Welcome

Who I am

My name is Qiaosong Wang and I'm currently a Senior Applied Scientist at Amazon AI. Previously I was a Senior Research Scientist at eBay Core AI.

Next

Research Interests

My research interests include Computer Vision, Machine Learning, AR/VR and Robotics.

Next

Projects

Click for details

Publications

Email me for source code (mostly available)

• Stereo Vision based Depth of Field Rendering on a Mobile Device [AR/VR]
  IS&T/SPIE Electronic Imaging (EI) 2014 [Oral Presentation][Best Student Paper]
  pdf cite
							@inproceedings{wang9023stereo,
							  title={Stereo Vision based Depth of Field Rendering on a Mobile Device},
							  author={Wang, Qiaosong and Yu, Zhan and Rasmussen, Christopher and Yu, Jingyi},
							  booktitle={Proc. of SPIE Vol},
							  volume={9023},
							  pages={902307--1}
							}
							
best student paper award

• Stereo Vision based Depth of Field Rendering on a Mobile Device [AR/VR]
  SPIE Journal of Electronic Imaging (JEI) 2014
  pdf cite
							@article{wang2014stereo,
							  title={Stereo vision--based depth of field rendering on a mobile device},
							  author={Wang, Qiaosong and Yu, Zhan and Rasmussen, Christopher and Yu, Jingyi},
							  journal={Journal of Electronic Imaging},
							  volume={23},
							  number={2},
							  pages={023009--023009},
							  year={2014},
							  publisher={International Society for Optics and Photonics}
							}
						  

• Perception and Control Strategies for Driving Utility Vehicles With a Humanoid Robot [AI]
  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2014
  pdf cite
							@inproceedings{rasmussen2014perception,
							  title={Perception and control strategies for driving utility vehicles with a humanoid robot},
							  author={Rasmussen, Christopher and Sohn, Kiwon and Wang, Qiaosong and Oh, Paul},
							  booktitle={Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International Conference on},
							  pages={973--980},
							  year={2014},
							  organization={IEEE}
							}
						

• Automatic Layer Separation using Light Field Imaging [AR/VR]
  arxiv 2015
  pdf cite
							@article{wang2015automatic,
							  title={Automatic Layer Separation using Light Field Imaging},
							  author={Wang, Qiaosong and Lin, Haiting and Ma, Yi and Kang, Sing Bing and Yu, Jingyi},
							  journal={arXiv preprint arXiv:1506.04721},
							  year={2015}
							}
						

• 3D Bridge Inspection and Evaluation Using UAV and Image Reconstruction [AI]
  11th Annual Inter-University Symposium on Infra Management (AISIM) 2015 [Oral Presentation]
  pdf cite

• Im2Fit: Fast 3D Model Fitting and Anthropometrics using Single Consumer
   Depth Camera and Synthetic Data [AR/VR]

  IS&T/SPIE Electronic Imaging (EI) 2016 [Oral Presentation]
  pdf cite
							@article{wang2016im2fit,
							  title={Im2fit: Fast 3d model fitting and anthropometrics using single consumer depth camera and synthetic data},
							  author={Wang, Qiaosong and Jagadeesh, Vignesh and Ressler, Bryan and Piramuthu, Robinson},
							  journal={Electronic Imaging},
							  volume={2016},
							  number={21},
							  pages={1--7},
							  year={2016},
							  publisher={Society for Imaging Science and Technology}
							}

						

• GraB: Visual Saliency via Novel Graph Model and Background Priors [AI]
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016
  pdf cite
							@inproceedings{wang2016grab,
							  title={GraB: Visual Saliency via Novel Graph Model and Background Priors},
							  author={Wang, Qiaosong and Zheng, Wen and Piramuthu, Robinson},
							  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
							  pages={535--543},
							  year={2016}
							}
						
saliency maps

• Advanced Multi-modal Integrated 3-D Reconstruction System [AI]
  Esri Imaging & Mapping Forum 2016
  pdf cite

