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 Hong Zhang

Hong Zhang

Improving Feature Extraction from Histopathological Images Through A Fine-tuning ImageNet Model


Jan 03, 2022
Xingyu Li, Min Cen, Jinfeng Xu, Hong Zhang, Xu Steven Xu


  Access Paper or Ask Questions

Online Mutual Adaptation of Deep Depth Prediction and Visual SLAM


Nov 27, 2021
Shing Yan Loo, Moein Shakeri, Sai Hong Tang, Syamsiah Mashohor, Hong Zhang

Figure 1 for Online Mutual Adaptation of Deep Depth Prediction and Visual SLAM
Figure 2 for Online Mutual Adaptation of Deep Depth Prediction and Visual SLAM
Figure 3 for Online Mutual Adaptation of Deep Depth Prediction and Visual SLAM
Figure 4 for Online Mutual Adaptation of Deep Depth Prediction and Visual SLAM
* 10 pages, 7 figures 
  Access Paper or Ask Questions

Online Adaptation of Monocular Depth Prediction with Visual SLAM


Nov 07, 2021
Shing Yan Loo, Moein Shakeri, Sai Hong Tang, Syamsiah Mashohor, Hong Zhang

Figure 1 for Online Adaptation of Monocular Depth Prediction with Visual SLAM
Figure 2 for Online Adaptation of Monocular Depth Prediction with Visual SLAM
Figure 3 for Online Adaptation of Monocular Depth Prediction with Visual SLAM
Figure 4 for Online Adaptation of Monocular Depth Prediction with Visual SLAM
* 9 pages, 8 figures 
  Access Paper or Ask Questions

Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction


Nov 05, 2021
Sara Elkerdawy, Mostafa Elhoushi, Hong Zhang, Nilanjan Ray

Figure 1 for Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction
Figure 2 for Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction
Figure 3 for Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction
Figure 4 for Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction

  Access Paper or Ask Questions

A Retrospective Analysis using Deep-Learning Models for Prediction of Survival Outcome and Benefit of Adjuvant Chemotherapy in Stage II/III Colorectal Cancer


Nov 05, 2021
Xingyu Li, Jitendra Jonnagaddala, Shuhua Yang, Hong Zhang, Xu Steven Xu

Figure 1 for A Retrospective Analysis using Deep-Learning Models for Prediction of Survival Outcome and Benefit of Adjuvant Chemotherapy in Stage II/III Colorectal Cancer
Figure 2 for A Retrospective Analysis using Deep-Learning Models for Prediction of Survival Outcome and Benefit of Adjuvant Chemotherapy in Stage II/III Colorectal Cancer

  Access Paper or Ask Questions

Relationship Oriented Affordance Learning through Manipulation Graph Construction


Nov 01, 2021
Chao Tang, Jingwen Yu, Weinan Chen, Hong Zhang

Figure 1 for Relationship Oriented Affordance Learning through Manipulation Graph Construction
Figure 2 for Relationship Oriented Affordance Learning through Manipulation Graph Construction
Figure 3 for Relationship Oriented Affordance Learning through Manipulation Graph Construction
Figure 4 for Relationship Oriented Affordance Learning through Manipulation Graph Construction

  Access Paper or Ask Questions

Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network


Oct 23, 2021
Tianqi Shen, Hong Zhang, Ding Yuan, Jiaping Xiao, Yifan Yang

Figure 1 for Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network
Figure 2 for Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network
Figure 3 for Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network
Figure 4 for Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network

  Access Paper or Ask Questions

Rethinking Training from Scratch for Object Detection


Jun 06, 2021
Yang Li, Hong Zhang, Yu Zhang

Figure 1 for Rethinking Training from Scratch for Object Detection
Figure 2 for Rethinking Training from Scratch for Object Detection
Figure 3 for Rethinking Training from Scratch for Object Detection
Figure 4 for Rethinking Training from Scratch for Object Detection
* tech reports 
  Access Paper or Ask Questions

Deep Snapshot HDR Reconstruction Based on the Polarization Camera


May 12, 2021
Juiwen Ting, Xuesong Wu, Kangkang Hu, Hong Zhang

Figure 1 for Deep Snapshot HDR Reconstruction Based on the Polarization Camera
Figure 2 for Deep Snapshot HDR Reconstruction Based on the Polarization Camera
Figure 3 for Deep Snapshot HDR Reconstruction Based on the Polarization Camera
Figure 4 for Deep Snapshot HDR Reconstruction Based on the Polarization Camera
* 5 pages, 4 figures 
  Access Paper or Ask Questions

