Contact
| |
|
|
]
(
Short Bio
Dr. Winston Hsu is an active researcher dedicated to novel algorithms and systems for large-scale image/video retrieval, social media mining/ recommendation, multimedia analytics, and mobile and cloud-based multimedia applications. He has been recognized with technical awards and best paper awards in multimedia research community. He is keen to realizing advanced researches towards business deliverables. Other major contributions include mobile visual search solutions, image/video reranking, image classification models (e.g., Columbia374), and large-scale multimedia ontologies (e.g., LSCOM). See more deatails in his Google Citations. He delivered keynote speech and lectured several state-of-the-art tutorials in top conferences. He is in the technical committee for top conferences (e.g., ACM Multimedia, SIGIR, and WWW) and the organizing committee for ACM Multimedia and ICME. He is on the Editorial Board for IEEE Multimedia Magazine and JMM. He is an Associate Professor in CSIE & GINM, National Taiwan University and the founder of MiRA (Multimedia indexing, Retrieval, and Analysis) Research Group, in Communication and Multimedia Lab (CMLab). He received his Ph.D. (2007) degree from Columbia University, New York, under the supervision of Prof. Shih-Fu Chang. Before that, he worked for years as a founding engineer in the multimedia software company, CyberLink Corp., where experiencing Engineer, Project Leader, and R&D Manager. He was experienced with software product/service shipping processes. He is recently awarded 2011 Ta-You Wu Memorial Award, a national and prestigious recognition for young researchers. See more details in his CV.
Research Focus
The prevalence of capture devices and the advent of media-sharing services have drastically increased the sheer amount of image and video collections. Here arise the strong needs for effective multimedia analysis and efficient multimedia retrieval. We have been devoted to large-scale photo and video retrieval, knowledge discovery from large-scale social media mining, distributed computation for multimedia analysis and retrieval, and devised novel multimedia applications in mobile devices.
Though having observed very exciting applications in large-scale multimedia analysis and retrieval, we further identify certain core challenges and respond to them respectively:
- Sematic gap – bridging the low-level visual features to satisfy semantic needs by proposing semantic ontology and learning semantic representations in an automatic manner;
- User gap – helping users issue proper queries to satisfy their intensions in different application scenarios and mobile devices (e.g., by sketch, attribute, snapshot, speech, and touch-based);
- Volume gap – learning ultra-large-scale photos and videos by distributed computation and efficient high-dimensional indexing (e.g., hash-based methods) for real-time query response over big photo/video data;
- Privacy – conducting privacy-preserving mining for large-scale photos and videos and addressing the privacy concerns as sharing sensitive photos and videos (e.g., family albums) in the public clouds.
- Industry needs – besides thorough algorithms for academic researches, we also investigate practical methods for meeting possible needs in industrial developments (e.g., technology transfer).
Recruiting
We keep recruiting
graduate students
(master or PhD) for the exciting projects
of both great theoretical interests and strong industrial
demands. Students have delivered brilliant results. See our news or publication
sections for more details.
- Several image/video/audio retrieval projects are also good for undergraduate students.
Why having research projects in MiRA group? for CSIE
undergraduates and PhD students. Some
quick demos:
- Effective and efficient product query by mobile phone
- Interactive video (Question and Answering)
- Realtime image retrieval over million-scale image
collections
- Million-scale image graph construction and clustering by
cloud computation (MapReduce over 18 Hadoop servers).
- Flora Project: Flower Retrieval and Social Network
- Multimodal Fusion for Mobile Annotation – GPS, Compass, or
Camera
- Indexing million-scale faces in sub-second response
- Real-time video retrieval and mobile question and answering
News!!
- Congratulations for receiving the resarch award in 2012 Microsoft Research Asia Windows Phone Theme Program
- Congratulations to "people team" for the work, Where is Who: Large-Scale Photo Retrieval by Facial Attributes and Canvas Layout, accepted for SIGIR 2012 (FULL paper, 89/483 ~= 20%) .
- Prof. Hsu has an invited demo in Cloud Futures 2012, Berkeley, California, May 7-8, 2012.
- Prof. Hsu has an invited talk in The Second Multimedia and Vision Meeting in Greater New York Area, Columbia University, New York, June 15, 2012.
- Prof. Hsu has an invited talk in AI Forum, Kaohsiung, Taiwan, May 12, 2012.
- Prof. Hsu had an invited talk in Digital Media Analysis, Search and Management DMASM 2012 International Workshop, San Diego, Feb. 27-28, 2012.
- Congratulations to Kuo, Yin-Hsi for her work, Unsupervised Semantic Feature Discovery for Image Object Retrieval and Tag Refinement, accepted for IEEE Transactions on Multimedia 2012.
- Congratulations for cloud-based photo management system
winning the 2nd Prize
(with 180,000 NTD cash award)
in Chunghwa Telecom Innovation Awards (2011
電信創新應用大賽雲端應用校園組亞軍)
- We won the prestigious award, First
Prize in ACM Multimedia Grand Challenge 2011 for
the project -- "Photo Search by Face Positions and Facial
Attributes on Touch Devices"
- Congratulations to Prof. Hsu for receiving 2011
(NSC) Ta-You Wu Memorial Award (國科會100年度吳大猷先生紀念獎),
the most prestigious Taiwan government award for young
researchers
- Congratulations to the group for having one FULL paper, three SHORT papers, three Grand Challenge posters, and one workshop paper, accepted for ACM Multimedia 2011
- Congratulations to Wen-yu and Yen-ta for having two short papers accepted for SIGIR 2011 and Wen-yu for receiving "Google Travel Grants for SIGIR 2011"
- Congratulations to Chen, Yan-Ying for receiving "WWW 2011 Google Fellowship for Women"
- Congratulations to Kuo, Yin-Hsi for our first
work accepted for CVPR 2011 -- "Unsupervised Auxiliary Visual
Words Discovery for Large-Scale Image Object Retrieval"
- Congratulations to Yu-Ming Hsu and Yen-Liang Lin for winning the Best Paper Award in The 17th International Conference on Multimedia Modeling (MMM) 2011 for the paper "Snap2Read: Automatic Magazine Capturing and Analysis for Adaptive Mobile Reading."
- Congratulations to students for winning the FIRST Prize
(with 300,000 NTD cash award) for their Flora Project (joint work with Prof. Mike Chen), sponsored by Chunghwa Telecom, Taiwan; the theme
"Mobile + Flower Retrieval + Social Network." See the demo.
- ... more