• Fast, Deep Detection and Tracking of Birds and Nests [AI]
  International Symposium on Visual Computing (ISVC) 2016 [Oral Presentation]
  pdf cite
							@inproceedings{wang2016fast,
							  title={Fast, Deep Detection and Tracking of Birds and Nests},
							  author={Wang, Qiaosong and Rasmussen, Christopher and Song, Chunbo},
							  booktitle={International Symposium on Visual Computing},
							  pages={146--155},
							  year={2016},
							  organization={Springer}
							}
							
dataset

• Object Recognition in Aerial Images Using Convolutional Neural Networks [AI]
  Journal of Imaging 2017
  pdf cite
						    @Article{radovic2017aerial,
								author = {Radovic, Matija and Adarkwa, Offei and Wang, Qiaosong},
								title = {Object Recognition in Aerial Images Using Convolutional Neural Networks},
								journal = {Journal of Imaging},
								volume = {3},
								year = {2017},
								number = {2},
								article number = {21},
								url = {http://www.mdpi.com/2313-433X/3/2/21},
								issn = {2313-433X},
								abstract = {There are numerous applications of unmanned aerial vehicles (UAVs) in the management of civil infrastructure assets. A few examples include routine bridge inspections, disaster management, power line surveillance and traffic surveying. As UAV applications become widespread, increased levels of autonomy and independent decision-making are necessary to improve the safety, efficiency, and accuracy of the devices. This paper details the procedure and parameters used for the training of convolutional neural networks (CNNs) on a set of aerial images for efficient and automated object recognition. Potential application areas in the transportation field are also highlighted. The accuracy and reliability of CNNs depend on the network’s training and the selection of operational parameters. This paper details the CNN training procedure and parameter selection. The object recognition results show that by selecting a proper set of parameters, a CNN can detect and classify objects with a high level of accuracy (97.5%) and computational efficiency. Furthermore, using a convolutional neural network implemented in the “YOLO” (“You Only Look Once”) platform, objects can be tracked, detected (“seen”), and classified (“comprehended”) from video feeds supplied by UAVs in real-time.},
								doi = {10.3390/jimaging3020021}
							}

						

• Visual Search at eBay [AI]
  ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD) 2017
  pdf cite
							@inproceedings{yang2017search,
							 author = {Yang, Fan and Kale, Ajinkya and Bubnov, Yury and Stein, Leon and Wang, Qiaosong and Kiapour, Hadi and Piramuthu, Robinson},
							 title = {Visual Search at eBay},
							 booktitle = {Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
							 series = {KDD '17},
							 year = {2017},
							 isbn = {978-1-4503-4887-4},
							 location = {Halifax, NS, Canada},
							 pages = {2101--2110},
							 numpages = {10},
							 url = {http://doi.acm.org/10.1145/3097983.3098162},
							 doi = {10.1145/3097983.3098162},
							 acmid = {3098162},
							 publisher = {ACM},
							 address = {New York, NY, USA},
							 keywords = {deep learning, e-commerce, search engine, semantics, visual search},
							}
						

• Towards the Success Rate of One: Real-time Unconstrained Salient Object Detection [AI]
  IEEE Winter Conference on Applications of Computer Vision (WACV) 2018 [Oral Presentation]
  pdf cite
							@article{najibi2017towards,
							  title={Towards the Success Rate of One: Real-time Unconstrained Salient Object Detection},
							  author={Najibi, Mahyar and Yang, Fan and Wang, Qiaosong and Piramuthu, Robinson},
							  booktitle={2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
							  year={2017}
							}

						

• Dual Learning for Cinematic Rendering of 3-D Avatars from Single Monocular Images [AR/VR]
  arxiv 2018
  pdf cite

• Towards Real-time 3D Reconstruction using Consumer UAVs [AI]
  The 28th Workshop on Information Technologies and Systems (WITS) 2018 [Oral Presentation]
  pdf cite
							@article{wang2018uav,
							  title={Towards Real-time 3D Reconstruction using Consumer UAVs},
							  author={Wang, Qiaosong},
							  journal={The 28th Workshop on Information Technologies and Systems},
							  year={2018}
							}
						

