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 Dong Zhang

Dong Zhang

Learning Calibrated-Guidance for Object Detection in Aerial Images


Mar 21, 2021
Dong Liang, Zongqi Wei, Dong Zhang, Qixiang Geng, Liyan Zhang, Han Sun, Huiyu Zhou, Mingqiang Wei, Pan Gao

Figure 1 for Learning Calibrated-Guidance for Object Detection in Aerial Images
Figure 2 for Learning Calibrated-Guidance for Object Detection in Aerial Images
Figure 3 for Learning Calibrated-Guidance for Object Detection in Aerial Images
Figure 4 for Learning Calibrated-Guidance for Object Detection in Aerial Images

  Access Paper or Ask Questions

Deep Image Prior for Sparse-sampling Photoacoustic Microscopy


Oct 15, 2020
Tri Vu, Anthony DiSpirito III, Daiwei Li, Zixuan Zhang, Xiaoyi Zhu, Maomao Chen, Dong Zhang, Jianwen Luo, Yu Shrike Zhang, Roarke Horstmeyer, Junjie Yao

Figure 1 for Deep Image Prior for Sparse-sampling Photoacoustic Microscopy
Figure 2 for Deep Image Prior for Sparse-sampling Photoacoustic Microscopy
Figure 3 for Deep Image Prior for Sparse-sampling Photoacoustic Microscopy
Figure 4 for Deep Image Prior for Sparse-sampling Photoacoustic Microscopy

  Access Paper or Ask Questions

Causal Intervention for Weakly-Supervised Semantic Segmentation


Oct 07, 2020
Dong Zhang, Hanwang Zhang, Jinhui Tang, Xiansheng Hua, Qianru Sun

Figure 1 for Causal Intervention for Weakly-Supervised Semantic Segmentation
Figure 2 for Causal Intervention for Weakly-Supervised Semantic Segmentation
Figure 3 for Causal Intervention for Weakly-Supervised Semantic Segmentation
Figure 4 for Causal Intervention for Weakly-Supervised Semantic Segmentation
* Accepted as a NeurIPS 2020 oral paper 
  Access Paper or Ask Questions

Dual-SLAM: A framework for robust single camera navigation


Sep 23, 2020
Huajian Huang, Wen-Yan Lin, Siying Liu, Dong Zhang, Sai-Kit Yeung

Figure 1 for Dual-SLAM: A framework for robust single camera navigation
Figure 2 for Dual-SLAM: A framework for robust single camera navigation
Figure 3 for Dual-SLAM: A framework for robust single camera navigation
Figure 4 for Dual-SLAM: A framework for robust single camera navigation
* Accepted by International Conference on Intelligent Robots and Systems (IROS) 2020 
  Access Paper or Ask Questions

Mask Detection and Breath Monitoring from Speech: on Data Augmentation, Feature Representation and Modeling


Aug 14, 2020
Haiwei Wu, Lin Zhang, Lin Yang, Xuyang Wang, Junjie Wang, Dong Zhang, Ming Li

Figure 1 for Mask Detection and Breath Monitoring from Speech: on Data Augmentation, Feature Representation and Modeling
Figure 2 for Mask Detection and Breath Monitoring from Speech: on Data Augmentation, Feature Representation and Modeling
Figure 3 for Mask Detection and Breath Monitoring from Speech: on Data Augmentation, Feature Representation and Modeling
Figure 4 for Mask Detection and Breath Monitoring from Speech: on Data Augmentation, Feature Representation and Modeling

  Access Paper or Ask Questions

Feature Pyramid Transformer


Jul 18, 2020
Dong Zhang, Hanwang Zhang, Jinhui Tang, Meng Wang, Xiansheng Hua, Qianru Sun

Figure 1 for Feature Pyramid Transformer
Figure 2 for Feature Pyramid Transformer
Figure 3 for Feature Pyramid Transformer
Figure 4 for Feature Pyramid Transformer
* Published at the European Conference on Computer Vision, 2020 
  Access Paper or Ask Questions

Reconstructing undersampled photoacoustic microscopy images using deep learning


May 30, 2020
Anthony DiSpirito III, Daiwei Li, Tri Vu, Maomao Chen, Dong Zhang, Jianwen Luo, Roarke Horstmeyer, Junjie Yao

Figure 1 for Reconstructing undersampled photoacoustic microscopy images using deep learning
Figure 2 for Reconstructing undersampled photoacoustic microscopy images using deep learning
Figure 3 for Reconstructing undersampled photoacoustic microscopy images using deep learning
Figure 4 for Reconstructing undersampled photoacoustic microscopy images using deep learning
* 12 pages, 7 main figures, 3 supplemental figures (see last 2 pages) 
  Access Paper or Ask Questions

