Concept-Based Video Retrieval
Concept-Based Video Retrieval reviews 300 references on video retrieval, indicating when the text-only solutions of present-day video search engines are unsatisfactory and showing the promising alternatives which are primarily concept-based. Central to the discussion, therefore, is the fundamental notion of a semantic concept: an objective linguistic description of an observable entity. The book aims to motivate and explain how automated detection, selection under uncertainty, and interactive usage might solve the major scientific problems for video retrieval: the semantic gap. In striving to bridge this gap, the authors structured their review by laying down the anatomy of a concept-based video search engine. They present a component-wise decomposition and evaluation of such an interdisciplinary multimedia system, covering influences from information retrieval, computer vision, machine learning, and human-computer interaction. Concept-Based Video Retrieval is aimed primarily at researchers and developers in the broad area of information retrieval. It will also be an invaluable reference for students in computer and information science at the (post)graduate level, as well as industrial practitioners
What people are saying - Write a review
We haven't found any reviews in the usual places.
Using Concept Detectors for Video Search
A. G. Hauptmann ACM International Conference active learning algorithms annotation eﬀorts approach automatic search task benchmark tasks broadcast color computer vision concept annotation concept detection task concept detectors concept-based video retrieval Conference on Multimedia cycle deﬁned deﬁnition diﬀerent diﬃcult eﬀective eﬃcient evaluation exploit feature extraction feature fusion feature vector ﬁeld ﬁnd ﬁrst histograms human–computer interaction IEEE Transactions image retrieval inﬂuence Information Retrieval interactive search task J. R. Smith key frame keypoint labeled examples machine learning NIST oﬀer ontology optimal parameters performance Proceedings query classes query methods query prediction relevant rely robust scheme search topics Section semantic concepts semantic gap speciﬁc speech transcripts suﬃcient supervised learning supervised machine learning support vector machine temporal tion training data TRECVID benchmark TRECVID Workshop vector space model video archives video content video data sets video retrieval results video retrieval system video search engine video segments visual features WordNet