Wei Liu

PhD Student
Department of Computer Science
The University of North Carolina at Chapel Hill
Office: Sitterson Hall at UNC, Chapel Hill, NC, 11794
Email: wli...@cs.unc.edu

I am a PhD student of Computer Science department at The University of North Carolina at Chapel Hill under the supervision of Prof. Alex Berg. I received my B.S. at Nanjing University at China in Jul. of 2009. Then, from Aug. 2009 to Jul. 2011, I worked as a research assistant at Carnegie Mellon University for two years with Prof. Fernando De la Torr and Prof. Alex Hauptmann. From Sep. 2011 to May 2012, I did one year PhD study at Computer Science department at UNC Chapel Hill under the supervision of Prof. Svetlana Lazebnik. From May 2012 to Aug. 2012, I was a research intern at the Core Location team under iOS Department at Apple, and I presented my project to SVP Scott Forstall. From Sep. 2012 to Aug. 2013, I did one year PhD study at Computer Science department at Stony Brook University under the supervision of Prof. Alex Berg, then I moved with him back to UNC Chapel Hill in Aug. 2013. I did a great internship at Google Mountain View in 2014 summer. Our team GoogLeNet won the classification and detection challenge in ILSVRC2014. My research speciality is computer vision. The main focus of my current research include:

Abrige the semantic gap of image understanding
Recognize and detect object from large scale image/video dataset

Resume, Google Scholar

News

June 2015: One paper "ParseNet: Looking Wider to See Better" is submitted to arXiv.
March 2015: One paper "Predicting Entry-Level Categories" is submitted to IJCV Marr Prize special issue.
December 2014: I will organize ILSVRC2015. Stay tuned.
November 2014: One paper "Refer-to-as Relations as Semantic Knowledge" is accepted to AAAI 2015.
August 2014: Our team GoogLeNet won the classification and detection challenge in ILSVRC2014 during my 2014 summer internship at Google.
I am the main contributor to the detection task. [Google Research Blog, New York Times, UNC News]

PUBLICATIONS

	ParseNet: Looking Wider to See Better [pdf] [arXiv] [code] Wei Liu, Andrew Rabinovich, and Alexander C. Berg arXiv Preprint, 2015.
	Refer-to-as Relations as Semantic Knowledge [pdf] Song Feng, Sujith Ravi, Ravi Kumar, Polina Kuznetsova, Wei Liu, Tamara L. Berg, Alexander C. Berg, and Yejin Choi AAAI 2015.
	Predicting Entry-Level Categories [pdf] [link] Vicente Ordonez, Wei Liu, Jia Deng, Yejin Choi, Alexander C. Berg, and Tamara L. Berg IJCV 2015 Marr Prize Special Issue. Learning to Name Objects Vicente Ordonez, Wei Liu, Jia Deng, Yejin Choi, Alexander C. Berg, and Tamara L. Berg Communications of the ACM. CACM 2015. (~Research Highlight)
	Going deeper with convolutions [pdf][poster] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich CVPR 2015 Oral.
	Double Fusion for Multimedia Event Detection [pdf] Zhenzhong Lan, Lei Bao, Shoou-I Yu, Wei Liu, and Alexander G. Hauptmann The 18th Int. Conf. on Multimdeida Modeling (MMM'12), 2012.
	A Crowdsourcing Approach to Tracker Fusion [pdf][code] Wei Liu and Alexander G. Hauptmann Technique Report, 2011.
	Informedia@TRECVID 2010 [pdf] Huan Li, Lei Bao, Zan Gao, Arnold Overwijk, Wei Liu, Long-fei Zhang, Shoou-I Yu, Ming-yu Chen, Florian Metze, and Alexander G. Hauptmann TRECVID Video Retrieval Evaluation Workshop, NIST, 2010.
	Rushes Video Summarization via Dynamic Unsupervised Learning [pdf] Yang Liu, Feng Zhou, Wei Liu, Fernando de la Torre, and Yan Liu ACM Multimedia 2010.
	Extending Semi-supervised Learning Methods for Inductive Transfer Learning [pdf] Yuan Shi, Zhenzhong Lan, Wei Liu, and Wei Bi ICDM 2009.