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

Add to Chrome

Add to Firefox

Picture for Shengyu Zhang

Shengyu Zhang

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

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