Introduction to MPEG-7: Multimedia Content Description Interface

By P. Salembier, Thomas Sikora, Bangalore S. Manjunath. 2002

1,357 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/0cedea5238038dcd32bdf25aed9f2030abccd1f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

The MPEG-7 visual standard for content description-an overview (2001, methodology): “For an overall overview of the MPEG-7 Standard, more detailed descriptions of MPEG-7 content-based visual, audio and speech descriptors, the reader is referred to the literature in [ 2 ], [3] and to the remaining papers of this Special Issue on MPEG-7 in [5]‐[12].”
Content-based image retrieval using color difference histogram (2013, methodology): “In MPEG-7, three shape descriptors are used for object-based image retrieval; these are the 3-D shape descriptor, region-based shapes derived from Zernike moments, and the curvature scale space (CSS) descriptor [10].”
Shape representation and classification using the Poisson equation (2004, methodology): “In addition, we compare our results to the contour- and region-based shape descriptors adopted by the MPEG7 International Standards, namely the curvature scale space descriptor (CSSD) [40], [19] and Angular Radial Transform descriptor (ARTD)[30], [9], [19].”
Geographic Image Retrieval Using Local Invariant Features (2013, methodology): “The chi-square measure is optimal for the Lab and RGB color spaces, and second only to the EMD measures for the HLS color space, and thus could be considered the best measure overall.”
Sketch-Based Image Retrieval: Benchmark and Bag-of-Features Descriptors (2011, methodology): “Additionally, we present the results of the evaluation of a set of four different global sketch-based descriptors: angular radial partitioning (ARP) [22], edge histogram descriptor from the MPEG-7 standard (EHD) [ 23 ] and the Tensor and HoG descriptors [9] and evaluate, whether a bag-of-features-ba”
Image retrieval based on micro-structure descriptor (2011, methodology): “The MPEG-7 standard adopts three texture descriptors: homogeneous texture descriptor, texture browsing descriptor and the edge histogram descriptor [10].”
CoPhIR: a Test Collection for Content-Based Image Retrieval (2009, background): “Visual descriptors are represented as vectors, and the MPEG-7 group proposed a distance measure for each descriptor to evaluate the similarity of two objects [5].”
Deep Learning Techniques for Inverse Problems in Imaging (2020, background): “umptions in many prior works. Sparsity (e.g., in Discrete Cosine Transform (DCT) or wavelet domains) plays the central role in most lossy compression standards like JPEG [71], JPEG-2000 [72] and MPEG [73]. Another successful example is graphical models: in this case a high dimensional distribution b”
Diversity in recommender systems - A survey (2017, methodology): “The user model can be an independent data structure separate from the algorithm itself [15–17, 29 ] , a part These differences severely limit the portability of user models between different systems and content types.”