This paper considers dynamic language model adaptation for Mandarin broadcast news recognition. Both contemporary newswire texts and in-domain automatic transcripts were exploited...
The method based on local features has an advantage that the important local motion feature is represented as bag-of-features, but lacks the location information. Additionally, in ...
This paper presents Latent Semantic Googling, a variant of Landauer’s Latent Semantic Indexing that uses the Google search engine to judge the semantic closeness of sets of word...
We propose a new method for human action recognition from video sequences using latent topic models. Video sequences are represented by a novel “bag-of-words” representation, w...