Vision and Objectives

NExT stands for NUS-Tsinghua Centre for Extreme Search, a leading research centre jointly established by the National University of Singapore (NUS) and Tsinghua University of China, funded by IDMPO (Interactive Digital Multimedia Program Office) under MDA (Media Development Authority). NExT conducts research in the areas of large-scale live social media content analysis and search, including live event detections, information organization, and the generation of live, multimedia and multilingual analytics for corporations, people, events and locations. The Centre commences in July 2010.

The vision of the Centre is to automatically gather, organize, search and track live, multimedia, multi-source and multilingual social media data and events, currently not available on the traditional Web. Such social media data is available in a myriad of sources, including live microblog sites like twitter; mobile sharing sites like 4Square and Instagram; information sharing sites like forums and blogs; image and video sharing sites like Flickr and YouTube; and the various community question-answering sites like Wiki-Answers and Yahoo!Answers; as well as their counterparts in China. These mostly publicly available data sources are collectively known as the user-generated contents or UGCs. They document the social interactions of people, and can be analyzed to uncover the social activities of and relationships between people, and their collective preferences and habits.

To analyse and fuse these UGCs, we need techniques to deal with the huge amount of real-time, multimedia and multimedia data. In addition we need to tackle the social aspects of these contents, such as the user relations, communities, and influential users with respect to any organization or topic. Key research areas of NExT include: (a) reliable strategies for harvesting representative UGCs; (b) indexing and retrieval of huge media resources arising from these media; (c) organization of unstructured UGCs and users on any topic into structured knowledge and user communities; (d) fusion of UGCs to generate analytics related to location, people, topic and organization; (e) live video event capturing and sharing; (f) differential news; (g) extreme database support; and (h) basic research on the analysis and retrieval of text, live discussion streams, images and videos.

Overall, the unique capability of NExT is its research on live, big, multi-source and multilingual UGC data.

The Centre will work closely with other MDA-funded Centres to jointly research into cyber physical systems (with SeSaMe), and language and translation technologies (with CSIDM), as well as with various start‐up companies and government agencies to deploy and transfer technologies. The Center will also work towards the sharing of derived analytics, as well as the related information processing tools.

The research in the Centre is organized into following six mutually supporting topics.

Topic 1: Live Social Observatory

Topic 2: Live City

Topic 3: Live Text Search

Topic 4: Live Video Processing

Topic 5: Live Video Event Capturing and Sharing

Topic 6: Extreme Database

Overview Paper:

[1] Tat-Seng Chua, Huanbo Luan, Maosong Sun, Shiqiang Yang: NExT: NUS-Tsinghua Center for Extreme Search of User-Generated Content. IEEE MultiMedia, 19(3): 81-87 (2012)