<HTML> <HEAD> <TITLE>Rongrong Ji | HomePage</TITLE> <META http-equiv=Content-Type content="text/html; charset=ISO-8859-1"> <link rel="shortcut icon" href="200px-ColumbiaNYUCoat.ico"> <STYLE> body {margin: 0; border: 0; padding: 0px; border-top: #2d2a62 18px solid; } p,td {font-size: 9.5pt;color: #000;font-family: Arial; } a:link {color: #2B2EAC; text-decoration:none; } a:visited {color: #2B2EAC; text-decoration:none; } a:hover {background: #2B2EAC; color: #ffffff; text-decoration:none; } img {border-width: 1px; border-color: #000000; border-style: solid; } #menu {text-align:right;width: 300px;margin-top:0px;border-bottom:1px dotted #000; } #menu a {color:#393939;font-weight:bold;} .menulinks {line-height:1.7em; margin:0 0 0 0;} .menulink {padding:6px 8px 5px 8px; font-weight:400; margin:0 0 0 2px;} .menulink:hover {background-color:#e6e6e6; } .active {background-color:#e6e6e6; } .active:hover {background-color:#e6e6e6; } .sectiontitle{font-size: 13pt; font-weight:bold; font-family: Arial; } .talks{font-size: 7.5pt; font-weight: bold; color: #393939; font-family: Arial; } #counter img {border-width:0px;} </STYLE> </HEAD> <BODY> <TABLE cellSpacing=18 width=800 border=0 cellpadding="6" align="left" style="height: 100%;"> <TBODY><TR><TD valign="top"> <TABLE cellSpacing=7 width=700 border=0> <TBODY> <TR> <TD align="left" width=150> <img width=150 src="newprofile.png"> </TD> <TD align="left" width=400> <P><font style="font-size: 19pt" face="Tahoma">Rongrong Ji</font><BR> <br><br> <font face=arial color=#666 size=-1> This is my new homepage at Columbia University. I have been a postdoc researcher in DVMM laboratory since October 2010, working with Professor Shih-Fu Chang.</font><br> <br> </TD> </TR> </TBODY> </TABLE> <br> <p class=sectiontitle>Contact Information</p> <TABLE cellSpacing=7 width=450 bgcolor=#e6e6e6 border=0> <TBODY> <TR><TD align=justify> <P> PostDoc Researcher at DVMM Lab<BR> Department of Electrical Engineering, Columbia University<BR> Address: Room 712, Schapiro Research Building (CEPSR).<BR> Mail: 1312 S. W. Mudd, 500 West 120th Street, New York, NY 10027<BR> Phone: (212) 854-3105, Fax: (212) 932-9421, Mobile: 917-655-3190<BR> <b>Email: jirongrong at gmail.com or rrji at ee.columbia.edu</b><BR> </TD></TR> </TBODY> </TABLE> <br><br> September 2012: I have joined the technical program committee of CVPR 2013<br> July 2012: I have co-organized a special session of Mobile-based Multimedia Analysis in MMM 2013<br> June 2012: I have co-organized a special session of Location-based Social Media in PCM 2012<br> April 2012: I have joined the technical program committee of ACM Multimedia 2012<br> <br> <br> <p class=sectiontitle>Research Interest</p> <TABLE cellSpacing=7 width=450 bgcolor=#e6e6e6 border=0> <TBODY> <TR><TD align=justify> <P> My research interests fall in the areas of computer vision and multimedia. My recent works mainly focus on social media, visual search, and computerized scene understanding.