Link to Qilin Zhang's New Homepage
This web page is outdated. Please check my new homepage here.

Qilin Zhang

Ph.D. candidate in Computer Science
Stevens Institute of Technology HERE Technologies, Highly Automated Driving Team
Hoboken, New Jersey Chicago, Illinois, USA

  email

Profile on LinkedIn   LinkedIn


USTC UFL STEVENS

This homepage serves as a time machine which reminds me of my good old days as a Ph.D. student in Computer Science at Stevens Institute of Technology, under the supervision of Dr. Gang Hua. Prof. Hua offered me both valuable research opportunities and priceless guidance in computer vision research. My research and working areas include computer vision, machine learning (including deep learning), signal processing, practical optimization and data analytics.

Thanks to Prof. Hua’s support and valuable help from faculty members such as Prof. Philippos Mordohai, I graduated from the Ph.D. program in the summer of 2016. The four years I spent at the Vision Lab would surely be among the most unforgettable time in my life. I often misses my old friends, including Haoxiang Li, Changjiang Cai, Le Wang, Lingyan Ran, Min Zheng, Yuxiao(James) Huang, Chengjiang Long, Mohammed Kutbi, and others.

Prior to attending Stevens, I received my Bachelor of Engineering from University of Science and Technology of China and my Master of Science from University of Florida.

After I graduated from Stevens in 2016, I joined HERE Technologies in Chicago, Illinois, as a Senior Research Engineer in the Highly Automated Driving (HAD) team of the Automotive Division. We are consistently building and perfecting deep neural network based automated map building algorithms, to enable autonomous driving with our super high definition 3D maps. HERE’s map is currently in use by major German luxury car manufacturers.

Publications: (Google Scholar)

sensors-18-01979
Action Recognition by an Attention-Aware Temporal Weighted Convolutional Neural Network
Le Wang, Jinliang Zang, Qilin Zhang, Zhenxing Niu, Gang Hua, and Nanning Zheng
Sensors 2018, 18(7), 1979; doi: 10.3390/s18071979 [Link] [PDF] [BibTeX]

sensors-18-01657
Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation
Le Wang, Xuhuan Duan, Qilin Zhang, Zhenxing Niu, Gang Hua, and Nanning Zheng
Sensors 2018, 18(5), 1657; doi: 10.3390/s18051657 [Link] [PDF] [BibTeX]

icip2018
Video Object Co-segmentation from Noisy Videos by a Multi-level Hypergraph Model
Xin Lv, Le Wang, Qilin Zhang, Nanning Zheng, and Gang Hua
Proc. IEEE International Conference on Image Processing (ICIP’2018), Athens, Greece, October, 2018. [PDF] [BibTeX]

icip2018
Joint Spatio-temporal Action Localization in Untrimmed Videos with Per-frame Segmentation
Xuhuan Duan, Le Wang, Changbo Zhai, Qilin Zhang, Zhenzing Niu, Nanning Zheng, and Gang Hua
Proc. IEEE International Conference on Image Processing (ICIP’2018), Athens, Greece, October, 2018. [PDF] [BibTeX]

icme2018workshop
Weighted Multi-Region Convolutional Neural Network for Action Recognition with Low-Latency Online Prediction
Yunfeng Wang, Wengang Zhou, Qilin Zhang, Xiaotian Zhu, and Houqiang Li
Proceedings of IEEE International Conference on Multimedia and Expo (ICME), Workshops, San Diego, USA, July 2018. [PDF] [BibTeX]

icme2018industry
Enhanced Action Recognition with Visual Attribute-augmented 3D Convolutional Neural Network
Yunfeng Wang, Wengang Zhou, Qilin Zhang, and Houqiang Li
Proceedings of IEEE International Conference on Multimedia and Expo (ICME), Industry Program, San Diego, USA, July 2018. [PDF] [BibTeX]

iv2018trafficsensory
Traffic Sensory Data Classification by Quantifying Scenario Complexity
Jiajie Wang, Chi Zhang, Yuehu Liu, and Qilin Zhang
Proceedings of IEEE Intelligent Vehicles Symposium (IV’2018), Changshu, China, June, 2018. [PDF] [BibTeX]

