I am currently a joint-training Ph.D. student (or called visiting scholar) in the IFP (Image Formation and Processing) group of the University of Illinois at Urbana-Champaign, advised by Prof. Thomas S. Huang. I am also a Ph.D. student in the Institute of Intelligent Media Computing at Fudan University, under the supervision of Prof. Yu-Gang Jiang and Prof. Xiangyang Xue. From July 2016 to July 2017, I was a research intern at Intel Labs China.
Department of Electrical and Computer Engineering
University of Illinois at Urbana-Champaign
2029 Beckman Institute MC 251, 405 N. Mathews Ave, Urbana, Illinois 61801
Email: shen54 AT illinois.edu / zhiqiangshen13 AT fudan.edu.cn / zhiqiangshen0214 AT gmail.com
[Google Scholar] | [Github]
My research focuses on the broad area of computer vision and machine learning. Specifically, I am interested in deep learning methods for object detection, fine-grained recognition, image/video captioning, etc. Recently, I focus on
- Deep Learning, including designing and training high-efficiency network structure
- Video Analysis, including detection, captioning, summarization and prediction
- Image Understanding, including visual question answering, captioning, fine-grained recognition and detection
- Weakly-supervised/Unsupervised Learning
- Low-bit Networks
- [02/26, 2019] One paper accepted to CVPR 2019.
- [12/21, 2018] One paper accepted to ICLR 2019.
- [11/1, 2018] Our paper MEAL: Multi-Model Ensemble via Adversarial Learning accepted in AAAI 2019 as Oral Presentation. Code and models are available at Github.
- [09/27, 2018] An extended version of DSOD is available on: arXiv.
- [07/29, 2018] One paper accepted in ECCV 2018.
- [01/12, 2018] I gave an invited talk at the Baidu IDL, Sunnyvale, CA, USA on the topic of learning object detectors from scratch. My talk involved our recent two papers DSOD and GRP-DSOD. Slides can be downloaded here (or Google Drive).
- [12/22, 2017] We released the code and model for MSR-VTT Challenge (Video Captioning) on Github.
- [12/04, 2017] Our new paper GRP-DSOD is available at: arXiv. Code and models are available at Github.
- Code and models for DSOD are available at: Github.
- Code and models for Network Slimming are available at: Github.
- Two papers accepted to ICCV 2017.
Two papers submitted to ICCV 2017.
- Our paper "Weakly Supervised Dense Video Captioning" accepted to CVPR 2017.
- Our paper "Iterative Object and Part Transfer for Fine-Grained Recognition" accepted to ICME 2017 as an oral presentation.
- During my internship, our team won the 2016 Intel China Award (ICA), the highest award for team achievement in Intel China.
- 4th Place (Human Evaluation) and 5th Place (Automatic Evaluation Metrics) Winners at the MSR-VTT Challenge (Video Captioning). Code is here .
- Conference reviewer: ICCV 2019, CVPR 2019, AAAI 2019, CVPR 2018, ACCV 2018, NIPS 2016.
- Journal reviewer: IJCV, TIP, JVCI.
Awards and Honors
- CVPR 2019 Doctoral Consortium travel award, 2019
- ICLR 2019 travel award, 2019
- AAAI 2019 student scholarship award, 2019
- ICCV 2017 student volunteer, 2017
- Huawei scholarship, 2017
- During my internship, our team won the 2016 Intel China Award (ICA), the highest award for team achievement in Intel China, 2016
- Tung OOCL scholarship, 2015
- Special Grade Scholarship, 2013
- University-level Outstanding Students, 2013
- MSR-VTT Challenge (video captioning): ranked 4th in human evaluation and ranked 5th in the automatic evaluation metrics (Team leader), 2016
- Top 10% in Kaggle Competition of Right Whale Recognition, 2016
- Second Prize in DataCastle Competition of the Verification Code Recognition, 2016
- Second Prize (National-level) in China Graduate Student Mathematical Contest in Modeling, 2015
- MCM/ICM -- Honorable Mention, 2012
- First Prize (National-level) in Electrical Engineering Mathematical Contest in Modeling, 2012
- First Prize (National-level) in China Undergraduate Mathematical Contest in Modeling, 2011
- 2015.9- 2016.1, Fudan University, COMP120008.02, C++ language programming