home

 

DVMM News & Awards
bar

 

News and Awards

2020

October: DVMM alum John R. Smith awarded ACM SIGMM Technical Achievement Award 2020 (more)

September: 09/2020 Columbia Engineering launched Center of AI Technology in collaboration with Amazon. Prof. Chang serves as Inaugural Director (more)

July: The DVMM team and collaborators in UIUC, Army Research Lab, and USC ISI, won the Best Demo paper Award at ACL 2020 for the following work!

GAIA: A Fine-grained Multimedia Knowledge Extraction System.  Manling Li*, Alireza Zareian*, Ying Lin, Xiaoman Pan, Spencer Whitehead, Brian Chen, Bo Wu, Heng Ji, Shih-Fu Chang, Clare Voss, Daniel Napierski and Marjorie Freedman (*equal contributions)  In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL2020) Demo Track   Seattle, WA   July, 2020 [pdf] [Project Page]

"novel multimedia, multi-language knowledge extraction system, rigorously tested". "incorporate several components alongside sota methods". "excellent associated online demo, video and open-source code"

2019

June: Prof. Chang gave keynote talks on multimodal knowledge graph and GAN Fake Image Detection at CVPR workshops (link)

June: Dr. Xu Zhang and and Prof. Chang co-authored the following paper that received the Best paper Award at 2019 EARTHVISION workshop at CVPR.
Matt Leotta, Chengjiang Long, Bastien Jacquet, Matthieu Zins, Dan Lipsa, Jie Shan, Bo Xu, Zhixin Li, Xu Zhang, Shih-Fu Chang, Matthew Purri, Jia Xue, Kristin Dana, "Urban Semantic 3D Reconstruction from Multiview Satellite Imagery," EARTHVISION 2019, IEEE/ISPRS Workshop on Large Scale Computer Vision for Remote Sensing Imagery, June 17, 2019, Long Beach, CA (link)

2018

July: Prof. Chang elected to Academia Sinica (link)

June: DVMM's research on pattern discovery received the Best Poster Award at ICMR 2018 (link)

January: DVMM Postdoc Hanwang Zhang joined Nanyang Technological University as Assistant Professor. (link)

January: DVMM Alum Dr. Wei Liu listed among "AI's 10 To Watch". (link)

2017

December: Prof. Chang named ACM Fellow (link)

October: Prof. Chang gave a keynote speech at the ACM Turing 50th Celebration Conference - China (link)

2016

October: Prof. Chang was listed as the Most Influential Scholar in the field of Multimedia 2016. (link)

June: The following paper published by the DVMM team together with collaborators in IDIAP RESEARCH INSTITUTE, YAHOO! LABS LONDON, and JW PLAYER won the first Multimodal Best Paper at ICMR 2016.

Nikolaos Pappas, Miriam Redi, Mercan Topkara, Brendan Jou, Hongyi Liu, Tao Chen, Shih-Fu Chang. Multilingual Visual Sentiment Concept Matching. In ACM International Conference on Multimedia Retrieval (ICMR), 2016. [link]

It studied how concepts associated with strong emotions in online photos are similar to or different from each other across 12 different languages. We developed new clustering methods to group adjective-noun pairs from different languages and discover insights about such multilingual concept clusters, such as the universal use of certain concepts across languages and unique concepts that are specific to certain languages only.

June: DVMM's Research on scalable image search using compact hashing received the Honorable Mention for the 2016 Best Paper Award of IEEE Transactions on Multimedia. The work, conducted by former DVMM postdoc Dr. Yu-Gang Jiang (now a Professor at Fudan University), presented novel methods to solve an open problem associated with hash-based image search in which a large number of images may have identical hash codes and thus rankings of individual images cannot be accurately determined. The proposed method uses an adaptive approach to change the weights for each query image when computing hash code distances.

Yu-Gang Jiang, Jun Wang, Xiangyang Xue, Shih-Fu Chang. Query-Adaptive Image Search with Hash Codes. IEEE Transactions on Multimedia, 15(2):442-453, 2013.

2015

October: This paper described a large team-built system, DIG, for crawling, ingesting, and searching large-scale heterogeneous data from the Web. The fast image similarity search tool capable of searching more than 10 million images within just few seconds was developed by the DVMM group using novel compact hashing techniques. The system has been used by law enforcement agencies and non-governmental organizations for countering online human trafficking crimes. Best Applied Paper Award, the 14th International Semantic Web Conference (ISWC), Oct. 2015.