• Towards Fine-Grained Recognition: Joint Learning for Object Detection
   and Fine-Grained Classification [AI]

  International Symposium on Visual Computing (ISVC) 2019 [Oral Presentation]
  pdf cite
							@inproceedings{wang2019fine,
							  title={Towards Fine-Grained Recognition: Joint Learning for Object Detection and Fine-Grained Classification},
							  author={Wang, Qiaosong and Rasmussen, Christopher},
							  booktitle={International Symposium on Visual Computing},
							  pages={332--344},
							  year={2019},
							  organization={Springer}
							}
							
dataset

• 3D Visual Object Detection from Monocular Images [AI]
  International Symposium on Visual Computing (ISVC) 2019 [Oral Presentation]
  pdf cite
							@inproceedings{wang20193d,
							  title={3D Visual Object Detection from Monocular Images},
							  author={Wang, Qiaosong and Rasmussen, Christopher},
							  booktitle={International Symposium on Visual Computing},
							  pages={168--180},
							  year={2019},
							  organization={Springer}
							}
						

• Adversarial Learning for Fine-grained Image Search [AI]
  IEEE International Conference on Multimedia and Expo (ICME) 2019 [Oral Presentation]
  pdf cite
							@inproceedings{lin2019adversarial,
							  author={Lin, Kevin and Yang, Fan and Wang, Qiaosong and Piramuthu, Robinson},
							  booktitle={2019 IEEE International Conference on Multimedia and Expo (ICME)},
							  pages={490--495},
							  year={2019},
							  organization={IEEE}
							}
						

• Mobile Head Tracking for eCommerce and Beyond [AI]
  IS&T/SPIE Electronic Imaging (EI) 2020 [Oral Presentation]
  pdf cite
							@article{cicek2020mobile,
							  title={Mobile Head Tracking for eCommerce and Beyond},
							  author={Cicek, Muratcan and Xie, Jinrong and Wang, Qiaosong and Piramuthu, Robinson},
							  journal={Proc. of SPIE Vol},
							  year={2020}
							}
							

• Weakly-Supervised Semantic Segmentation via Sub-category Exploration [AI]
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020
  pdf cite
							@inproceedings{chang2020wsss,
							  title={Weakly-Supervised Semantic Segmentation via Sub-Category Exploration},
							  author={Chang, Yu-Ting and Wang, Qiaosong and Hung, Wei-Chih and Piramuthu, Robinson and Tsai, Yi-Hsuan and Yang, Ming-Hsuan},
							  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
							  pages={8991--9000},
							  year={2020}
							}
							

• Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization [AI]
  The British Machine Vision Conference (BMVC) 2020
  pdf cite
							@article{chang2020mixup,
							  title={Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization},
							  author={Chang, Yu-Ting and Wang, Qiaosong and Hung, Wei-Chih and Piramuthu, Robinson and Tsai, Yi-Hsuan and Yang, Ming-Hsuan},
							  journal={arXiv preprint arXiv:2008.01201},
							  year={2020}
							}
							

• Towards Real-time 3D Terrain Reconstruction from Aerial Imagery [AI]
  Geographies 2023
  pdf cite
							@article{wang2023aerial,
								doi = {10.20944/preprints202308.1425.v1},
								url = {https://doi.org/10.20944/preprints202308.1425.v1},
								year = 2023,
								month = {August},
								publisher = {Preprints},
								author = {Qiaosong Wang},
								title = {Towards Real-time 3D Terrain Reconstruction from Aerial Imagery},
								journal = {Preprints}
							}
							

