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.
My research interests include Computer Vision, Machine Learning, AR/VR and Robotics.
Email me for source code (mostly available)
@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
@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} }
@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} }
@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} }
@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} }
@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
@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
@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} }
@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}, }
@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} }
@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} }
@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
@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} }
@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} }
@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} }
@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} }
@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} }
@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} }
Contact