Direct Quantification for Coronary Artery Stenosis Using Multiview Learning


Aug 02, 2019
Dong Zhang, Guang Yang, Shu Zhao, Yanping Zhang, Heye Zhang, Shuo Li

Figure 1 for Direct Quantification for Coronary Artery Stenosis Using Multiview Learning
Figure 2 for Direct Quantification for Coronary Artery Stenosis Using Multiview Learning
Figure 3 for Direct Quantification for Coronary Artery Stenosis Using Multiview Learning
Figure 4 for Direct Quantification for Coronary Artery Stenosis Using Multiview Learning
* 9 pages, 4 figures 
  Access Paper or Ask Questions

Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds


Aug 02, 2018
Haroon Idrees, Muhmmad Tayyab, Kishan Athrey, Dong Zhang, Somaya Al-Maadeed, Nasir Rajpoot, Mubarak Shah

Figure 1 for Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
Figure 2 for Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
Figure 3 for Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
Figure 4 for Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
* ECCV 2018 
  Access Paper or Ask Questions

ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information


Dec 04, 2017
Rodney LaLonde, Dong Zhang, Mubarak Shah

Figure 1 for ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
Figure 2 for ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
Figure 3 for ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
Figure 4 for ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
* Main paper is 8 pages. Supplemental section contains a walk-through of our method (using a qualitative example) and qualitative results for WPAFB 2009 dataset 
  Access Paper or Ask Questions

Unsupervised Action Proposal Ranking through Proposal Recombination


Apr 03, 2017
Waqas Sultani, Dong Zhang, Mubarak Shah

Figure 1 for Unsupervised Action Proposal Ranking through Proposal Recombination
Figure 2 for Unsupervised Action Proposal Ranking through Proposal Recombination
Figure 3 for Unsupervised Action Proposal Ranking through Proposal Recombination
Figure 4 for Unsupervised Action Proposal Ranking through Proposal Recombination

  Access Paper or Ask Questions

Video Fill in the Blank with Merging LSTMs


Oct 13, 2016
Amir Mazaheri, Dong Zhang, Mubarak Shah

Figure 1 for Video Fill in the Blank with Merging LSTMs
Figure 2 for Video Fill in the Blank with Merging LSTMs
Figure 3 for Video Fill in the Blank with Merging LSTMs
* for Large Scale Movie Description and Understanding Challenge (LSMDC) 2016, "Movie fill-in-the-blank" Challenge, UCF_CRCV 
  Access Paper or Ask Questions

Local feature hierarchy for face recognition across pose and illumination


Jul 12, 2016
Xiaoyue Jiang, Dong Zhang, Xiaoyi Feng

Figure 1 for Local feature hierarchy for face recognition across pose and illumination
Figure 2 for Local feature hierarchy for face recognition across pose and illumination
Figure 3 for Local feature hierarchy for face recognition across pose and illumination

  Access Paper or Ask Questions

A Framework for Human Pose Estimation in Videos


Apr 26, 2016
Dong Zhang, Mubarak Shah

Figure 1 for A Framework for Human Pose Estimation in Videos
Figure 2 for A Framework for Human Pose Estimation in Videos
Figure 3 for A Framework for Human Pose Estimation in Videos
Figure 4 for A Framework for Human Pose Estimation in Videos

  Access Paper or Ask Questions

Robust Scene Text Recognition Using Sparse Coding based Features


Dec 29, 2015
Da-Han Wang, Hanzi Wang, Dong Zhang, Jonathan Li, David Zhang

Figure 1 for Robust Scene Text Recognition Using Sparse Coding based Features
Figure 2 for Robust Scene Text Recognition Using Sparse Coding based Features
Figure 3 for Robust Scene Text Recognition Using Sparse Coding based Features
Figure 4 for Robust Scene Text Recognition Using Sparse Coding based Features

  Access Paper or Ask Questions

Face Verification Using Boosted Cross-Image Features


Sep 28, 2013
Dong Zhang, Omar Oreifej, Mubarak Shah

Figure 1 for Face Verification Using Boosted Cross-Image Features
Figure 2 for Face Verification Using Boosted Cross-Image Features
Figure 3 for Face Verification Using Boosted Cross-Image Features
Figure 4 for Face Verification Using Boosted Cross-Image Features

  Access Paper or Ask Questions