The problem of joint modeling the text and image components of multimedia documents is studied. The text component is represented as a sample from a hidden topic model, learned wi...
Nikhil Rasiwasia, Jose Costa Pereira, Emanuele Cov...
Joke-o-mat HD is a system that allows a user to navigate sitcoms (such as Seinfeld) by "narrative themes", including scenes, punchlines, and dialog segments. The themes ...
While there have been research efforts in organizing largescale web videos into topics, efficient browsing of web video topics remains a challenging problem not yet addressed. The...
Juan Cao, Chong-Wah Ngo, Yongdong Zhang, Dongming ...
This paper proposes a new framework to formulate the problem of rushes video summarization as an unsupervised learning problem. We pose the problem of video summarization as one o...
Yang Liu, Feng Zhou, Wei Liu, Fernando De la Torre...
In today's age of digital multimedia deluge, a clear understanding of the dynamics of online communities is capital. Users have abandoned their role of passive consumers and ...
Radu Andrei Negoescu, Alexander C. Loui, Daniel Ga...