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 Shengyu Zhang

Shengyu Zhang

ODBO: Bayesian Optimization with Search Space Prescreening for Directed Protein Evolution


May 19, 2022
Lixue Cheng, Ziyi Yang, Benben Liao, Changyu Hsieh, Shengyu Zhang

Figure 1 for ODBO: Bayesian Optimization with Search Space Prescreening for Directed Protein Evolution
Figure 2 for ODBO: Bayesian Optimization with Search Space Prescreening for Directed Protein Evolution
Figure 3 for ODBO: Bayesian Optimization with Search Space Prescreening for Directed Protein Evolution
Figure 4 for ODBO: Bayesian Optimization with Search Space Prescreening for Directed Protein Evolution
* 24 pages, 10 figures 
  Access Paper or Ask Questions

Contrastive Learning with Positive-Negative Frame Mask for Music Representation


Apr 03, 2022
Dong Yao, Zhou Zhao, Shengyu Zhang, Jieming Zhu, Yudong Zhu, Rui Zhang, Xiuqiang He

Figure 1 for Contrastive Learning with Positive-Negative Frame Mask for Music Representation
Figure 2 for Contrastive Learning with Positive-Negative Frame Mask for Music Representation
Figure 3 for Contrastive Learning with Positive-Negative Frame Mask for Music Representation
Figure 4 for Contrastive Learning with Positive-Negative Frame Mask for Music Representation
* Accepted by WWW2022 
  Access Paper or Ask Questions

BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation


Mar 21, 2022
Wenqiao Zhang, Lei Zhu, James Hallinan, Andrew Makmur, Shengyu Zhang, Qingpeng Cai, Beng Chin Ooi

Figure 1 for BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
Figure 2 for BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
Figure 3 for BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
Figure 4 for BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
* CVPR 2022 
 * 11 pages 
  Access Paper or Ask Questions

End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding


Mar 15, 2022
Mengze Li, Tianbao Wang, Haoyu Zhang, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Wenming Tan, Jin Wang, Peng Wang, Shiliang Pu, Fei Wu

Figure 1 for End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding
Figure 2 for End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding
Figure 3 for End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding
Figure 4 for End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding

  Access Paper or Ask Questions

A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation


Feb 21, 2022
Dongqi Wang, Shengyu Zhang, Zhipeng Di, Xin Lin, Weihua Zhou, Fei Wu

Figure 1 for A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation
Figure 2 for A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation
Figure 3 for A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation
Figure 4 for A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation

  Access Paper or Ask Questions

Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer


Jan 29, 2022
Yue Wan, Benben Liao, Chang-Yu Hsieh, Shengyu Zhang


  Access Paper or Ask Questions

MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning


Dec 13, 2021
Wenqiao Zhang, Haochen Shi, Jiannan Guo, Shengyu Zhang, Qingpeng Cai, Juncheng Li, Sihui Luo, Yueting Zhuang

Figure 1 for MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning
Figure 2 for MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning
Figure 3 for MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning
Figure 4 for MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning

  Access Paper or Ask Questions

Learning Large-scale Network Embedding from Representative Subgraph


Dec 02, 2021
Junsheng Kong, Weizhao Li, Ben Liao, Jiezhong Qiu, Chang-Yu, Hsieh, Yi Cai, Jinhui Zhu, Shengyu Zhang

Figure 1 for Learning Large-scale Network Embedding from Representative Subgraph
Figure 2 for Learning Large-scale Network Embedding from Representative Subgraph
Figure 3 for Learning Large-scale Network Embedding from Representative Subgraph
Figure 4 for Learning Large-scale Network Embedding from Representative Subgraph
* 10 pages, 5 figures 
  Access Paper or Ask Questions

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey


Nov 12, 2021
Jiangchao Yao, Shengyu Zhang, Yang Yao, Feng Wang, Jianxin Ma, Jianwei Zhang, Yunfei Chu, Luo Ji, Kunyang Jia, Tao Shen, Anpeng Wu, Fengda Zhang, Ziqi Tan, Kun Kuang, Chao Wu, Fei Wu, Jingren Zhou, Hongxia Yang

Figure 1 for Edge-Cloud Polarization and Collaboration: A Comprehensive Survey
Figure 2 for Edge-Cloud Polarization and Collaboration: A Comprehensive Survey
Figure 3 for Edge-Cloud Polarization and Collaboration: A Comprehensive Survey
* 20 pages. Under Submission. arXiv admin note: text overlap with arXiv:2103.13630 by other authors 
  Access Paper or Ask Questions

Multi-trends Enhanced Dynamic Micro-video Recommendation


Oct 08, 2021
Yujie Lu, Yingxuan Huang, Shengyu Zhang, Wei Han, Hui Chen, Zhou Zhao, Fei Wu