GNAS: A Generalized Neural Network Architecture Search Framework


Apr 08, 2021
Dige Ai, Hong Zhang

Figure 1 for GNAS: A Generalized Neural Network Architecture Search Framework
Figure 2 for GNAS: A Generalized Neural Network Architecture Search Framework
Figure 3 for GNAS: A Generalized Neural Network Architecture Search Framework
Figure 4 for GNAS: A Generalized Neural Network Architecture Search Framework
* 12 pages,15 figures 
  Access Paper or Ask Questions

A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches


Feb 21, 2021
Chen Li, Xintong Li, Md Rahaman, Xiaoyan Li, Hongzan Sun, Hong Zhang, Yong Zhang, Xiaoqi Li, Jian Wu, Yudong Yao, Marcin Grzegorzek

Figure 1 for A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches
Figure 2 for A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches
Figure 3 for A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches
Figure 4 for A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches

  Access Paper or Ask Questions

Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior


Feb 10, 2021
Moein Shakeri, Shing Yan Loo, Hong Zhang

Figure 1 for Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior
Figure 2 for Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior
Figure 3 for Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior
Figure 4 for Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior
* 9 pages, 9 figure 
  Access Paper or Ask Questions

Full Matching on Low Resolution for Disparity Estimation


Dec 10, 2020
Hong Zhang, Shenglun Chen, Zhihui Wang, Haojie Li, Wanli Ouyang

Figure 1 for Full Matching on Low Resolution for Disparity Estimation
Figure 2 for Full Matching on Low Resolution for Disparity Estimation
Figure 3 for Full Matching on Low Resolution for Disparity Estimation
Figure 4 for Full Matching on Low Resolution for Disparity Estimation
* 9pages,5 figures 
  Access Paper or Ask Questions

Direct Depth Learning Network for Stereo Matching


Dec 10, 2020
Hong Zhang, Haojie Li, Shenglun Chen, Tiantian Yan, Zhihui Wang, Guo Lu, Wanli Ouyang

Figure 1 for Direct Depth Learning Network for Stereo Matching
Figure 2 for Direct Depth Learning Network for Stereo Matching
Figure 3 for Direct Depth Learning Network for Stereo Matching
Figure 4 for Direct Depth Learning Network for Stereo Matching
* 10 pages,4 figures 
  Access Paper or Ask Questions

Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving


Dec 01, 2020
Mu Cai, Hong Zhang, Huijuan Huang, Qichuan Geng, Gao Huang

Figure 1 for Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving
Figure 2 for Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving
Figure 3 for Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving
Figure 4 for Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving
* 13 pages 
  Access Paper or Ask Questions

Object-aware Feature Aggregation for Video Object Detection


Oct 23, 2020
Qichuan Geng, Hong Zhang, Na Jiang, Xiaojuan Qi, Liangjun Zhang, Zhong Zhou

Figure 1 for Object-aware Feature Aggregation for Video Object Detection
Figure 2 for Object-aware Feature Aggregation for Video Object Detection
Figure 3 for Object-aware Feature Aggregation for Video Object Detection
Figure 4 for Object-aware Feature Aggregation for Video Object Detection

  Access Paper or Ask Questions

PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features


Oct 11, 2020
Qiang Fu, Jialong Wang, Hongshan Yu, Islam Ali, Feng Guo, Yijia He, Hong Zhang

Figure 1 for PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features
Figure 2 for PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features
Figure 3 for PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features
Figure 4 for PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features
* Visual-Inertial SLAM, LSD, Lines, SLAM, VINS-Mono 
  Access Paper or Ask Questions

A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis


Sep 29, 2020
Chen Li, Yixin Li, Changhao Sun, Hao Chen, Hong Zhang

Figure 1 for A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis
Figure 2 for A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis
Figure 3 for A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis
Figure 4 for A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis

  Access Paper or Ask Questions

PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line


Sep 16, 2020
Qiang Fu, Jialong Wang, Hongshan Yu, Islam Ali, Feng Guo, Hong Zhang

Figure 1 for PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line
Figure 2 for PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line
Figure 3 for PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line
Figure 4 for PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line
* Visual-Inertial SLAM, LSD, Lines, SLAM, VINS-Mono 
  Access Paper or Ask Questions

FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching


Aug 22, 2020
Qiang Fu, Hongshan Yu, Xiaolong Wang, Zhengeng Yang, Hong Zhang, Ajmal Mian

Figure 1 for FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching
Figure 2 for FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching
Figure 3 for FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching
Figure 4 for FastORB-SLAM: a Fast ORB-SLAM Method with Coarse-to-Fine Descriptor Independent Keypoint Matching
* Keypoint Matching, Optical Flow, Motion Model, ORB SLAM, Pose, Estimation, Visual SLAM 
  Access Paper or Ask Questions

To filter prune, or to layer prune, that is the question


Jul 11, 2020
Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh, Hong Zhang, Nilanjan Ray

Figure 1 for To filter prune, or to layer prune, that is the question
Figure 2 for To filter prune, or to layer prune, that is the question
Figure 3 for To filter prune, or to layer prune, that is the question
Figure 4 for To filter prune, or to layer prune, that is the question

  Access Paper or Ask Questions

DeepRelativeFusion: Dense Monocular SLAM using Single-Image Relative Depth Prediction


Jun 07, 2020
Shing Yan Loo, Syamsiah Mashohor, Sai Hong Tang, Hong Zhang

Figure 1 for DeepRelativeFusion: Dense Monocular SLAM using Single-Image Relative Depth Prediction
Figure 2 for DeepRelativeFusion: Dense Monocular SLAM using Single-Image Relative Depth Prediction
Figure 3 for DeepRelativeFusion: Dense Monocular SLAM using Single-Image Relative Depth Prediction
Figure 4 for DeepRelativeFusion: Dense Monocular SLAM using Single-Image Relative Depth Prediction

  Access Paper or Ask Questions

Gated Path Selection Network for Semantic Segmentation


Jan 19, 2020
Qichuan Geng, Hong Zhang, Xiaojuan Qi, Ruigang Yang, Zhong Zhou, Gao Huang

Figure 1 for Gated Path Selection Network for Semantic Segmentation
Figure 2 for Gated Path Selection Network for Semantic Segmentation
Figure 3 for Gated Path Selection Network for Semantic Segmentation
Figure 4 for Gated Path Selection Network for Semantic Segmentation

  Access Paper or Ask Questions

Large-scale Multi-modal Person Identification in Real Unconstrained Environments


Dec 17, 2019
Jiajie Ye, Yisheng Guan, Junfa Liu, Xinghong Huang, Hong Zhang

Figure 1 for Large-scale Multi-modal Person Identification in Real Unconstrained Environments
Figure 2 for Large-scale Multi-modal Person Identification in Real Unconstrained Environments
Figure 3 for Large-scale Multi-modal Person Identification in Real Unconstrained Environments
Figure 4 for Large-scale Multi-modal Person Identification in Real Unconstrained Environments
* 6 pages, IEEE International Conference on Robotics and Biomimetics 2019 
  Access Paper or Ask Questions

Implicit Semantic Data Augmentation for Deep Networks


Sep 27, 2019
Yulin Wang, Xuran Pan, Shiji Song, Hong Zhang, Cheng Wu, Gao Huang

Figure 1 for Implicit Semantic Data Augmentation for Deep Networks
Figure 2 for Implicit Semantic Data Augmentation for Deep Networks
Figure 3 for Implicit Semantic Data Augmentation for Deep Networks
Figure 4 for Implicit Semantic Data Augmentation for Deep Networks
* Accepted by NeurIPS 2019 
  Access Paper or Ask Questions

Improved Techniques for Training Adaptive Deep Networks


Aug 17, 2019
Hao Li, Hong Zhang, Xiaojuan Qi, Ruigang Yang, Gao Huang

Figure 1 for Improved Techniques for Training Adaptive Deep Networks
Figure 2 for Improved Techniques for Training Adaptive Deep Networks
Figure 3 for Improved Techniques for Training Adaptive Deep Networks
Figure 4 for Improved Techniques for Training Adaptive Deep Networks

  Access Paper or Ask Questions

Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network


May 18, 2019
Ali Jahani Amiri, Shing Yan Loo, Hong Zhang

Figure 1 for Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network
Figure 2 for Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network
Figure 3 for Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network
Figure 4 for Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network
* Submitted to IROS2019 
  Access Paper or Ask Questions

Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruning


May 13, 2019
Sara Elkerdawy, Hong Zhang, Nilanjan Ray

Figure 1 for Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruning
Figure 2 for Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruning
Figure 3 for Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruning
Figure 4 for Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruning

  Access Paper or Ask Questions