Multi-turn Dialog System on Single-turn Data in Medical Domain


May 27, 2021
Nazib Sorathiya, Chuan-An Lin, Daniel Chen Daniel Xiong, Scott Zin, Yi Zhang, He Sarina Yang, Sharon Xiaolei Huang

Figure 1 for Multi-turn Dialog System on Single-turn Data in Medical Domain

  Access Paper or Ask Questions

Context-aware Cross-level Fusion Network for Camouflaged Object Detection


May 26, 2021
Yujia Sun, Geng Chen, Tao Zhou, Yi Zhang, Nian Liu

Figure 1 for Context-aware Cross-level Fusion Network for Camouflaged Object Detection
Figure 2 for Context-aware Cross-level Fusion Network for Camouflaged Object Detection
Figure 3 for Context-aware Cross-level Fusion Network for Camouflaged Object Detection
Figure 4 for Context-aware Cross-level Fusion Network for Camouflaged Object Detection
* 7 pages, 4 figures. Accepted by IJCAI-2021 
  Access Paper or Ask Questions

Learning Synergistic Attention for Light Field Salient Object Detection


May 16, 2021
Yi Zhang, Geng Chen, Qian Chen, Yujia Sun, Olivier Deforges, Wassim Hamidouche, Lu Zhang

Figure 1 for Learning Synergistic Attention for Light Field Salient Object Detection
Figure 2 for Learning Synergistic Attention for Light Field Salient Object Detection
Figure 3 for Learning Synergistic Attention for Light Field Salient Object Detection
Figure 4 for Learning Synergistic Attention for Light Field Salient Object Detection
* 14 pages, 12 figures 
  Access Paper or Ask Questions

One Network to Solve Them All: A Sequential Multi-Task Joint Learning Network Framework for MR Imaging Pipeline


May 14, 2021
Zhiwen Wang, Wenjun Xia, Zexin Lu, Yongqiang Huang, Yan Liu, Hu Chen, Jiliu Zhou, Yi Zhang

Figure 1 for One Network to Solve Them All: A Sequential Multi-Task Joint Learning Network Framework for MR Imaging Pipeline
Figure 2 for One Network to Solve Them All: A Sequential Multi-Task Joint Learning Network Framework for MR Imaging Pipeline
Figure 3 for One Network to Solve Them All: A Sequential Multi-Task Joint Learning Network Framework for MR Imaging Pipeline
Figure 4 for One Network to Solve Them All: A Sequential Multi-Task Joint Learning Network Framework for MR Imaging Pipeline
* 9 pages, 3 figures 
  Access Paper or Ask Questions

CMA-Net: A Cascaded Mutual Attention Network for Light Field Salient Object Detection


May 07, 2021
Yi Zhang, Lu Zhang, Wassim Hamidouche, Olivier Deforges

Figure 1 for CMA-Net: A Cascaded Mutual Attention Network for Light Field Salient Object Detection
Figure 2 for CMA-Net: A Cascaded Mutual Attention Network for Light Field Salient Object Detection
Figure 3 for CMA-Net: A Cascaded Mutual Attention Network for Light Field Salient Object Detection
Figure 4 for CMA-Net: A Cascaded Mutual Attention Network for Light Field Salient Object Detection
* 5 pages, 4 figures, 2 tables 
  Access Paper or Ask Questions

Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates


May 07, 2021
Yuqing Xie, Yi-an Lai, Yuanjun Xiong, Yi Zhang, Stefano Soatto

Figure 1 for Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Figure 2 for Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Figure 3 for Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Figure 4 for Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
* 13 pages, 3 figures, Accepted at ACL 2021 main conference 
  Access Paper or Ask Questions

Deformable TDNN with adaptive receptive fields for speech recognition


Apr 30, 2021
Keyu An, Yi Zhang, Zhijian Ou

Figure 1 for Deformable TDNN with adaptive receptive fields for speech recognition
Figure 2 for Deformable TDNN with adaptive receptive fields for speech recognition
Figure 3 for Deformable TDNN with adaptive receptive fields for speech recognition
Figure 4 for Deformable TDNN with adaptive receptive fields for speech recognition
* 5 pages. submitted to Interspeech 2021 
  Access Paper or Ask Questions