Content based video indexing and retrieval

Smoliar, Stephen W.; Zhang, Hong-Jiang

doi:10.1109/93.311653

Cited by 384 publications

(123 citation statements)

References 8 publications

Supporting

Mentioning

118

Contrasting

Unclassified

Order By: Relevance

“…During the last few years many researchers have proposed a variety of image indexing methods, based on shape, colour, or combinations of such indices (Faloutsos et al 1994;Smoliar & Zhang 1994). The general approach is to calculate an approximately invariant statistic, such as colour histogram or invariants of shape moments, and use that to stratify or partition the image database.…”

Section: (B) Comparison With Other Approachesmentioning

confidence: 99%

“…The key conceptual breakthrough was the idea of contentbased indexing, allowing images and audio to be searched directly instead of relying on keyword (or propositional) annotation. The Massachusetts Institute of Technology (MIT)`Photobook' system (Pentland & Picard 1994;Pentland et al 1994) together with e¡orts such as the IBM`query-by-image-content' (Faloutsos et al 1994) system or the ISS project in Singapore (Smoliar & Zhang 1994), have demonstrated that such a search is both possible and useful. The idea has since become the focus of dozens of special journal issues, workshops, and the like.…”

Section: Introduction : T H E Probl E Mmentioning

confidence: 99%

See 1 more Smart Citation

Content-based indexing of images and video

Pentland

1997

Phil. Trans. R. Soc. Lond. B

View full text Add to dashboard Cite

SU M M A RYBy representing image content using probabilistic models of an object's appearance we can obtain semantics-preserving compression of the image data. Such compact representations of an image's salient features allow rapid computer searches of even large image databases. Examples are shown for databases of face images, a video of American sign language (ASL), and a video of facial expressions.

show abstract

Section: (B) Comparison With Other Approachesmentioning

confidence: 99%

Section: Introduction : T H E Probl E Mmentioning

confidence: 99%

Content-based indexing of images and video

Pentland

1997

Phil. Trans. R. Soc. Lond. B

View full text Add to dashboard Cite

show abstract

“…In contrast, content-based retrieval has been proposed to index and search multimedia data by their low-level features. This approach has been respectively adopted to image, video and audio retrieval [3] [5]. Formulating a query in this approach is to create or select a representative media object as example and search for other objects that resemble to it in terms of low-level features, denoted as query-by-example.…”

Section: Introductionmentioning

confidence: 99%

Search for Multi-modality Data in Digital Libraries

Yang

Zhuang

2001

Advances in Multimedia Information Processing — PCM 2001

View full text Add to dashboard Cite

Developing effective and efficient retrieval techniques for multimedia data is a challenging issue in building a digital library. Unlike most previously proposed retrieval approaches that focus on a specific media type, this paper presents 2M2Net as a seamless integration framework for retrieval of multi-modality data in digital libraries. As its specific approaches, a learning-fromelements strategy is devised for propagation of semantic descriptions, and a cross media search mechanism with relevance feedback is proposed for evaluation and refinement of user queries. Experiments conducted on a digital encyclopedia manifest the effectiveness and flexibility of our approaches.

show abstract

“…The machine-aided retrieval of multimedia information-audio [32], image [8] [26], or video [28] [16], etc.-is achieved based on representations in the form of descriptors (or feature vectors), i.e., a set of real numbers. Two issues arise: one is the effectiveness of the representation, i.e., to what extent can the meaningful contents of the media be represented in these vectors?…”

Section: Introductionmentioning

confidence: 99%

Comparing discriminating transformations and SVM for learning during multimedia retrieval

Zhou

Huang

2001

Proceedings of the Ninth ACM International Conference on Multimedia

View full text Add to dashboard Cite

On-line learning or "relevance feedback" techniques for multimedia information retrieval have been explored from many different points of view: from early heuristic-based feature weighting schemes to recently proposed optimal learning algorithms, probabilistic/Bayesian learning algorithms, boosting techniques, discriminant-EM algorithm, support vector machine, and other kernel-based learning machines. Based on a careful examination of the problem and a detailed analysis of the existing solutions, we propose several discriminating transforms as the learning machine during the user interaction. We argue that relevance feedback problem is best represented as a biased classification problem, or a (1+x)-class classification problem. Biased Discriminant Transform (BDT) is shown to outperform all the others. A kernel form is proposed to capture non-linearity in the class distributions.

show abstract

Content based video indexing and retrieval

Cited by 384 publications

References 8 publications

Content-based indexing of images and video

Content-based indexing of images and video

Search for Multi-modality Data in Digital Libraries

Comparing discriminating transformations and SVM for learning during multimedia retrieval

Contact Info

Product

Resources

About