P. Szekely, C. Knoblock, J. Slepicka, A. Philpot, A. Singh, C. Yin, D Kapoor, P. Natarajan, D. Marcu, K. Knight, D. Stallard, S. S. Karunamoorthy, R Bojanapalli, S. Minton, B. Amanatullah, T. Hughes, M. Tamayo, D. Flynt, R. Artiss, S.-F. Chang, T. Chen, G. Hiebel and L. Ferreira, "Building and Using a Knowledge Graph to Combat Human Trafficking," In International Conference on Semantic Web (ICSW), Pennsylvania, Oct. 2015. (link)

September: DVMM team publishes a comprehensive survey paper on compact hashing to address fundamental challenges in finding similar data or patterns in large databases. It covers learning to hash methods that exploit information such as data distributions or class labels when optimizing the hash codes or functions. It surveys unsupervised, semi-supervised, and supervised learning techniques. It also summarizes recent hashing approaches utilizing the deep learning models.

Jun Wang, Wei Liu, Sanjiv Kumar, and Shih-Fu Chang. "Learning to Hash for Indexing Big Data-A Survey." arXiv preprint arXiv:1509.05472 (2015). (link)

September: Every culture and language is unique. How are images in various languages used to express affective visual concepts? And how are affective visual concepts used to convey different emotions and sentiment across languages? We have developed an ontology that culled over 15,600 hierarchically organized visual concepts consisting of adjective-noun pairs from 12 languages, trained language-specific visual concept detector banks for six major languages using deep networks, and studied the commonalities and differences in predicting sentiments using image content across languages.

project web page: http://mvso.cs.columbia.edu/

paper: Brendan Jou*, Tao Chen*, Nikolaos Pappas*, Miriam Redi*, Mercan Topkara* and Shih-Fu Chang, "Visual Affect Around the World: A Large-scale Multilingual Visual Sentiment Ontology," ACM Conference on Multimedia (ACMMM), Brisbane, Australia, 2015. (link)

September: Most of existing event categories in video recognition research are limited and predefined, far less than the scale and diversity of event classes encountered in real-world applications. Many practical situations also call for abilities to answer queries of new events that have not been seen before. To address these challenges, we have developed a large-scale structured event ontology, called EventNet. EventNet consists of 500 events and 4,490 event-specific concepts. It includes automatic detection models for the video events and constituent concepts using deep learning with around 95,000 training videos from YouTube. The system allows users to explore rich hierarchical structures among video events, relations between concepts and events, and automatic detection of events and concepts embedded in user-uploaded videos in a live fashion. Most importantly, it showed significant performance gains in retrieving videos of novel events by mapping new events to the large semantic concept pool and using the existing concept detector bank to retrieve videos from large archives.

project page: http://eventnet.ee.columbia.edu

paper: Guangnan Ye* , Yitong Li* , Hongliang Xu, Dong Liu, Shih-Fu Chang, "EventNet: A Large Scale Structured Concept Library for Complex Event Detection in Video," in ACM Multimedia (ACMMM), Brisbane, Australia October, 2015. (link)

2014

September: The DVMM group hosted a farewell lunch for visiting PhD students from UvA (Svetlana Kordumova, Masoud Mazloom, Zhenyang Li, Ran Tao, and Z. Ren). We wish them continuing success in future research (group pic after the farewell lunch: 1 2).

September: DVMM Lab will demonstrate the latest prototypes of the following two projects at NYC Media Lab Annual Summit, September 19, 2014.

1. Columbia News Rover
video demo
An automatic system linking news from 100 broadcast TV channels to Wiki events and summarizing who speaks on what topics in real time.

2. AICER: an Assistive Image Comment Robot That Automatically Suggests
Comments for Social Media Photos
video demo

AICER improves user experience with social media photos by automatically suggesting comments relevant to depicted emotions in the photos.

May: Congratulations to DVMM MS student Yin Cui, who has received the prestigious Edwin Howard Armstrong Memorial Award from the Department of Electrical Engineering of Columbia University. It is given to one outstanding candidate for the M.S. degree to honor the late Edwin Howard Armstrong, professor of Electrical Engineering and inventor of wideband FM broadcasting, the regenerative circuit, and other basic circuits of communications and electronics. Yin worked in the DVMM Lab during 2013-2014 on research of machine learning and computer vision, developing automatic techniques for complex event detection in open source videos. He has published three papers in this area and made major contributions to Columbia's video search project during his MS study.