Patents

• Multi-functional Intelligent Surveillance and Control System (MISCS) CHINA Patent Issued CN 200920032192
• Wiimote-Based Infrared VR Teaching Assistant System CHINA Patent Issued CN 201020185719
• A Novel Cruise Robot CHINA Patent Issued CN 201020185799
• Fast 3D Model Fitting and Anthropometrics Using Synthetic Data US Patent Issued US 20160110595;
   CHINA Patent Issued CN 201580055935; EU Patent Issued EP 3207525
• Automated Saliency Map Estimation US Patent Issued US 20170372162
• Category Prediction From Semantic Image Clustering US Patent Issued US 20180107682
• Intelligent Online Personal Assistant With Multi-turn Dialog Based On Visual Search US Patent Issued US 20180108066
• Determining An Item That Has Confirmed Characteristics US Patent Issued US 20180053069
• Image Analysis and Prediction Based Visual Search US Patent Issued US 20180107902
• Intelligent Online Personal Assistant With Offline Visual Search Database US Patent Issued US 20180107685
• Anchored Search US Patent Issued US 20180157681
• Commercial Integration of 3D Models US Patent Issued US 20200234489
• Integration of 3D Models US Patent Issued US 20180261001
• Saliency-based Object Counting and Localization US Patent Issued US 20180285682
• Camera Platform and Object Inventory Control US Patent Issued US 20190080171
• Camera Platform Incorporating Schedule and Stature US Patent Issued US 20190080172
• Reconstruction of 3D Model with Immersive Experience US Patent Issued US 20190378341
• Adversarial Learning for Fine-grained Image Search US Patent Issued US 20220245406
• Systems and Methods for Automatically Reconfiguring a Building Structure US Patent Issued US 20220025638
• Systems and Methods for Deploying a Robotic Security Escort US Patent Issued US 20210080926
• Auto Posting System US Patent Issued US 20210272171
• Image Cleanup on a Mobile Device US Patent Issued US 20220138914
• Systems and Methods for Deploying a Robotic Security Escort to Enhance Enterprise Security US Patent Issued US 20210080926
• Systems and Methods for Automatically Reconfiguring a Building Structure US Patent Issued US 11167925B2
• Auto Posting System US Patent Issued US 20210272171

Awards & Achievements

• National Third Prize, 11th Chinese National Challenge Cup Competition (Team Leader)
  China Association for Science and Technology (CAST), Ministry of Industry and Information Technology(MIIT), 2009 Certificate
• Honorable Mention Prize, Mathematical Contest in Modeling (MCM) (Team Leader)
  Consortium for Mathematics and its Applications (COMAP), U.S. National Security Agency (NSA), 2010 Certificate
• Excellence Award, Microsft Student Challenge
  Microsoft Research Asia (MSRA), 2010 Certificate
• Best Student Paper Award, IS&T/SPIE International Conference on Digital Photography
  The International Society for Optics and Photonics (SPIE), Society for Imaging Science and Technology (IS&T), 2014 Certificate
• 8th Place, DARPA Robotics Challenge Finals (Team Member w/ UNLV)
  Defense Advanced Research Projects Agency (DARPA), 2015
• Honorable Mention Prize, eBay Hackweek
  eBay Inc.,2017 Certificate

• Fire-fighting Robot Featured On the New York Times
  The New York Times, 2010 Article
• Finalist at Transportation Research Board (TRB)'s National Startup Challenge
  The National Academies of Sciences, Engineering, and Medicine, 2016 Website
• Saliency Algorithm and Code Are Deployed to Production Microsoft XBOX
  Microsoft Corporation, 2011 - Present Legal Notice
• Mobile 3D Reconstruction Featured on Google Cloud Next '17 Keynote
  Google LLC, 2017 Video View 3D Model
• Developed Deep Neural Network Models for Marktplaats Visual Category Recognition
  eBay Inc, 2017 Go to Marktplaats
• Developed Deep Neural Network Models for eBay Shopbot Visual Search
  eBay Inc, 2017
• Mobile Head Tracking Project Selected as Finalist in Fast Company's World Changing Ideas 2019
  Fast Company Magazine, 2019 List
• Developed and Implemented the Image Cleanup Algorithm For the eBay Core App
  VentureBeat, 2020 Article
• Initiated and Developed the Magic Card Visual Search Algorithm For the eBay Core App
  The Verge, 2020 Article
• CTO Spot Award for "Extraordinary Contribution During the COVID-19 Pandemic"
  eBay Inc, 2020 Certificate

