FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2907173717> ?p ?o ?g. }

• W2907173717 endingPage "1708" @default.
• W2907173717 startingPage "1694" @default.
• W2907173717 abstract "Local binary descriptors, such as local binary pattern (LBP) and its various variants, have been studied extensively in texture and dynamic texture analysis due to their outstanding characteristics, such as grayscale invariance, low computational complexity and good discriminability. Most existing local binary feature extraction methods extract spatio-temporal features from three orthogonal planes of a spatio-temporal volume by viewing a dynamic texture in 3D space. For a given pixel in a video, only a proportion of its surrounding pixels is incorporated in the local binary feature extraction process. We argue that the ignored pixels contain discriminative information that should be explored. To fully utilize the information conveyed by all the pixels in a local neighborhood, we propose extracting local binary features from the spatio-temporal domain with 3D filters that are learned in an unsupervised manner so that the discriminative features along both the spatial and temporal dimensions are captured simultaneously. The proposed approach consists of three components: 1) 3D filtering; 2) binary hashing; and 3) joint histogramming. Densely sampled 3D blocks of a dynamic texture are first normalized to have zero mean and are then filtered by 3D filters that are learned in advance. To preserve more of the structure information, the filter response vectors are decomposed into two complementary components, namely, the signs and the magnitudes, which are further encoded separately into binary codes. The local mean pixels of the 3D blocks are also converted into binary codes. Finally, three types of binary codes are combined via joint or hybrid histograms for the final feature representation. Extensive experiments are conducted on three commonly used dynamic texture databases: 1) UCLA; 2) DynTex; and 3) YUVL. The proposed method provides comparable results to, and even outperforms, many state-of-the-art methods." @default.
• W2907173717 created "2019-01-11" @default.
• W2907173717 creator A5012088434 @default.
• W2907173717 creator A5018617528 @default.
• W2907173717 creator A5029771864 @default.
• W2907173717 creator A5063481044 @default.
• W2907173717 creator A5072890921 @default.
• W2907173717 date "2019-07-01" @default.
• W2907173717 modified "2023-10-01" @default.
• W2907173717 title "Dynamic Texture Classification Using Unsupervised 3D Filter Learning and Local Binary Encoding" @default.
• W2907173717 cites W1522734439 @default.
• W2907173717 cites W1554235224 @default.
• W2907173717 cites W1560120246 @default.
• W2907173717 cites W1583531441 @default.
• W2907173717 cites W1585059879 @default.
• W2907173717 cites W1586730761 @default.
• W2907173717 cites W1628899544 @default.
• W2907173717 cites W180242331 @default.
• W2907173717 cites W18669060 @default.
• W2907173717 cites W1974813066 @default.
• W2907173717 cites W1975056068 @default.
• W2907173717 cites W1976566382 @default.
• W2907173717 cites W1983364832 @default.
• W2907173717 cites W1984024674 @default.
• W2907173717 cites W1984282654 @default.
• W2907173717 cites W1990063939 @default.
• W2907173717 cites W1992960277 @default.
• W2907173717 cites W2001937638 @default.
• W2907173717 cites W2002128052 @default.
• W2907173717 cites W2002195055 @default.
• W2907173717 cites W2008082651 @default.
• W2907173717 cites W2012103782 @default.
• W2907173717 cites W2016053056 @default.
• W2907173717 cites W2020430625 @default.
• W2907173717 cites W2034017214 @default.
• W2907173717 cites W2037901790 @default.
• W2907173717 cites W2047186200 @default.
• W2907173717 cites W2059426744 @default.
• W2907173717 cites W2069112299 @default.
• W2907173717 cites W2082265779 @default.
• W2907173717 cites W2088240871 @default.
• W2907173717 cites W2095463701 @default.
• W2907173717 cites W2105795585 @default.
• W2907173717 cites W2108674937 @default.
• W2907173717 cites W2120634833 @default.
• W2907173717 cites W2123175289 @default.
• W2907173717 cites W2126918828 @default.
• W2907173717 cites W2127541232 @default.
• W2907173717 cites W2130258210 @default.
• W2907173717 cites W2136155248 @default.
• W2907173717 cites W2139916508 @default.
• W2907173717 cites W2141859737 @default.
• W2907173717 cites W2142040002 @default.
• W2907173717 cites W2146966357 @default.
• W2907173717 cites W2147141800 @default.
• W2907173717 cites W2150515037 @default.
• W2907173717 cites W2160144769 @default.
• W2907173717 cites W2162374132 @default.
• W2907173717 cites W2163352848 @default.
• W2907173717 cites W2218665234 @default.
• W2907173717 cites W2345247439 @default.
• W2907173717 cites W2461069268 @default.
• W2907173717 cites W2518260411 @default.
• W2907173717 cites W2533739470 @default.
• W2907173717 cites W2551439276 @default.
• W2907173717 cites W2563138978 @default.
• W2907173717 cites W2620727906 @default.
• W2907173717 cites W2743674619 @default.
• W2907173717 cites W2753424941 @default.
• W2907173717 cites W2765610253 @default.
• W2907173717 cites W2790164970 @default.
• W2907173717 cites W2912155302 @default.
• W2907173717 cites W2963972490 @default.
• W2907173717 cites W3102431071 @default.
• W2907173717 cites W3103539074 @default.
• W2907173717 cites W4246750223 @default.
• W2907173717 doi "https://doi.org/10.1109/tmm.2018.2890362" @default.
• W2907173717 hasPublicationYear "2019" @default.
• W2907173717 type Work @default.
• W2907173717 sameAs 2907173717 @default.
• W2907173717 citedByCount "22" @default.
• W2907173717 countsByYear W29071737172020 @default.
• W2907173717 countsByYear W29071737172021 @default.
• W2907173717 countsByYear W29071737172022 @default.
• W2907173717 countsByYear W29071737172023 @default.
• W2907173717 crossrefType "journal-article" @default.
• W2907173717 hasAuthorship W2907173717A5012088434 @default.
• W2907173717 hasAuthorship W2907173717A5018617528 @default.
• W2907173717 hasAuthorship W2907173717A5029771864 @default.
• W2907173717 hasAuthorship W2907173717A5063481044 @default.
• W2907173717 hasAuthorship W2907173717A5072890921 @default.
• W2907173717 hasBestOaLocation W29071737172 @default.
• W2907173717 hasConcept C106131492 @default.
• W2907173717 hasConcept C115961682 @default.
• W2907173717 hasConcept C138885662 @default.
• W2907173717 hasConcept C153180895 @default.
• W2907173717 hasConcept C154945302 @default.
• W2907173717 hasConcept C160633673 @default.

• next