April: Subh and Felix have won the Best Paper Award at International Conference on Multimedia Retrieval (ICMR) for the following work. It developed a novel quiz based interface to understand the needed evidences for human annotations in making judgements of events in videos. The findings that one microshot is sufficient in majority cases for correct identification or rejection of events are surprising but intuitive. The results are useful for discovering key concepts needed in event representations used in computer vision models.

Minimally Needed Evidence for Complex Event Recognition in Unconstrained Videos. Subhabrata Bhattacharya, Felix X. Yu, Shih-Fu Chang In ACM International Conference on Multimedia Retrieval Glasgow, UK, April, 2014. [pdf]

March: Felix X. Yu, PhD student of electrical engineering, has received the 2014-2015 IBM PhD Fellowship Award. The IBM PhD Fellowship Awards Program is an intensely competitive worldwide program, which honors exceptional PhD students who have an interest in solving problems that are important to IBM and fundamental to innovation in many academic disciplines and areas of study. Yu was granted the award based on his two internships at IBM, where he developed innovative techniques and systems on learning with weakly supervised data in computer vision. Yu¿s advisor is Shih-Fu Chang, Richard Dicker Professor, Senior Vice Dean of Engineering School at Columbia University. Yu was also named a finalist for the Facebook Fellowship Award this year.

2013

November: Prof. Chang shared his views on the major research trends that emerged in the last two decades within the broad area of multimedia information retrieval, with a focus on the ACM Multimedia community. The paper [link] is part of the special issue of ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) celebrating the 20th Anniversary of ACM International Conference on Multimedia.

November: Following their award winning presentation at Barcelona last month, Columbia NewsRover team (Joe Ellis, Hong-Zhi Li, Brendan Jou, Dan Morozoff (remote), and Prof. Chang) demonstrated the multi-modal news aggregation system live at the NY Tech Meetup November 2013 event attended by 675 people.

More details of Columbia NewsRover can be found at http://www.ee.columbia.edu/dvmm/newsrover/







October: DVMM teams won the first and 2nd prizes at the 2013 Multimedia Conference of ACM. The teams and papers are listed below:

Grand Challenge 1st Place Award
-------------------------------
Brendan Jou, Hongzhi Li, Joseph G. Ellis, Daniel Morozoff-Abegauz and Shih-Fu Chang
Structured Exploration of Who, What, When, and Where in Heterogenous Multimedia News Sources

paper:
http://dl.acm.org/ft_gateway.cfm?id=2508118&ftid=1406083&dwn=1&CFID=257526528&CFTOKEN=87000185

project page:
http://www.ee.columbia.edu/dvmm/newsrover/


Grand Challenge 2nd Place Award
-------------------------------
Subhabrata Bhattacharya, Behnaz Nojavanasghari, Tao Chen, Dong Liu, Shih-Fu Chang, Mubarak Shah
Towards a Comprehensive Computational Model for Aesthetic Assessment of Videos

http://dl.acm.org/ft_gateway.cfm?id=2508119&ftid=1406084&dwn=1&CFID=257526528&CFTOKEN=87000185

(joint work with the Computer Vision Lab of University of Central Florida)

June: Congratulations to DVMM members for winning awards at the 3rd Greater New York Area Workshop on Multimedia and Vision, June 14, 2013.

(Best Poster Award)
Felix Yu, Liangliang Cao, Rogerio Feris, John Smith, and Shih-Fu Chang, "Designing category-level attributes for discriminative visual recognition". (Joint work with IBM Research)

(Best Demo Award)
Brendan Jou, Hongzhi Li, Joseph G. Ellis, Daniel Morozoff, and Shih-Fu Chang, "News Rover: Exploring Topical Structures and Serendipity in Heterogeneous Multimedia News"

May: Congratulations to Wei Liu, who has received the 2013 Jury Thesis Award from the Department of Electrical Engineering for outstanding achievement by a graduate student in the areas of circuits, system, communication or signal processing. Wei's thesis is entitled "Large-Scale Machine Learning for Classification and Search". He is currently working in IBM T.J. Watson Research Center.