<BR> </TD></TR> </TBODY> </TABLE> <br> <p class=sectiontitle>Education Background</p> <TABLE cellSpacing=7 width=600 bgcolor=#e6e6e6 border=0> <TBODY> <TR><TD align=justify> <P> <LI>September 2007  Normber 2011<BR> Doctor, Department of Computer Science and Technology, Harbin Institute of Technology<BR> <LI>September 2005  July 2007<BR> Master, Department of Computer Science and Technology, Harbin Institute of Technology<BR> <LI>September 2001 - July 2005<BR> Bachelor, Department of Computer Science and Technology, Harbin Engineering University<BR> </TD></TR> </TBODY> </TABLE> <br> <p class=sectiontitle>Research Experiences</p> <TABLE cellSpacing=7 width=600 bgcolor=#e6e6e6 border=0> <TBODY> <TR><TD align=justify> <P> <LI>October, 2010 - now, PostDoc Researcher<BR> Digital Video and Multimedia Lab (Advisor: Professor Shih-Fu Chang)<BR> <LI>May, 2010  October 2010<BR> Visiting Student: Institute of Digital Media, Peking University (Advisor: Professor Wen Gao)<BR> <LI>April, 2010  May, 2010<BR> Visiting Student, Texas University at San Antonio (Advisor: Professor Qi Tian)<BR> <LI>August, 2007 - September, 2008<BR> Research Intern: Microsoft Research Asia (Advisor: Dr. Xing Xie)<BR> <LI>September, 2005  October 2010<BR> Research Assistant, Visual Intelligence Laboratory, (Advisor: Professor Hongxun Yao)<BR> </TD></TR> </TBODY> </TABLE> <br> <p class=sectiontitle>Selected Journal Publications</p> <TABLE cellSpacing=7 width=675 bgcolor=#e6e6e6 border=0> <TBODY> <TR><TD align=justify> <div class="pub" id="ijcv11:compactdescriptor"> <UL> <LI>Rongrong Ji, Ling-Yu Duan, Jie Chen, Hongxun Yao, Junsong Yuan, Yong Rui, and Wen Gao.<BR> <b>Location Discriminative Vocabulary Coding for Mobile Landmark Search</b><BR> International Journal of Computer Vision (IJCV), 2012. </UL> </div> <div class="pub" id="tip11:codebookcompression"> <UL> <LI>Rongrong Ji, Hongxun Yao, Wei Liu, Xiaoshuai Sun, and Qi Tian.<BR> <b>Task Dependent Visual Codebook Compression</b> <BR> IEEE Transactions on Image Processing (TIP), 2012. </UL> </div> <div class="pub" id="tip:3d"> <UL> <LI>Yue Gao, Meng Wang, Dacheng Tao, Rongrong Ji, Qionghai Dai, and Naiyao Zhang.<BR> <b>3D Object Retrieval and Recognition with Constructive Hypergraph Analysis</b> <BR> IEEE Transactions on Image Processing (TIP), 2012. </UL> </div> <div class="pub" id="tmm"> <UL> <LI>Rongrong Ji, Ling-Yu Duan, Hongxun Yao, Lexing Xie, Yong Rui and Wen Gao.<BR> <b>Learning to Distribute Vocabulary Indexing for Scalable Visual Search</b> <BR> IEEE Transactions on Multimedia (TMM), 2012. </UL> </div> <div class="pub" id="tomccap12:aqs"> <UL> <LI>Rongrong Ji, Felix X. Yu, and Shih-Fu Chang.<BR> <b>Active Query Sensing for Mobile Location Search</b> <BR> ACM Transactions on Multimedia Computing, <BR> Communications and Applications (TOMCCAP), 2012. </UL> </div> <div class="pub" id="tomccap12:hashing"> <UL> <LI>Dong Liu, Shuicheng Yan, Rongrong Ji, Xian-Sheng Hua, and Hong-Jiang Zhang.<BR> <b>Image Retrieval with Query-Adaptive Hashing</b> <BR> ACM Transactions on Multimedia Computing, <BR> Communications and Applications (TOMCCAP), 2012. </UL> </div> <div class="pub" id="tomccap11:mining"> <UL> <LI>Rongrong Ji, Bineng Zhong, Hongxun Yao, and Qi Tian.<BR> <b>Mining City Landmarks by Modeling Reconstruction Sparsity</b> <BR> ACM Transactions on Multimedia Computing, <BR> Communications and Applications (TOMCCAP), 2011. </UL> </div> <div class="pub" id="tist11:context"> <UL> <LI>Rongrong Ji, Hongxun Yao, Xiaoshuai Sun, Pengfei Xu, Xianming Liu, and Qi Tian.<BR> <b>Context-aware Semi-Local Feature Detector</b> <BR> ACM Transactions on Intelligent System and Technology (TIST), 2012. </UL> </div> <div class="pub" id="pr11:action"> <UL CLASS="PUB"> <LI>Rongrong Ji, Hongxun Yao, and Xiaoshuai Sun.