Figure 1 for Multi-trends Enhanced Dynamic Micro-video Recommendation
Figure 2 for Multi-trends Enhanced Dynamic Micro-video Recommendation
Figure 3 for Multi-trends Enhanced Dynamic Micro-video Recommendation
Figure 4 for Multi-trends Enhanced Dynamic Micro-video Recommendation
* 11 pages, 2 figures 
  Access Paper or Ask Questions

Stable Prediction on Graphs with Agnostic Distribution Shift


Oct 08, 2021
Shengyu Zhang, Kun Kuang, Jiezhong Qiu, Jin Yu, Zhou Zhao, Hongxia Yang, Zhongfei Zhang, Fei Wu

Figure 1 for Stable Prediction on Graphs with Agnostic Distribution Shift
Figure 2 for Stable Prediction on Graphs with Agnostic Distribution Shift
Figure 3 for Stable Prediction on Graphs with Agnostic Distribution Shift
Figure 4 for Stable Prediction on Graphs with Agnostic Distribution Shift
* 11 pages, 6 figures 
  Access Paper or Ask Questions

Why Do We Click: Visual Impression-aware News Recommendation


Sep 26, 2021
Jiahao Xun, Shengyu Zhang, Zhou Zhao, Jieming Zhu, Qi Zhang, Jingjie Li, Xiuqiang He, Xiaofei He, Tat-Seng Chua, Fei Wu

Figure 1 for Why Do We Click: Visual Impression-aware News Recommendation
Figure 2 for Why Do We Click: Visual Impression-aware News Recommendation
Figure 3 for Why Do We Click: Visual Impression-aware News Recommendation
Figure 4 for Why Do We Click: Visual Impression-aware News Recommendation
* Accepted by ACM Multimedia 2021 
  Access Paper or Ask Questions

Fast Extraction of Word Embedding from Q-contexts


Sep 15, 2021
Junsheng Kong, Weizhao Li, Zeyi Liu, Ben Liao, Jiezhong Qiu, Chang-Yu Hsieh, Yi Cai, Shengyu Zhang

Figure 1 for Fast Extraction of Word Embedding from Q-contexts
Figure 2 for Fast Extraction of Word Embedding from Q-contexts
Figure 3 for Fast Extraction of Word Embedding from Q-contexts
Figure 4 for Fast Extraction of Word Embedding from Q-contexts
* Accepted by CIKM 2021 
  Access Paper or Ask Questions

CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation


Sep 11, 2021
Shengyu Zhang, Dong Yao, Zhou Zhao, Tat-seng Chua, Fei Wu

Figure 1 for CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
Figure 2 for CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
Figure 3 for CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
Figure 4 for CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation
* Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021) 
  Access Paper or Ask Questions

Modeling High-order Interactions across Multi-interests for Micro-video Reommendation


Apr 01, 2021
Dong Yao, Shengyu Zhang, Zhou Zhao, Wenyan Fan, Jieming Zhu, Xiuqiang He, Fei Wu

Figure 1 for Modeling High-order Interactions across Multi-interests for Micro-video Reommendation
Figure 2 for Modeling High-order Interactions across Multi-interests for Micro-video Reommendation
Figure 3 for Modeling High-order Interactions across Multi-interests for Micro-video Reommendation
* accepted to AAAI 2021 
  Access Paper or Ask Questions

MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination


Oct 02, 2020
Shengyu Zhang, Donghui Wang, Zhou Zhao, Siliang Tang, Di Xie, Fei Wu

Figure 1 for MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination
Figure 2 for MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination
Figure 3 for MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination
Figure 4 for MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination
* 8 pages, 6 figures 
  Access Paper or Ask Questions

DeVLBert: Learning Deconfounded Visio-Linguistic Representations


Aug 16, 2020
Shengyu Zhang, Tan Jiang, Tan Wang, Kun Kuang, Zhou Zhao, Jianke Zhu, Jin Yu, Hongxia Yang, Fei Wu

Figure 1 for DeVLBert: Learning Deconfounded Visio-Linguistic Representations
Figure 2 for DeVLBert: Learning Deconfounded Visio-Linguistic Representations
Figure 3 for DeVLBert: Learning Deconfounded Visio-Linguistic Representations
Figure 4 for DeVLBert: Learning Deconfounded Visio-Linguistic Representations
* 10 pages, 4 figures, to appear in ACM MM 2020 proceedings 
  Access Paper or Ask Questions

Poet: Product-oriented Video Captioner for E-commerce


Aug 16, 2020
Shengyu Zhang, Ziqi Tan, Jin Yu, Zhou Zhao, Kun Kuang, Jie Liu, Jingren Zhou, Hongxia Yang, Fei Wu