Mar.: DVMM Papers to appear in CVPR 2013

Hash Bit Selection: a Unified Solution for Selection Problems in Hashing
Xianglong Liu, Junfeng He, Bo Lang, Shih-Fu Chang

Designing Category-Level Attributes for Discriminative Visual Recognition
Felix Yu, Liangliang Cao, Rogerio Feris, John Smith, Shih-Fu Chang

A Bayesian Approach to Multimodal Visual Dictionary Learning
Go Irie, Dong Liu, Zhenguo Li, Shih-Fu Chang

Label Propagation from ImageNet to 3D Point Clouds
Yan Wang, Rongrong Ji, Shih-Fu Chang

Sample Specific Late Fusion for Visual Category Recognition
Dong Liu, Kuan-Ting Lai, Guangnan Ye, Ming-Syan Chen, Shih-Fu Chang

Robust Object Co-Detection
Xin Guo, Dong Liu, Brendan Jou, Mojun Zhu, Anni Cai, Shih-Fu Chang

Mar.: The IEEE has honored Prof. Shih-Fu Chang with the 2012 Signal Processing Society Technical Achievement Award for his "pioneering contributions to signal processing for multimedia content analysis and retrieval." The award honors a person who, over a period of years, has made outstanding technical contributions to theory and/or practice in technical areas within the scope of the Society, as demonstrated by publications, patents, or recognized impact on the field. The prize shall be $1500, a plaque and a certificate, and shall be presented at the Society's Awards Ceremonies, normally held during ICASSP in the Spring following selection of the winner.

2012

Nov.: DVMM group publishes a comprehensive survey paper on high-level event detection in video, in collaboration with the vision group of UCF. It includes more than 170 references and detailed discussion of features, event models, applications, and evaluation benchmarks.

Yu-Gang Jiang, Subhabrata Bhattacharya, Shih-Fu Chang, Mubarak Shah. High-Level Event Recognition in Unconstrained Videos. International Journal of Multimedia Information Retrieval, June 2013, Volume 2, Issue 2, pp 73-101. [pdf]

Nov.: Congratulations to DVMM alum Lexing Xie (faculty at Australian National University) whose group received Grand Challenge Award, and Winston Hsu (faculty at National Taiwan University) whose group received the Doctoral Symposium Best Paper Award at the 2012 ACM Multimedia Conference.

DVMM Alumni

Aug.: Prof. Chang co-edited a special issue on Web Scale Media Processing and Applications for Proceedings of the IEEE. (more)

Aug.: Prof. Chang co-directs the new NSF IGERT program on From Data to Solutions. (more)

June: DVMM team received a Magic Grant from the David and Helen Gurley Brown Institute for Media Innovation to develop Personalized Television News system (more).

Apr.: Wei Liu, one of the doctoral candidates at DVMM Laboratory, has been selected as the recipient of the IBM 2012 Josef Raviv Memorial Postdoctoral Fellowship. The fellowship was set up in memory of Dr. Josef Raviv, the founder and director of the IBM Research - Haifa Laboratory; it is awarded to a recent Ph.D. who shows exceptional promise for a research career in computer science or computer engineering. The winner of the fellowship can choose to work with any research group at IBM Research's labs around the world. Congratulations, Wei!

Apr.: Brendan Jou, one of the doctoral candidates at the DVMM Laboratory, has been awarded the prestigious NDSEG Fellowship. Only about 200 students out of 3000 applicants were selected this year. Brendan was also one of the recipients of the Wei Foundation Scholarship granted to graduate students of Chinese heritage at Columbia's Electrical Engineering Department. Congratulations, Brendan!

Apr.: DVMM Group to co-host the 2nd Multimedia and Vision Workshop in the Greater New York Region. [Poster]

Mar.: Prof. Chang has received the 2012 IEEE Signal Processing Society Meritorious Service Award, together with Dr. Li Deng of Microsoft for their "extraordinary service contributions and outstanding leadership of the IEEE Signal Processing Magazine." More details at http://www.signalprocessingsociety.org/awards-fellows/awardspage/meritorious-service/

2011

Dec.: Dr. Ching-Yung Lin has been selected for elevation to IEEE Fellow in recognition of his pioneering contributions to network science and multimedia security and retrieval. Dr. Lin graduated from the DVMM group in 2000 and is currently leading several large projects in social media networks in IBM T.J. Watson Research Center.

