SPECIAL SESSION, ACM ICIMCS 2011, CHENGDU, CHINA
Special Session
  
Co-Chairs
Tao Mei, Microsoft Research Asia
Jinhui Tang, Nanjing University of Science and Technology, China
Zheng-Jun Zha, National University of Singapore, Singapore
Session 1: Web-Scale Social Media Data Mining
Organizer:

Richang Hong, Hefei University of Technology, China   Email: hongrc@hfut.edu.cn

Meng Wang, National University of Singapore, Singapore   Email: mengwang@comp.nus.edu.sg

Lingyu Duan, Peking University, China   Email: lingyu@pku.edu.cn

 
Today, increasingly rich and massive social media data (such as texts, images, audios, videos, blogs, etc.) are being posted to the web, including social networking websites (e.g., MySpace, Facebook), photo and video sharing websites (e.g., Flickr, YouTube), and photo forums (e.g., Photosig.com and Photo.net).  The proliferation of such sites have produced a new type of multimedia content, termed as “social media” here as it is created by people using highly accessible and scalable publishing technologies for sharing via the web. The intrinsic attributes of social media is to facilitate interactive information sharing, interoperability and collaboration on the internet. By virtue of that, web images, videos and audios are generally accompanied by user-contributed contextual information such as, tag, category, title, metadata, comments, and viewer ratings, etc. Massive emerging social media data offer new opportunities for resolving the long-standing challenges such as how can we build video indexing and search benefit from the shared videos and other metadata? Furthermore, this new media also introduces many challenging and new research problems and many exciting real-world applications (e.g. social image search, social group recommendation, etc.).
The special session seeks for original contribution of works which addresses the challenges from social media mining.  Submissions are highly encouraged to use the web image data set of NUS-WIDE (created by Lab for media search, National University of Singapore. There have been more than 75 citations on this work, see: http://lms.comp.nus.edu.sg/research/NUS-WIDE.htm). Submissions working on other Internet-based datasets are also welcome. The list of possible topics includes, but not limited to:
Social context-based media content analysis
Web driven media creation
Collaborative filtering and recommendation systems for social media
Organization, indexing and navigation of multimedia content
Interactive/collaborative image, video and audio search in web environment
Machine learning and data mining methods for social media content
Large scale image, video and audio classification using social contextual cues
Image, video and audio recommendation in social networks
Online social media-based advertising
Near-duplicate and copy detection
Privacy and security issues in social media (e.g. media watermarking)
Session 2: Web-Scale Media Search and Management
Organizer:

Jialie Shen, School of Information Systems, Singapore Management University, Singapore  Email: jlshen@smu.edu.sg

Frank Hopfgartner, International Computer Science Institute, Berkeley CA, USA  Email: fh@icsi.berkeley.edu

Yan-Tao Zheng, Institute for Infocomm Research, A*STAR, Singapore  Email: yantaozheng@gmail.com


Nowadays, more and more amount of media content is shared on social media websites such as YouTube, Flickr or Facebook. The social web portals have brought about a fundamental change in the way how users generate, consume and analyze the media data. Meanwhile, comparing to traditional multimedia data, they generally consists of text and multimedia data, enriched with additional data (annotations, comments, tags, etc.). In addition, semantic relationships between content and content sharers can be inferred by considering the structure of the social content sharing websites. However, this social factor has hardly been studied in the information retrieval and recommendation research domain. This special session aims at state-of-the-art research approaches that address the underlying social structure for retrieval and filtering of multimedia content.
The special session invites unpublished, original research relating to media data management and search. It specifically seeks the most leading-edge research that creates and evaluates innovative web scale media search and mining, and data management techniques in the social web. The special session is positioned as a unique place enabling researchers from academia and industrial firms to exchange recent technical development. The list of possible topics includes, but not limited to: 
Web scale media information management
Media knowledge discovery
Privacy and security issues in media data management
Media recommendation systems
Performance evaluation of media search engine
Media retrieval algorithm design
Multimodal Analysis for Retrieval Applications
Data structure and algorithm design for scalability improvement Personalization
Information visualization for data management
Cloud computing platform for large scale of media data management
Emerging Trends on Web Scale Media Search (e.g., social media and e-learning)
Economic value of media search and management