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 Siyu Huang

Siyu Huang

Boosting Active Learning via Improving Test Performance


Dec 10, 2021
Tianyang Wang, Xingjian Li, Pengkun Yang, Guosheng Hu, Xiangrui Zeng, Siyu Huang, Cheng-Zhong Xu, Min Xu

Figure 1 for Boosting Active Learning via Improving Test Performance
Figure 2 for Boosting Active Learning via Improving Test Performance
Figure 3 for Boosting Active Learning via Improving Test Performance
Figure 4 for Boosting Active Learning via Improving Test Performance
* AAAI 2022 
 * 13 pages 
  Access Paper or Ask Questions

FINO: Flow-based Joint Image and Noise Model


Nov 11, 2021
Lanqing Guo, Siyu Huang, Haosen Liu, Bihan Wen

Figure 1 for FINO: Flow-based Joint Image and Noise Model
Figure 2 for FINO: Flow-based Joint Image and Noise Model
Figure 3 for FINO: Flow-based Joint Image and Noise Model
Figure 4 for FINO: Flow-based Joint Image and Noise Model

  Access Paper or Ask Questions

AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators


Sep 21, 2021
Yihang Yin, Qingzhong Wang, Siyu Huang, Haoyi Xiong, Xiang Zhang

Figure 1 for AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Figure 2 for AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Figure 3 for AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Figure 4 for AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators

  Access Paper or Ask Questions

Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study


Sep 02, 2021
Xuhong Li, Haoyi Xiong, Siyu Huang, Shilei Ji, Dejing Dou

Figure 1 for Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study
Figure 2 for Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study
Figure 3 for Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study
Figure 4 for Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study

  Access Paper or Ask Questions

Semi-Supervised Active Learning with Temporal Output Discrepancy


Jul 29, 2021
Siyu Huang, Tianyang Wang, Haoyi Xiong, Jun Huan, Dejing Dou

Figure 1 for Semi-Supervised Active Learning with Temporal Output Discrepancy
Figure 2 for Semi-Supervised Active Learning with Temporal Output Discrepancy
Figure 3 for Semi-Supervised Active Learning with Temporal Output Discrepancy
Figure 4 for Semi-Supervised Active Learning with Temporal Output Discrepancy
* ICCV 2021. Code is available at https://github.com/siyuhuang/TOD 
  Access Paper or Ask Questions

ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement


Jul 13, 2021
Rongkai Zhang, Lanqing Guo, Siyu Huang, Bihan Wen

Figure 1 for ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement
Figure 2 for ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement
Figure 3 for ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement
Figure 4 for ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement
* Accepted by ACM MM 2021 
  Access Paper or Ask Questions

Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples


Jun 20, 2021
Xuanyu Wu, Xuhong Li, Haoyi Xiong, Xiao Zhang, Siyu Huang, Dejing Dou

Figure 1 for Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Figure 2 for Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Figure 3 for Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Figure 4 for Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples

  Access Paper or Ask Questions

BM-NAS: Bilevel Multimodal Neural Architecture Search


Apr 19, 2021
Yihang Yin, Siyu Huang, Xiang Zhang, Dejing Dou

Figure 1 for BM-NAS: Bilevel Multimodal Neural Architecture Search
Figure 2 for BM-NAS: Bilevel Multimodal Neural Architecture Search
Figure 3 for BM-NAS: Bilevel Multimodal Neural Architecture Search
Figure 4 for BM-NAS: Bilevel Multimodal Neural Architecture Search

  Access Paper or Ask Questions

ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows


Apr 09, 2021
Jie An, Siyu Huang, Yibing Song, Dejing Dou, Wei Liu, Jiebo Luo

Figure 1 for ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
Figure 2 for ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
Figure 3 for ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
Figure 4 for ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
* CVPR 2021 Accepted 
  Access Paper or Ask Questions

Contour Primitive of Interest Extraction Network Based on One-shot Learning for Object-Agnostic Vision Measurement


Oct 07, 2020
Fangbo Qin, Jie Qin, Siyu Huang, De Xu

Figure 1 for Contour Primitive of Interest Extraction Network Based on One-shot Learning for Object-Agnostic Vision Measurement
Figure 2 for Contour Primitive of Interest Extraction Network Based on One-shot Learning for Object-Agnostic Vision Measurement
Figure 3 for Contour Primitive of Interest Extraction Network Based on One-shot Learning for Object-Agnostic Vision Measurement
Figure 4 for Contour Primitive of Interest Extraction Network Based on One-shot Learning for Object-Agnostic Vision Measurement
* Submitted to IEEE Robotics and Automation Letters 
  Access Paper or Ask Questions

TP-LSD: Tri-Points Based Line Segment Detector


Sep 11, 2020
Siyu Huang, Fangbo Qin, Pengfei Xiong, Ning Ding, Yijia He, Xiao Liu