Dec.: The Active Query Sensing paper received the Best Paper Award at the prestigious ACM Multimedia Conference 2011 held in Scottsdale Arizona.

Felix X. Yu, Rong-Rong Ji, and Shih-Fu Chang, "Active Query Sensing for Mobile Location Search," ACM Multimedia, Scottsdale, AZ, USA, Nov. 2011.

Nov.: DVMM participated in the 2011 DARPA Shredder Challenge and ranked among the top five places among 9000 participating teams (more)

Oct.: Prof. Chang awarded the 2011 ACM SIGMM Technical Achievement Award (more)

Aug.: DVMM members will present the following papers and demos at the upcoming ACM Multimedia Conference 2011

Full Papers
Active Query Sensing for Mobile Location Search AbstractPDF
Towards Low Bit Rate Mobile Visual Search with Multiple-Channel Coding AbstractPDF

Demos
Mobile Product Search with Bag of Hash Bits
A Mobile Location Recognition System with Active View Suggestions AbstractPDF


May: Congratulations to Jun Wang, who has received the 2011 Jury Thesis Award from the Department of Electrical Engineering for outstanding achievement by a graduate student in the areas of system, communication or signal processing. Jun's thesis is entitled "Semi-Supervised Learning for Scalable and Robust Visual Search". He has joined IBM T.J. Watson Research Center in 2011.

Apr.: Congratulations to Wei Liu who was just selected to receive the 2011 Facebook Fellowship. Wei's research area is machine learning with applications in large scale image tagging and retrieval.

Official news can be found here.

Five winners were chosen from hundreds of applicants. Each will receive full payment for their tuition, as well as a $30,000 stipend, $5,000 for travel, and $2,500 for a personal computer.

Jan.: Prof. Chang elected as Fellow of AAAS (more).

2010

Nov.: Congratulations to Dr. Qibin Sun who has just been elevated to IEEE Fellow in recognition of his "contributions to multimedia security". Dr. Sun worked in the DVMM Lab as a research scientist from 2000 to 2001.

Nov.: Columbia DVMM Lab took part in the Multimedia Event Detection (MED) task organized by NIST as part of the TRECVID 2010 video retrieval benchmark event. In collaboration with the LABROSA lab of Columbia University and the computer vision group of UCF, the team developed new approaches to detect semantic events in user-generated videos that involve objects, activities, and dynamic evolutions over time (e.g., batting a run in baseball; assembling a shelter). Columbia's approaches archived the top performance by integrating multiple modalities (audio visual), context fusion, and temporal matching. More details can be found in the paper.

Oct.: The DVMM group takes part in two large team projects on video retrieval and analysis funded by DARPA and another one on forensics sciences funded by Department of Justice.
One DARPA project, PerSEAS (Persistent Stare Exploitation and Analysis System), in collaboration with several companies and universities, aims at developing innovative research in the area of airborne, wide area motion imagery processing, analysis, and exploitation. The second DARPA project, VIRAT (Video Image Retrieval and Analysis Tool), aims at development of a database that could store large quantities of video, and make it easily searchable by intelligence agents to find video content of interest.
The three-year project funded by Department of Justice will develop a science base and open source software for bloodstain pattern analysis. It is a joint project in collaboration with Prof. Daniel Attinger (PI) of Mechanical Engineering and Prof. Marc Spiegelman of APAM and Earth and Environmental Sciences.

Oct.: Prof. Chang recently gave keynote talks at IEEE International Conference on Semantic Computing (ICSC 2010) hosted at CMU, and Workshop for Emerging Leaders in Multimedia hosted by IBM Watson Research Center. He also visited Boston University to give a distinguished lecture at the Electrical and Computer Engineering Department.

May: DVMM PhD student, Jun Wang, just won the 2009 Chinese Government Award for Outstanding Self-Financed Students Abroad. The scholarship, carrying a $5,000 prize and a certificate, was set up by China Scholarship Council to honor students with outstanding academic accomplishment. There are a total of 23 students receiving this award from 10 states of the east coast in the USA covering all academic fields.
Jun Wang is working on machine learning and multimedia in the Digital Video and Multimedia Lab, directed by Prof. Shih-Fu Chang. Jun has already won numerous awards (including Goggle Global Intern Scholarship 2009, IBM Watson Emerging Leader in Multimedia 2009) and has authored or coauthored papers published in ACMMM, ICML, CVPR, ICCV, Proteomics, and Biomedical Informatics.