Education

• Ph.D., Computer Science
  Department of Computer and Information Sciences
  University of Delaware, Newark, DE, USA

• M.Sc., Computer Science
  Department of Computer and Information Sciences
  University of Delaware, Newark, DE, USA

• B.Eng., Artificial Intelligence
  School of Electronics and Information Engineering
  Xi'an Jiaotong University, Xi'an, Shannxi, CHINA

Invited Talks

• A Novel Cruise Robot.
  Microsoft Research Asia (MSRA). Beijing, China, 2010.
• A Vision based Automatic Patient and Device Recognition System.
  Siemens Medical Solutions. Malvern, PA, 2011.
• Stereo Vision based Depth of Field Rendering on a Mobile Device.
  IS&T/SPIE Electronic Imaging (EI). San Francisco, CA, 2014.
• Vision based Rapid Modeling of Personalized Rehabilitation Devices.
  11th Annual Biomechanics Research Symposium. Newark, DE, 2014.
• 3D Bridge Inspection and Evaluation Using UAV and Image Reconstruction.
  11th Annual Inter-University Symposium on Infra Management (AISIM). Newark, DE, 2015.
• 3D Bridge Inspection and Evaluation Using UAV and Image Reconstruction.
  Transportation Research Board Annual Meeting. Washington, D.C., 2016.
• GraB: Visual Saliency via Novel Graph Model and Background Priors.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, 2016.
• Im2Fit: Fast 3D Model Fitting and Anthropometrics using Single Consumer Depth Camera and Synthetic Data.
  IS&T/SPIE Electronic Imaging (EI). San Francisco, CA, 2016.
• Towards the Success Rate of One: Real-time Unconstrained Salient Object Detection.
  IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Tahoe, NV, 2018.
• Towards Real-time 3D Reconstruction using Consumer UAVs.
  The 28th Workshop on Information Technologies and Systems (WITS). Santa Clara, CA, 2018.
• Towards Fine-Grained Recognition: Joint Learning for Object Detection and Fine-Grained Classification.
  International Symposium on Visual Computing (ISVC). Lake Tahoe, NV, 2019.
• 3D Visual Object Detection from Monocular Images.
  International Symposium on Visual Computing (ISVC). Lake Tahoe, NV, 2019.
• Mobile Head Tracking for eCommerce and Beyond.
  IS&T/SPIE Electronic Imaging (EI). San Francisco, CA, 2020.

Professional Activities

• Program Committee
   The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020

• Journal Reviewer
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  IEEE Transactions on Cybernetics
  IEEE Transactions on Instrumentation and Measurement (TIM)
  IEEE Access
  Nature Scientific Reports
  Springer Machine Vision and Applications (MVA)
  IET Computer Vision
  SPIE Journal of Electronic Imaging
  SPIE Optical Engineering
  MDPI Remote Sensing
  MDPI Sensors
  MDPI Robotics

• Conference Reviewer
  IEEE International Conference on Robotics and Automation (ICRA) 2020, 2021.
  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019, 2020.
  European Conference on Computer Vision (ECCV) 2019, 2020.
  Asian Conference on Computer Vision (ACCV) 2019, 2020.
  British Machine Vision Conference (BMVC) 2019, 2020.
  IEEE Winter Conference on Applications of Computer Vision (WACV) 2019, 2020.
  The International Conference on Learning Representations (ICLR), 2020
  IEEE International Conference on Computer Vision (ICCV), 2019

Contact

Email: {my first name}@udel.edu

Visitor Stats: (click for details)

Locations of Site Visitors