Multimedia Content Analysis and Retrieval

Video Structuring and Semantic Modeling

We work on algorithm designing and system development for large-scale video (news, sports, movies, etc.) content analysis and management.

Representative Publications:

  • Anan Liu*, Zhaoxuan Yang, "Watching, Thinking, Reacting: A Human-Centered Framework for Movie Content Analysis", JDCTA: International Journal of Digital Content Technology and its Applications, Vol. 4, No. 5, pp. 23~37, 2010.

  • Anan Liu*, Yongdong Zhang, Jintao Li, “Personalized Movie Recommendation”, ACM Multimedia 2009. (Student Participation Grant).

  • Anan Liu*, Jinhao Fei, Jianping Fan, et al., “Confusion Network Based Video OCR Post-processing Approach,” Proc. of ICME 2009, Mexico (Oral).

  • Anan Liu*, Sheng Tang, Yongdong Zhang, et al., “A Hierarchical Framework for Movie Content Analysis: Let Computers Watch Films like Humans,” Proc. of CVPR2008 Workshop on Semantic Learning Applications in Multimedia (SLAM2008), America (Oral).

  • Anan Liu*, Yongdong Zhang, Yan Song, et al., “Human Attention Model for Semantic Scene Analysis in Movies,” Proc. of ICME 2008, Germany.

  • Anan Liu*, Jintao Li, Yongdong Zhang, et al., “An Innovative Model of Tempo and Its Application in Action Scene Detection for Movie Analysis,” Proc. of IEEE Workshop on Applications of Computer Vision (WACV2008), IEEE Winter Vision Meeting, Jan 7-9, America.

  • Location based Social Network

    The dimension of location brings social networks back to reality, bridging the gap between the physical world and online social networking services. Location-based social network (LBSN) does not only mean adding a location to an existing social network so that people in the social structure can share location-embedded information, but also consists of the new social structure made up of individuals connected by the interdependency derived from their locations in the physical world as well as their location-tagged media content, such as photos, video, and texts. Here, the physical location consists of the instant location of an individual at a given timestamp and the location history that an individual has accumulated in a certain period. Further, the interdependency includes not only that two persons co-occur in the same physical location or share similar location histories but also the knowledge.

    Representative Publications:

  • Venue Semantics: Multimedia Topic Modeling of Social Media Contents. Nie Weizhi, Wang Xiangyu, Zhao Yiliang, Gao Yue, Su Yuting, Chua Tat-Seng. Pacific-Rim Conference on Multimedia (PCM) 2013.