<BR> <b>Actor-Independent Action Search Using Spatiotemporal Vocabulary with Appearance Hashing</b> <BR> Pattern Recognition (PR), 2011. </UL> </div> <div class="pub" id="ieeemm:vocbaulary"> <UL CLASS="PUB"> <LI>Rongrong Ji, Hongxun Yao, Xing Xie, and Qi Tian.<BR> <b>Vocabulary Hierarchy Optimization and Transfer for Scalable Image Search</b> <BR> IEEE Multimedia Magazine (IEEE MM), <BR> Special Issue on Visual Content Identification and Search, Accept, 2011. </UL> </div> </TD></TR> </TBODY> </TABLE> <br> <p class=sectiontitle>Selected Conference Publications</p> <TABLE cellSpacing=7 width=790 bgcolor=#e6e6e6 border=0> <TBODY> <TR><TD align=justify> <div class="pub" id="cvpr12a"> <UL> <LI>Wei Liu, Jun Wang, Rongrong Ji, Yu-Gang Jiang, and Shih-Fu Chang.<BR> <b>Supervised Hashing with Kernels</b> <BR> IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2012. </UL> </div> <div class="pub" id="cvpr12b"> <UL> <LI>Xiaoshuai Sun, Hongxun Yao, and Rongrong Ji.<BR> <b>What Are We Looking For: Towards Statistical Modeling of Saccadic Eye Movements and Visual Saliency</b> <BR> IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2012. </UL> </div> <div class="pub" id="cvpr12c"> <UL> <LI>Rongrong Ji, Ling-Yu Duan, Jie Chen, and Wen Gao.<BR> <b>Towards Compact Topical Descriptor</b> <BR> IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2012. </UL> </div> <div class="pub" id="cvpr12d"> <UL> <LI>Liujuan Cao*, Rongrong Ji*, Yue Gao, Yi Yang, and Qi Tian.<BR> <b>Weakly Supervised Coding with Geometric Consistency Pooling</b> <BR> IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), (* denotes equal contributions), 2012. </UL> </div> <div class="pub" id="cvpr12e"> <UL> <LI>Felix X. Yu, Rongrong Ji, Ming-Hen Tsai, Guangnan Ye, and Shih-Fu Chang.<BR> <b>Weak attributes for large-scale image retrieval</b> <BR> IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2012. </UL> </div> <div class="pub" id="cvpr10:semanticembedding"> <UL> <LI>Rongrong Ji, Hongxun Yao, Xiaoshuai Sun, Bineng Zhong, and Wen Gao.<BR> <B>Towards Semantic Embedding in Visual Vocabulary</B><BR> IEEE International Conference of Computer Vision and Pattern Recognition (CVPR), Oral, 2010. </UL> </div> <div class="pub" id="cvpr10:weakly"> <UL> <LI>Bineng Zhong, Hongxun Yao, Rongrong Ji, Xiaotong Yuan, Shaohui Liu, and Wen Gao.<BR> <B>Visual Tracking via Weakly Supervised Learning from Multiple Imperfect Oracles</B> <BR> IEEE International Conference of Computer Vision and Pattern Recognition (CVPR), 2010. </UL> </div> <div class="pub" id="cvpr11:tracking"> <UL> <LI>Dawei Liang, Qingming Huang, Hongxun Yao, Shuqiang Jiang, Rongrong Ji, and Wen Gao.<BR> <B>Novel Observation Model for Probabilistic Object Tracking</B> <BR> IEEE International Conference of Computer Vision and Pattern Recognition (CVPR), 2010. </UL> </div> <div class="pub" id="cvpr09:hierarchy"> <UL> <LI>Rongrong Ji, Xing Xie, Hongxun Yao, and Wei-Ying Ma.<BR> <b>Hierarchical Optimization of Visual Vocabulary for Effective and Transferable Retrieval</b> <BR> IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2009. </UL> </div> <div class="pub" id="ijcai11:compactdescriptor"> <UL> <LI>Rongrong Ji, Ling-Yu Duan, Jie Chen, Hongxun Yao, and Wen Gao.