Conventional approaches to video annotation predominantly focus on supervised identification of a limited set of concepts, while unsupervised annotation with infinite vocabulary...
Emily Moxley, Tao Mei, Xian-Sheng Hua, Wei-Ying Ma...
Text-based search using video speech transcripts is a popular approach for granular video retrieval at the shot or story level. However, misalignment of speech and visual tracks, ...
We present methods for improving text search retrieval of visual multimedia content by applying a set of visual models of semantic concepts from a lexicon of concepts deemed relev...
Alexander Haubold, Apostol Natsev, Milind R. Napha...
Pattern mining algorithms are often much easier applied than quantitatively assessed. In this paper we address the pattern evaluation problem by looking at both the capability of ...
We present a three-step post-processing method for increasing the precision of video shot labels in the domain of television news. First, we demonstrate that news shot sequences c...