One of the first steps towards understanding natural multimodal language is aligning gesture and speech, so that the appropriate gestures ground referential pronouns in the speech...
Semantic role labeling (SRL) is an important module of spoken language understanding systems. This work extends the standard evaluation metrics for joint dependency parsing and SR...
Quantization plays a central role in data compression. In speech systems, vector quantizers are used to compress speech parameters. In video systems, scalar quantizers are used to...
Salman Aslam, Aaron F. Bobick, Christopher F. Barn...
Collection understanding shifts the traditional focus of retrieval in large collections from locating specific artifacts to gaining a comprehensive view of the collection. Visuali...
Michelle Chang, John J. Leggett, Richard Furuta, A...
ABSTRACT. In this paper, illocutionary acts of commanding will be differentiated from perlocutionary acts that affect preferences of addressees in a new dynamic logic which combine...