Mar.: The premier ACM Multimedia Conference will be held this year in the attractive location, Florence Italy, from Oct 25 to 29 of 2010. Prof. Chang, together with Prof. Alberto del Bimbo, will co-chair this exciting event.

2009

Dec: DVMM Lab wins 3-year ONR Research Grant. The sponsored project will develop new representations and machine learning techniques for target recognition and multimedia search. Our goal is to harness the synergistic powers of graph-based representations and semi-supervised learning to develop robust, efficient, and scalable solutions suitable for applications critical for Naval operations, such as rapid target annotation, information triage, and multimedia retrieval from hybrid, unreliable sources.

Oct: Congratulations to DVMM members Jun Wang and Yu-Gang Jiang for being selected as IBM Watson Emerging Leaders in Multimedia 2009. The awardees, selected from a large pool of nominees, were highlighted in a two-day workshop presenting the state of art and trend of multimedia research. Jun Wang also won the Best Presentation Award in this prominent event.

Sep: Congratulations to EE PhD student, Jun Wang, who has just been selected to receive the Google Global Intern Scholarship. The scholarship recipients will each receive a USD $10,000 award for the 2009-2010 academic year. The recipients are selected from the 2009 Google interns worldwide after a comprehensive review process which takes into consideration academic, internship and leadership accomplishments. Jun Wang is currently working with Prof. Shih-Fu Chang at Columbia University on research of image search, machine learning, and hybrid neural-computer vision systems. He worked as an intern in Google Research in NYC in the summer of 2009. 

Aug: Prof. Chang gave a keynote speech at International Conference on Multimedia and Exhibition (ICME) New York, July 2009. The title of his talk is "Image/Video Classification and Search: Addressing Semantic Gap and User Gap".

Aug: Congratulations to Wei Jiang for having her paper included in the best paper session at ACM Multimedia 2009, a prestigious conference with a 18% acceptance rate. The work has been in collaboration with Courtenay Cotton and Prof. Dan Ellis of LabROSA of Columbia University and Dr. Alex Loui of Kodak Research Lab.

Aug: The DVMM group hosted a farewell lunch for Xavier Giro and Eric Liu, who were returning to Technical University of Catalonia Spain and USTC China after three-month and one-year visits to the DVMM lab. We wish Xavier and Eric continuing success in future research (group pic after the farewell lunch: 1 2).

April: Congratulations to DVMM Alumnus, Prof. Hari Sundaram, who has just received tenure at Arizona State University, where he is affiliated with the department of Computer science and the Arts Media and Engineering program (AME). Research activities of his group can be found at http://ame2.asu.edu/faculty/hs/ .

Jan: Congratulations to Lyndon Kennedy for completing his PhD thesis, entitled "Advanced Techniques for Multimedia Search: Leveraging Cues from Content and Structure".  He will join Yahoo! Research and starting working in Jan 2009 (group pic after the farewell lunch).

Jan: Congratulations to DVMM Alumnus Prof. Winston Hsu for leading an expanding group, with more than 10 graduate students, working on multimedia information retrieval in National Taiwan University. His group has also won Microsoft Research Faculty Grant and Fellowship recently.

2008

Nov: Prof. Chang delivered a keynote talk on the topic of Interactive Visual Search at ACM International Conference on Multimedia Information Retrieval (MIR). His talk highlighted a recent search engine, CuZero, co-developed by doctoral candidate Eric Zavesky. Prof. Chang also gave a talk on Recent Advance in Image/Video Search in the Distinguished Lecture Series at the College of Computing and Informatics, the University of North Carolina - Charlotte.

Oct: Congratulations to DVMM student member Wei Jiang for being selected as one of the IBM Watson Emerging Leaders in Multimedia 2008. The awardees, selected from a large pool of nominees, are highlighted in a two-day workshop discussing state of art and trend of multimedia research. Wei has been supported and recognized as a Kodak Research Fellow.

Oct: The DVMM group hosted a farewell lunch for Xavier Giro, who was returning to Technical University of Catalonia as an Assistant Professor after a 6-month visit to the DVMM lab. We wish Xavier continuing success in his future endeavors (group pic after this activity).

