Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964276093> ?p ?o ?g. }
- W2964276093 endingPage "97958" @default.
- W2964276093 startingPage "97949" @default.
- W2964276093 abstract "Background subtraction is an important task in computer vision. Traditional approaches usually utilize low-level visual features like color, texture, or edge to build background models. Due to the lack of deep features, they often achieve poor performance when facing complex video scenes such as illumination changes, background, or camera motions, camouflage effects and shadows. Recently, deep learning has shown to perform well in extracting deep features. To improve the robustness of background subtraction, in this paper, we propose an end-to-end multi-scale spatio-temporal (MS-ST) method which is able to extract deep features from video sequences. First, a video clip is input into a convolutional neural network for extracting multi-scale spatial features. Subsequently, to exploit the temporal information, we combine temporal sampling operations and ConvLSTM modules to extract the multi-scale temporal contextual information. Finally, the segmentation result is generated by fusing multi-scale spatio-temporal features. The experimental results on the CDnet-2014 dataset and the LASIESTA dataset demonstrate the effectiveness and superiority of the proposed method." @default.
- W2964276093 created "2019-07-30" @default.
- W2964276093 creator A5035701638 @default.
- W2964276093 creator A5053413465 @default.
- W2964276093 creator A5066869045 @default.
- W2964276093 creator A5084521033 @default.
- W2964276093 creator A5084681436 @default.
- W2964276093 date "2019-01-01" @default.
- W2964276093 modified "2023-10-17" @default.
- W2964276093 title "End-to-End Background Subtraction via a Multi-Scale Spatio-Temporal Model" @default.
- W2964276093 cites W1903029394 @default.
- W2964276093 cites W1942214758 @default.
- W2964276093 cites W1964127768 @default.
- W2964276093 cites W1967456674 @default.
- W2964276093 cites W1969977005 @default.
- W2964276093 cites W1994634851 @default.
- W2964276093 cites W2033453961 @default.
- W2964276093 cites W2055983636 @default.
- W2964276093 cites W2062520372 @default.
- W2964276093 cites W2064675550 @default.
- W2964276093 cites W2067813398 @default.
- W2964276093 cites W2098305432 @default.
- W2964276093 cites W2102625004 @default.
- W2964276093 cites W2116076678 @default.
- W2964276093 cites W2118143383 @default.
- W2964276093 cites W2127070222 @default.
- W2964276093 cites W2139501017 @default.
- W2964276093 cites W2142412278 @default.
- W2964276093 cites W2143612262 @default.
- W2964276093 cites W2158592639 @default.
- W2964276093 cites W2158604775 @default.
- W2964276093 cites W2165698076 @default.
- W2964276093 cites W2237782131 @default.
- W2964276093 cites W2293582111 @default.
- W2964276093 cites W2326050853 @default.
- W2964276093 cites W2412782625 @default.
- W2964276093 cites W2417256080 @default.
- W2964276093 cites W2511363568 @default.
- W2964276093 cites W2514564637 @default.
- W2964276093 cites W2519528544 @default.
- W2964276093 cites W2525668722 @default.
- W2964276093 cites W2755190242 @default.
- W2964276093 cites W2759692151 @default.
- W2964276093 cites W2767970498 @default.
- W2964276093 cites W2774176625 @default.
- W2964276093 cites W2793865950 @default.
- W2964276093 cites W2888845200 @default.
- W2964276093 cites W2902464468 @default.
- W2964276093 cites W2963351448 @default.
- W2964276093 cites W2963881378 @default.
- W2964276093 cites W4300179783 @default.
- W2964276093 doi "https://doi.org/10.1109/access.2019.2930319" @default.
- W2964276093 hasPublicationYear "2019" @default.
- W2964276093 type Work @default.
- W2964276093 sameAs 2964276093 @default.
- W2964276093 citedByCount "16" @default.
- W2964276093 countsByYear W29642760932020 @default.
- W2964276093 countsByYear W29642760932021 @default.
- W2964276093 countsByYear W29642760932022 @default.
- W2964276093 countsByYear W29642760932023 @default.
- W2964276093 crossrefType "journal-article" @default.
- W2964276093 hasAuthorship W2964276093A5035701638 @default.
- W2964276093 hasAuthorship W2964276093A5053413465 @default.
- W2964276093 hasAuthorship W2964276093A5066869045 @default.
- W2964276093 hasAuthorship W2964276093A5084521033 @default.
- W2964276093 hasAuthorship W2964276093A5084681436 @default.
- W2964276093 hasBestOaLocation W29642760931 @default.
- W2964276093 hasConcept C104317684 @default.
- W2964276093 hasConcept C108583219 @default.
- W2964276093 hasConcept C121332964 @default.
- W2964276093 hasConcept C153180895 @default.
- W2964276093 hasConcept C154945302 @default.
- W2964276093 hasConcept C160633673 @default.
- W2964276093 hasConcept C185592680 @default.
- W2964276093 hasConcept C2776196576 @default.
- W2964276093 hasConcept C2778755073 @default.
- W2964276093 hasConcept C31972630 @default.
- W2964276093 hasConcept C32653426 @default.
- W2964276093 hasConcept C41008148 @default.
- W2964276093 hasConcept C55493867 @default.
- W2964276093 hasConcept C62520636 @default.
- W2964276093 hasConcept C63479239 @default.
- W2964276093 hasConcept C81363708 @default.
- W2964276093 hasConcept C89600930 @default.
- W2964276093 hasConceptScore W2964276093C104317684 @default.
- W2964276093 hasConceptScore W2964276093C108583219 @default.
- W2964276093 hasConceptScore W2964276093C121332964 @default.
- W2964276093 hasConceptScore W2964276093C153180895 @default.
- W2964276093 hasConceptScore W2964276093C154945302 @default.
- W2964276093 hasConceptScore W2964276093C160633673 @default.
- W2964276093 hasConceptScore W2964276093C185592680 @default.
- W2964276093 hasConceptScore W2964276093C2776196576 @default.
- W2964276093 hasConceptScore W2964276093C2778755073 @default.
- W2964276093 hasConceptScore W2964276093C31972630 @default.
- W2964276093 hasConceptScore W2964276093C32653426 @default.
- W2964276093 hasConceptScore W2964276093C41008148 @default.
- W2964276093 hasConceptScore W2964276093C55493867 @default.
- W2964276093 hasConceptScore W2964276093C62520636 @default.