132 search results - page 14 / 27 » Harmonium Models for Semantic Video Representation and Class... |
WSDM
2010
ACM
15 years 6 months ago
2010
ACM
We describe an approach for multi-modal characterization of social media by combining text features (e.g. tags as a prominent example of short, unstructured text labels) with spat...
ECCV
2008
Springer
15 years 11 months ago
2008
Springer
Abstract. This paper presents a novel framework for detecting abnormal pedestrian and vehicle behaviour by modelling cross-correlation among different co-occurring objects both loc...
NIPS
2004
14 years 10 months ago
2004
Statistical approaches to language learning typically focus on either short-range syntactic dependencies or long-range semantic dependencies between words. We present a generative...
IJIS
2008
14 years 9 months ago
2008
The ability to analyse and represent formally semantic relations of terms is a core issue in information retrieval (IR), natural language processing (NLP), and in many related are...
MM
2004
ACM
15 years 2 months ago
2004
ACM
Motion information is a powerful cue for visual perception. In the context of video indexing and retrieval, motion content serves as a useful source for compact video representati...