July: Congratulations to Eric Zavesky, Prof. Shih-Fu Chang, and Cheng-Chih Yang, for winning the Best Paper Award at ACM International Conference on Image and Video Retrieval, held in Niagara Fall, Canada in July 2008. The paper is entitled "Visual Islands: Intuitive Browsing of Visual Search Results"

May: Congratulations to Eric and Wei Jiang for receiving the Millman Outstanding TA Award in 2008. The awards are given by the Department each year to two students for their outstanding performance and contributions as Teaching Assistant. The list of awards of previous years is here.

April: Congratulations to Junfeng He, Wei Liu, Jun Wang, and Dong Xu.  Each has a paper accepted for publication in the upcoming IEEE Computer Vision and Pattern Recognition (CVPR) conference. Papers may be downloaded from link DVMM paper site year 2008. Also congratulations to Jun for having his new work on transductive graph-based learning accepted for publication in International Conference on Machine Learning (ICML).

March: Columbia DVMM lab is pleased to release a software program for detecting near-duplicate images for image/video retrieval applications. Please visit the link for the download instructions.

2007

Oct: Congratulations to DVMM Ph.D. student Lyndon Kennedy for being selected as one of the IBM Watson Emerging Leaders in Multimedia 2007. The awardees, selected from a large pool of nominees, are highlighted in a two-day workshop discussing state of art and trend of multimedia research.

June: Prof. Chang gave a keynote speech at International Workshop on Image Analysis for Multimedia Interactive Services, Greece , June 2007. The title of his talk is "Advances and Open Issues for Digital Image/Video Search".

2006

Nov: Congratulations to Winston Hsu for successfully completing the PhD defense exams! He has joined National Taiwan University as an Assistant Professor in the Department of Computer and Information Science Engineering.

Nov: Congratulations to Dr. John R. Smith, a DVMM alumnus, for being elected to IEEE Fellow with citation - for contributions to multimedia content analysis, retrieval and adaptation.

Oct: Congratulations to Winston Hsu and Lyndon Kennedy for having their paper included in the best paper session at ACM Multimedia 2006, a prestigious conference with a 16% acceptance rate. Only one paper from the content track receives such recognition this year.

2005

Nov: Hearty congratulations to Tian-Tsong, Jessie, and Lexing for receiving the Best Student Paper Award at the prestigious ACM Multimedia Conference 2005! Three top student papers were chosen from the accepted pool and the final winner was selected after the on-site presentation.

Oct: Prof. Shih-Fu Chang has been selected as the new Editor in Chief for the IEEE Signal Processing Magazine, for the duration of 2006-8.

Oct: Congratulations to Lexing for receiving the prestigious IBM Research Josef Raviv Memorial Postdoctoral Fellowship, given to only one recipient selected from more than 30 outstanding applicants.

Oct: Congratulations to Shahram, Lexing, Yong, and Dongqing for their successfully completing the PhD defense exams! Shahram and Lexing have joined IBM T.J. Watson Research Center . Yong has started working at Motorola Research and Dongqing is joining Thomson Research in Burbank CA .

2004

Oct: Dongqing Zhang and Jessie Hsu are selected as the outstanding TAs respectively for Spring 03 and Spring 04.

Sept: Farewell and best wishes to research scientist, Masami Mizutani of Fujitsu Labs

Sept: Lexing Xie winning the IBM Student Paper Award in the ICIP 2004 conference.Despite the high competitiveness of the award, Lexing's paper emerged as one of the top 3 papers in the ICIP 2004 conference. The details of the paper is as below: "Discovering Meaningful Multimedia Patterns with Audio-Visual Concepts and Associated Text," Lexing Xie, L. Kennedy, S.-F. Chang, A.Divakaran, H. Sun and C.-Y. Lin.

July: Welcoming Visiting Scientist, Dr. Jinwoong Kim, from Electronics and Telecommunications Research Institute (ETRI), Korea. Our great honor to have Dr. Jinwoong Kim visiting our research group. Dr. Kim is currently the director of the Broadcast Media Research Group in ETRI, Korea.

May: Welcoming Visiting Scientist, Dr. Hyun Lim, from Mokpo National University, Korea. It is our pleasure to have Dr. Hyun Lim joining us. Dr. Lim's research interests include image protection and authentication using digital watermarking technique, and FPGA implementation of image processing algorithm. 