Figure 1 for TP-LSD: Tri-Points Based Line Segment Detector
Figure 2 for TP-LSD: Tri-Points Based Line Segment Detector
Figure 3 for TP-LSD: Tri-Points Based Line Segment Detector
Figure 4 for TP-LSD: Tri-Points Based Line Segment Detector
* Europeon Conference on Computer Vision (2020) 
 * Accepted by ECCV 2020 
  Access Paper or Ask Questions

SBAT: Video Captioning with Sparse Boundary-Aware Transformer


Jul 23, 2020
Tao Jin, Siyu Huang, Ming Chen, Yingming Li, Zhongfei Zhang

Figure 1 for SBAT: Video Captioning with Sparse Boundary-Aware Transformer
Figure 2 for SBAT: Video Captioning with Sparse Boundary-Aware Transformer
Figure 3 for SBAT: Video Captioning with Sparse Boundary-Aware Transformer
Figure 4 for SBAT: Video Captioning with Sparse Boundary-Aware Transformer
* Appearing at IJCAI 2020 
  Access Paper or Ask Questions

Generating Person Images with Appearance-aware Pose Stylizer


Jul 17, 2020
Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng, Qingzhong Wang, Xingran Zhou, Bihan Wen, Jun Huan, Dejing Dou

Figure 1 for Generating Person Images with Appearance-aware Pose Stylizer
Figure 2 for Generating Person Images with Appearance-aware Pose Stylizer
Figure 3 for Generating Person Images with Appearance-aware Pose Stylizer
Figure 4 for Generating Person Images with Appearance-aware Pose Stylizer
* Appearing at IJCAI 2020. The code is available at https://github.com/siyuhuang/PoseStylizer 
  Access Paper or Ask Questions

Parameter-Free Style Projection for Arbitrary Style Transfer


Mar 17, 2020
Siyu Huang, Haoyi Xiong, Tianyang Wang, Qingzhong Wang, Zeyu Chen, Jun Huan, Dejing Dou

Figure 1 for Parameter-Free Style Projection for Arbitrary Style Transfer
Figure 2 for Parameter-Free Style Projection for Arbitrary Style Transfer
Figure 3 for Parameter-Free Style Projection for Arbitrary Style Transfer
Figure 4 for Parameter-Free Style Projection for Arbitrary Style Transfer
* 9 pages, 12 figures 
  Access Paper or Ask Questions

Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning


Nov 01, 2019
Tao Jin, Siyu Huang, Yingming Li, Zhongfei Zhang

Figure 1 for Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
Figure 2 for Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
Figure 3 for Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
Figure 4 for Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
* Accepted as a long paper at EMNLP 2019 
  Access Paper or Ask Questions

Text Guided Person Image Synthesis


Apr 10, 2019
Xingran Zhou, Siyu Huang, Bin Li, Yingming Li, Jiachen Li, Zhongfei Zhang

Figure 1 for Text Guided Person Image Synthesis
Figure 2 for Text Guided Person Image Synthesis
Figure 3 for Text Guided Person Image Synthesis
Figure 4 for Text Guided Person Image Synthesis
* To appear at CVPR 2019 
  Access Paper or Ask Questions

Perceiving Physical Equation by Observing Visual Scenarios


Nov 29, 2018
Siyu Huang, Zhi-Qi Cheng, Xi Li, Xiao Wu, Zhongfei Zhang, Alexander Hauptmann

Figure 1 for Perceiving Physical Equation by Observing Visual Scenarios
Figure 2 for Perceiving Physical Equation by Observing Visual Scenarios
Figure 3 for Perceiving Physical Equation by Observing Visual Scenarios
Figure 4 for Perceiving Physical Equation by Observing Visual Scenarios
* NIPS 2018 Workshop on Modeling the Physical World 
  Access Paper or Ask Questions

Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance


Aug 22, 2018
Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann

Figure 1 for Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance
Figure 2 for Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance
Figure 3 for Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance
Figure 4 for Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance
* The code is available at http://github.com/siyuhuang/crowdcount-stackpool 
  Access Paper or Ask Questions

GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning


Aug 01, 2018
Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann

Figure 1 for GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
Figure 2 for GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
Figure 3 for GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
Figure 4 for GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
* ACM MM 2018 (Oral) 
  Access Paper or Ask Questions

Deep Learning Driven Visual Path Prediction from a Single Image


Jan 27, 2016
Siyu Huang, Xi Li, Zhongfei Zhang, Zhouzhou He, Fei Wu, Wei Liu, Jinhui Tang, Yueting Zhuang

Figure 1 for Deep Learning Driven Visual Path Prediction from a Single Image
Figure 2 for Deep Learning Driven Visual Path Prediction from a Single Image
Figure 3 for Deep Learning Driven Visual Path Prediction from a Single Image
Figure 4 for Deep Learning Driven Visual Path Prediction from a Single Image
* IEEE Transactions on Image Processing, vol. 25, no. 12, pp. 5892-5904, Dec. 2016 
  Access Paper or Ask Questions