iv2018Multimodel
Multi-model Traffic Scene Simulation with Road Image Sequences and GIS Information
Zhichao Cui, Yuehu Liu, Fuji Ren, and Qilin Zhang
Proceedings of IEEE Intelligent Vehicles Symposium (IV’2018), Changshu, China, June, 2018. [PDF] [BibTeX]

iv2018aGraded
A Graded Offline Evaluation Framework for Intelligent Vehicle’s Cognitive Ability
Chi Zhang, Yuehu Liu, Qilin Zhang, and Le Wang
Proceedings of IEEE Intelligent Vehicles Symposium (IV’2018), Changshu, China, June, 2018. (oral presentation) [PDF] [BibTeX]

aiai18
Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition
Jinliang Zang, Le Wang, Ziyi Liu, Qilin Zhang, Zhenxing Niu, Gang Hua, and Nanning Zheng
Proceedings of 14th International Conference on Artificial Intelligence Applications and Innovations (AIAI’2018), May 25-27, 2018, Rhodes, Greece. [Link] [PDF] [arXiv] [BibTeX]

AAAI-18
Video-based Sign Language Recognition without Temporal Segmentation
Jie Huang, Wengang Zhou, Qilin Zhang, Houqiang Li, and Weiping Li
Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18), Feb. 2-7, 2018, New Orleans, Louisiana, USA. [Link] [PDF] [arXiv] [BibTeX]

Spatial-Pixel-Pair
A Hyperspectral Image Classification Framework with Spatial Pixel Pair Features
Lingyan Ran, Yanning Zhang, Wei Wei and Qilin Zhang
Sensors 2017, 17(10), 2421; doi:10.3390/s17102421 [Link] [PDF] [BibTeX]

CNN-navigation
Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images
Lingyan Ran, Yanning Zhang, Qilin Zhang and Tao Yang
Sensors 2017, 17(6), 1341; doi:10.3390/s17061341 [Link] [PDF] [Video Demo] [Code Zip] [BibTex]

ACMMM-15-oral
Multi-View Visual Recognition of Imperfect Testing Data
Qilin Zhang and Gang Hua
Proceedings of the 23rd ACM international conference on Multimedia (ACMMM) October, 2015, Brisbane, Australia (oral presentation) [Link] [PDF] [BibTeX] [Presentation Slides]

IPSJ-CVA-Vol7-2015
Auxiliary Training Information Assisted Visual Recognition
Qilin Zhang, Gang Hua, Wei Liu, Zicheng Liu, and Zhengyou Zhang
IPSJ Transactions on Computer Vision and Applications, Vol. 7 (2015) pp. 138-150 [Link] [PDF] [BibTeX]

ACCV-14
Can Visual Recognition Benefit from Auxiliary Information in Training?
Qilin Zhang, Gang Hua, Wei Liu, Zicheng Liu, and Zhengyou Zhang
Asian Conference on Computer Vision (ACCV), Singapore, 2014. (oral presentation, oral acceptance rate 4%) [Link] [PDF] [BibTeX]

IEEEtrans
Iterative Sparse Asymptotic Minimum Variance Based Approaches for Array Processing
Habti Abeida, Qilin Zhang, Jian Li, and Nadjim Merabtine
IEEE Transactions on Signal Processing, vol. 61, no. 4, pp. 933--944, Feb. 2013 [DOI] [preprint PDF] [Matlab Code Zip] [BibTeX]

jasa
Fast Implementation of Sparse Iterative Covariance-Based Estimation for Source Localization
Qilin Zhang, Habti Abeida, Ming Xue, William Rowe, and Jian Li
The Journal of the Acoustical Society of America, vol. 131, no. 2, pp. 1249--1259, Feb. 2012. [DOI] [preprint PDF] [BibTeX]

asilomar
Fast Implementation of Sparse Iterative Covariance-Based Estimation for Array Processing
Qilin Zhang, Habti Abeida, Ming Xue, William Rowe, and Jian Li
The 45th Asilomar Conference on Signals, Systems and Computers, Asilomar Conference Grounds, Pacific Grove, CA, Nov. 2011. (oral presentation) [DOI] [preprint PDF] [BibTeX]



*Electronic papers shared on this website are for fast dissemination of research work. The copyrights of the papers belong to the corresponding publishers.*

View Qilin Zhang's profile on LinkedIn links