Feb: Lexing was among the outstanding TAs in the school of Engineering and Applied Science for the fun in deciphering papers and discussing problems in multimedia analysis during Fall 2003 EE6882 Statistical Methods for Video Indexing and Analysis. 

2003

Dec: Prof. Chang Elected IEEE Fellow. Our hearty congratulations on Prof. Chang's being elected to IEEE Class of 2004 Fellows for his "contributions to digital video and multimedia technologies". The DVMM group looks forward to more exciting research under his outstanding leardership.

Sept: Welcoming Naoko Nitta and Masami Mizutani. We are most pleased to have Naoko Nitta and Masami Mizutani to join DVMM as visiting scientists, following Masaki Miura and Ryoma Oami who have just completed their research attachment with DVMM recently. Naoko Nitta is from the reputed Osaka University of Japan while Masami Mizutani is a researcher in Fujitsu Laboratory, Japan. We wish them a pleasant stay in New York .

Aug: Farewell to Visiting Scientist Ryoma Oami. Ryoma Oami, a visiting scientist for NEC Japan, has completed his one-year research attachment with DVMM Lab. We had a farewell lunch for him in Tomo Japanese restaurant before his departure. Photos and videos are taken during the event.

July: Masaki Miura Returning to Japan . Masaki Miura just finished his 1-year visiting research with DVMM Lab and will return to Fujitsu Lab Japan . His stay has been very productive and enjoyable -- we miss his Japanese lessons! He participates in the video surveillance mining project and has conducted extensive experiments in face detection and tracking. We wish him continuing success in his career!

For the photos and videos taken during the farewell lunch with Masaki, please visit the event page.

June: Ana and Shahram Won Prizes in IBM Watson Workshop on Multimedia. Congratulations to Ana and Shahram for winning the best student poster presentations at the IBM Watson Workshop on Multimedia, held on June 20 2003. Ana's project on IMKA, constructing multimedia knowledge network, was awarded the first prize. Shahram's work on echocardiogram video indexing and summarization won the 2nd prize.

Dr. Ching-Ying Lin Won Young Author Paper Award 2003

Great news from DVMM alumnus, Dr. Ching-Yung Lin. His paper on semi-fragile authentication watermarking published in IEEE TCSVT has been selected to be the winner of the IEEE Circuits and Systems Society 2003 Young Author Paper Award.

Best wishes to recent DVMM graduates. Congratulations, Dr. Hari Sundaram and Dr. Alex Jaimes!

Hari Sundaram has started his tenure-track faculty position at Arizona State University , with Department of Computer Science and Institute for Studies in the Arts. He is working on several fantastic projects related to the Media and Arts Center .

Alex Jaimes is joining FujiXerox Research near Tokyo after his exciting travel over south America and a productive mini-postdoc at U. de Chile.

2002

Oct: DVMM members, Hari Sundaram and Lexing Xie received the ACM Multimedia Conference Best Student Paper Award for their paper entitled “A Utility Framework for the Automatic Generation of Audio-Visual Skims?co-authored with Prof. Shih-Fu Chang) in France. This is a very selective conference with a paper acceptance rate of 16%. Hari and Lexing deserve the recognition of the fruit of their hard work and passionate dedication to research. 

Mar: Raj Kumar has won the 2nd Prize Best Paper Award at the IEEE Sarnoff Symposium with a $500 cash prize! His paper, co-authored with Prof. Chang and Dr. Mihaela van der Schaar is entitled“FGS+: Optimizing the Joint SNR-Temporal Video Quality in MPEG-4 Fine Grained Scalable Coding".

Others

Jury Award for Best Thesis

Over the years, several DVMM alumni have received the Jury Award for Best Thesis in Communications, Signal Processing and Systems from the Department of Electrical Engineering at Columbia University . This has set an inspirational and chllalenging tradition for future DVMMers.

John R. Smith (1997) with thesis entitled“Integrated Spatial and Feature Image Systems: Retrieval, Compression and Analysis"

Di Zhong (2000) with thesis entitled "Segmentation, Index and Summarization of Digital Video Content"

Hari Sundaram (2002) with thesis entitled "Segmentation, Structure Detection and Summarization of Multimedia Sequences"

Error: News not found.

 

bar

For problems or questions regarding this web site contact The Web Master.