Matches in SemOpenAlex for { <https://semopenalex.org/work/W2905439159> ?p ?o ?g. }
- W2905439159 abstract "Visual tracking has recently gained a great advance with the use of the convolutional neural network (CNN). Usually, existing CNN-based trackers exploit the features from a single layer or a certain combination of multiple layers. However, these features only characterise an object from an invariable aspect and cannot adapt to scene variation, which limits the performance of such trackers. To overcome this limitation, the authors study the problem from a new perspective and propose a novel convolutional layer selection method. To obtain robust appearance representation, they investigate the advantages of features extracted from different convolutional layers. To determine the correctness of the tracking prediction and updated model, they design a verification mechanism based on historical retrospect, which can estimate the deviation for each layer by bidirectionally locating the target. Meanwhile, the deviation works as the layer-wise selection criteria. Extensive evaluations on the OTB-2013, visual object tracking (VOT)-2016 and VOT-2017 benchmarks demonstrate that the proposed tracker performs favourably against several state-of-the-art trackers." @default.
- W2905439159 created "2018-12-22" @default.
- W2905439159 creator A5002391274 @default.
- W2905439159 creator A5005591242 @default.
- W2905439159 creator A5011167321 @default.
- W2905439159 creator A5063880073 @default.
- W2905439159 creator A5072015576 @default.
- W2905439159 creator A5081796777 @default.
- W2905439159 date "2019-03-04" @default.
- W2905439159 modified "2023-10-15" @default.
- W2905439159 title "Adaptive convolutional layer selection based on historical retrospect for visual tracking" @default.
- W2905439159 cites W134197611 @default.
- W2905439159 cites W182940129 @default.
- W2905439159 cites W1904671147 @default.
- W2905439159 cites W1915599933 @default.
- W2905439159 cites W1955514522 @default.
- W2905439159 cites W1963882359 @default.
- W2905439159 cites W1964846093 @default.
- W2905439159 cites W1985560977 @default.
- W2905439159 cites W2027714080 @default.
- W2905439159 cites W2039477421 @default.
- W2905439159 cites W2089961441 @default.
- W2905439159 cites W2098854771 @default.
- W2905439159 cites W2109579504 @default.
- W2905439159 cites W2121193292 @default.
- W2905439159 cites W2124211486 @default.
- W2905439159 cites W2124386111 @default.
- W2905439159 cites W2126302311 @default.
- W2905439159 cites W2139047213 @default.
- W2905439159 cites W2154889144 @default.
- W2905439159 cites W2161381512 @default.
- W2905439159 cites W2168117308 @default.
- W2905439159 cites W2211629196 @default.
- W2905439159 cites W2211807644 @default.
- W2905439159 cites W2214352687 @default.
- W2905439159 cites W2244956674 @default.
- W2905439159 cites W2343187456 @default.
- W2905439159 cites W2380373457 @default.
- W2905439159 cites W2470394683 @default.
- W2905439159 cites W2473868734 @default.
- W2905439159 cites W2474599091 @default.
- W2905439159 cites W2518013266 @default.
- W2905439159 cites W2557641257 @default.
- W2905439159 cites W2558899534 @default.
- W2905439159 cites W2599547527 @default.
- W2905439159 cites W2609910506 @default.
- W2905439159 cites W2681067697 @default.
- W2905439159 cites W2765908332 @default.
- W2905439159 cites W2768634781 @default.
- W2905439159 cites W2771877920 @default.
- W2905439159 cites W2885992220 @default.
- W2905439159 cites W2897666265 @default.
- W2905439159 cites W2916780012 @default.
- W2905439159 cites W2917435394 @default.
- W2905439159 cites W29474918 @default.
- W2905439159 cites W2962824803 @default.
- W2905439159 cites W2963272600 @default.
- W2905439159 cites W2964111344 @default.
- W2905439159 cites W3102624093 @default.
- W2905439159 doi "https://doi.org/10.1049/iet-cvi.2018.5194" @default.
- W2905439159 hasPublicationYear "2019" @default.
- W2905439159 type Work @default.
- W2905439159 sameAs 2905439159 @default.
- W2905439159 citedByCount "1" @default.
- W2905439159 countsByYear W29054391592019 @default.
- W2905439159 crossrefType "journal-article" @default.
- W2905439159 hasAuthorship W2905439159A5002391274 @default.
- W2905439159 hasAuthorship W2905439159A5005591242 @default.
- W2905439159 hasAuthorship W2905439159A5011167321 @default.
- W2905439159 hasAuthorship W2905439159A5063880073 @default.
- W2905439159 hasAuthorship W2905439159A5072015576 @default.
- W2905439159 hasAuthorship W2905439159A5081796777 @default.
- W2905439159 hasConcept C11413529 @default.
- W2905439159 hasConcept C153180895 @default.
- W2905439159 hasConcept C154945302 @default.
- W2905439159 hasConcept C17744445 @default.
- W2905439159 hasConcept C178790620 @default.
- W2905439159 hasConcept C185592680 @default.
- W2905439159 hasConcept C199539241 @default.
- W2905439159 hasConcept C202474056 @default.
- W2905439159 hasConcept C2776151529 @default.
- W2905439159 hasConcept C2776359362 @default.
- W2905439159 hasConcept C2779227376 @default.
- W2905439159 hasConcept C2781238097 @default.
- W2905439159 hasConcept C31972630 @default.
- W2905439159 hasConcept C41008148 @default.
- W2905439159 hasConcept C55439883 @default.
- W2905439159 hasConcept C56461940 @default.
- W2905439159 hasConcept C57501372 @default.
- W2905439159 hasConcept C81363708 @default.
- W2905439159 hasConcept C81917197 @default.
- W2905439159 hasConcept C94625758 @default.
- W2905439159 hasConceptScore W2905439159C11413529 @default.
- W2905439159 hasConceptScore W2905439159C153180895 @default.
- W2905439159 hasConceptScore W2905439159C154945302 @default.
- W2905439159 hasConceptScore W2905439159C17744445 @default.
- W2905439159 hasConceptScore W2905439159C178790620 @default.
- W2905439159 hasConceptScore W2905439159C185592680 @default.
- W2905439159 hasConceptScore W2905439159C199539241 @default.
- W2905439159 hasConceptScore W2905439159C202474056 @default.