I am currently a post-doctoral researcher in CyLab, ECE Department, CMU, advised by Prof. Marios Savvides. My research interests span computer vision, machine learning, deep learning, etc.
Prior to CMU, I was fortunate to be a joint-training Ph.D student (2017-2019) in UIUC/IFP group, advised by Prof. Thomas S. Huang.
I received my Ph.D from Fudan University, collaborating with Prof. Yu-Gang Jiang and Prof. Xiangyang Xue. I was a research intern at Intel Labs China and SenseTime Research, working with Zhuang Liu, Jianguo Li, Yurong Chen (ILC), Mingyang Huang, Jianping Shi (SenseTime Research).
Carnegie Mellon University
5000 Forbes Avenue, Pittsburgh, PA, 15213
Email: zhiqians AT andrew.cmu.edu / 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
- Few-shot and zero-shot learning
- 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 to 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, TMM, JVCI.
Awards and Honors
- CVPR 2019 Doctoral Consortium travel award, 2019
- ICLR 2019 travel award, 2019
- AAAI 2019 student scholarship award, 2018
- 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