<BR> <b>Learning Compact Visual Descriptor for Low Bit Rate Mobile Landmark Search</b> <BR> International Joint Conference of Artificial Intelligence (IJCAI), 2011. </UL> </div> <div class="pub" id="aaai11:matrix"> <UL> <LI>Yi Yang, Heng Tao Shen, Feiping Nie, Rongrong Ji, and Xiaofang Zhou.<BR> <b>Nonnegative Spectral Clustering with Discriminative Regularization</b> <BR> Twenty-Fifth Conference on Artificial Intelligence (AAAI), 2011. </UL> </div> <div class="pub" id="mm11:multichannel"> <UL> <LI>Rongrong Ji, Ling-Yu Duan, Jie Chen, Hongxun Yao, Yong Rui, Shih-Fu Chang, and Wen Gao.<BR> <b>Towards Low Bit Rate Mobile Visual Search with Multiple Channel Coding</b> <BR> ACM Multimedia (MM), Full Paper, Oral, 2011. </UL> </div> <div class="pub" id="mm11:aqs"> <UL> <LI>Felix X. Yu, Rongrong Ji, and Shih-Fu Chang.<BR> <b>Active Query Sensing</b> <BR> ACM Multimedia (MM), Full Paper, Oral, 2011 (Best Paper Award). </UL> </div> <div class="pub" id="mm11:transfer"> <UL> <LI>Xianming Liu, Hongxun Yao, Rongrong Ji, and Qi Tian.<BR> <b>Learning Heterogeneous Data for Hierarchical Web Video Classification</b> <BR> ACM Multimedia (MM), Full Paper, Oral, 2011. </UL> </div> <div class="pub" id="mm09:landmark"> <UL> <LI>Rongrong Ji, Xing Xie, Hongxun Yao, Wei-Ying Ma.<BR> <b>Mining City Landmarks from Blogs by Graph Modeling</b> <BR> ACM Multimedia (MM), Oral, 2009. </UL> </div> </TD></TR> </TBODY> </TABLE> <br> <p class=sectiontitle>Selected Academic Services</p> <TABLE cellSpacing=7 width=600 bgcolor=#e6e6e6 border=0> <TBODY> <TR><TD align=justify> <LI><b>Associate Editor</b><BR> Frontiers of Computer Science<BR> <BR> <LI><b>Section Chair</b><BR> Multimedia Modeling, 2013<BR> Pacific Rim Conference on Multimedia, 2012<BR> <BR> <LI><b>Program Committee Member</b><BR> Computer Vision and Pattern Recognition 2013<BR> European Conference on Computer Vision 2012<BR> ACM Multimedia, 2012<BR> ACM Multimedia, 2011<BR> <BR> <LI><b>Journal Reviewer</b><BR> IEEE Signal Processing Magazine<BR> IEEE Transactions on Pattern Analysis and Machine Intelligence<BR> IEEE Transactions on Image Processing<BR> IEEE Transactions on Multimedia<BR> IEEE Transactions on Knowledge and Data Engineering<BR> IEEE Transactions on Circuits and Systems for Video Technology<BR> IEEE Transactions on System man and Cybernetics Part A, B, C<BR> ACM Transactions on Multimedia Computing, Communication and Application<BR> ACM Transactions on Information Systems<BR> Pattern Recognition <BR> </TD></TR> </TBODY> </TABLE> <br> <p class=sectiontitle>Selected Awards</p> <TABLE cellSpacing=7 width=600 bgcolor=#e6e6e6 border=0> <TBODY> <TR><TD align=justify> 2011 ACM Multimedia Best Paper Award<BR> 2010 CVPR Doctoral Consortium Award<BR> 2009 Ongoing Excellent PH.D. Thesis Award of HIT<BR> 2008 Tencent Fellowship<BR> 2007 Microsoft Fellowship<BR> </TD></TR> </TBODY> </TABLE> <p> <span lang=EN-US> <a href="http://www3.clustrmaps.com/counter/maps.php?url=http://vilab.hit.edu.cn/~rrji/"> <span style='mso-no-proof:yes;text-decoration:none;text-underline:none'><img border=0 width=160 height=106 id="_x0000_i1025" src="http://www3.clustrmaps.com/counter/index2.php?url=http://vilab.hit.edu.cn/~rrji/" alt="Locations of visitors to this page"> </span> </a> </span></p> <HR color="#000" size="5"> <font style="font-size: 7pt" face="Arial"> &copy; Rongrong Ji - Last modified on October, 12, 2012 </font> </TD></TR></TBODY></TABLE> </BODY></HTML>