Figure 1 for Poet: Product-oriented Video Captioner for E-commerce
Figure 2 for Poet: Product-oriented Video Captioner for E-commerce
Figure 3 for Poet: Product-oriented Video Captioner for E-commerce
Figure 4 for Poet: Product-oriented Video Captioner for E-commerce
* 10 pages, 3 figures, to appear in ACM MM 2020 proceedings 
  Access Paper or Ask Questions

Comprehensive Information Integration Modeling Framework for Video Titling


Jun 24, 2020
Shengyu Zhang, Ziqi Tan, Jin Yu, Zhou Zhao, Kun Kuang, Tan Jiang, Jingren Zhou, Hongxia Yang, Fei Wu

Figure 1 for Comprehensive Information Integration Modeling Framework for Video Titling
Figure 2 for Comprehensive Information Integration Modeling Framework for Video Titling
Figure 3 for Comprehensive Information Integration Modeling Framework for Video Titling
Figure 4 for Comprehensive Information Integration Modeling Framework for Video Titling
* 11 pages, 6 figures, to appear in KDD 2020 proceedings 
  Access Paper or Ask Questions

Adaptive Double-Exploration Tradeoff for Outlier Detection


May 13, 2020
Xiaojin Zhang, Honglei Zhuang, Shengyu Zhang, Yuan Zhou

Figure 1 for Adaptive Double-Exploration Tradeoff for Outlier Detection
Figure 2 for Adaptive Double-Exploration Tradeoff for Outlier Detection
Figure 3 for Adaptive Double-Exploration Tradeoff for Outlier Detection

  Access Paper or Ask Questions

Grounded and Controllable Image Completion by Incorporating Lexical Semantics


Feb 29, 2020
Shengyu Zhang, Tan Jiang, Qinghao Huang, Ziqi Tan, Zhou Zhao, Siliang Tang, Jin Yu, Hongxia Yang, Yi Yang, Fei Wu

Figure 1 for Grounded and Controllable Image Completion by Incorporating Lexical Semantics
Figure 2 for Grounded and Controllable Image Completion by Incorporating Lexical Semantics
Figure 3 for Grounded and Controllable Image Completion by Incorporating Lexical Semantics
Figure 4 for Grounded and Controllable Image Completion by Incorporating Lexical Semantics
* 9 pages, 9 figures 
  Access Paper or Ask Questions

Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models


Jun 22, 2019
Guangyong Chen, Pengfei Chen, Chang-Yu Hsieh, Chee-Kong Lee, Benben Liao, Renjie Liao, Weiwen Liu, Jiezhong Qiu, Qiming Sun, Jie Tang, Richard Zemel, Shengyu Zhang

Figure 1 for Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
Figure 2 for Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
Figure 3 for Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
Figure 4 for Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
* Authors are listed in alphabetical order 
  Access Paper or Ask Questions

A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR


Jun 13, 2019
Pengfei Chen, Benben Liao, Guangyong Chen, Shengyu Zhang

Figure 1 for A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR
Figure 2 for A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR
Figure 3 for A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR
Figure 4 for A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR
* Correspondence to: Guangyong Chen  
  Access Paper or Ask Questions

Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization


Jun 13, 2019
Pengfei Chen, Weiwen Liu, Chang-Yu Hsieh, Guangyong Chen, Shengyu Zhang

Figure 1 for Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
Figure 2 for Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
Figure 3 for Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
Figure 4 for Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
* 1. Pengfei Chen and Weiwen Liu have equal contribution. 2. Correspondence to: Guangyong Chen  
  Access Paper or Ask Questions

Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks


May 15, 2019
Guangyong Chen, Pengfei Chen, Yujun Shi, Chang-Yu Hsieh, Benben Liao, Shengyu Zhang

Figure 1 for Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
Figure 2 for Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
Figure 3 for Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
Figure 4 for Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
* Correspondence to:Benben Liao  
  Access Paper or Ask Questions

Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels


May 13, 2019
Pengfei Chen, Benben Liao, Guangyong Chen, Shengyu Zhang

Figure 1 for Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Figure 2 for Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Figure 3 for Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Figure 4 for Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
* Correspondence to: Guangyong Chen  
  Access Paper or Ask Questions

Quantum algorithms for feedforward neural networks


Dec 07, 2018
Jonathan Allcock, Chang-Yu Hsieh, Iordanis Kerenidis, Shengyu Zhang

Figure 1 for Quantum algorithms for feedforward neural networks
Figure 2 for Quantum algorithms for feedforward neural networks
* 18 pages, 2 figures 
  Access Paper or Ask Questions

Online Clustering of Contextual Cascading Bandits


Nov 23, 2017
Shuai Li, Shengyu Zhang

Figure 1 for Online Clustering of Contextual Cascading Bandits

  Access Paper or Ask Questions