Social networks and multimedia content sharing websites have become increasingly popular in recent years. Their service typically focuses on building online communities of people who interact with each other by sharing their own interests or activities, and exploring shared content of others. Such social networks have become a popular way to disseminate different type of information, such as photo, video, text, and audio. For example, a user uploads his/her wedding album to let other people from the online community comment or rate the photos. This sharing trend has resulted in a continuously growing volume of publicly available multimedia content on content sharing websites like Flickr, Picasa, Photobucket and YouTube, as well as social networks like Facebook and Google+. For instance, Photobucket hosts more than 8 billion photos, compared to 7 billion photos on Picasa and 6 billion photos on Flickr. Facebook has more than 250 million photos posted to its network every day and approximately 100 billion photos stored on its servers, while 3.4 billion photos have been uploaded to Google+ in the first 100 days of it being open to the public. Every minute, 48 hours of video are uploaded to YouTube, and 20 million videos are uploaded to Facebook every month. This large volume of multimedia content poses significant challenges for efficient search, retrieval and processing of the shared content. These new challenges call for novel solutions to create and share knowledge with consideration of social context, new models of collective and social computing, new ways to analyze how users learn from each other as well as from past experiences, new mechanisms to leverage the specific abilities of massive human participants, etc. By tackling some of these challenges, our group has provided significant contribution to social media research community.
- Object Duplicate Detection
- Tag Propagation
- Trust Modeling in Social Media Tagging
- Photo Album Summarization