Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899018466> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2899018466 abstract "Visual tracking based on deep learning technique is a very attractive research topic recently in the computer vision field. Deep convolutional neural networks (CNNs) are inherently limited to low spatial resolution, due to the max pooling process in the modules, and they are constrained by the high computation burden. We present a pretrained deep learning network architecture to the task of visual tracking, by introducing a wavelet representation in the network and a two-stage fine-tuning for learning appearance features, which improves the original deep learning tracker. Moreover, a loss layer based on Bayesian theorem is adopted to compute maximum classifier score, instead of the softmax loss layer, which can enhance the success rate. In addition, the idea of wavelet pooling helps perform feature dimension reduction. In addition, wavelet representation helps to reduce the computation time greatly. Compared with the original algorithm and other state-of-the-art methods, the proposed tracking method shows excellent performances on test baseline dataset. As our optimized spectrum CNN can extract a compact and efficient representation of objects, it can be further applied to multiple objects tracking." @default.
- W2899018466 created "2018-11-09" @default.
- W2899018466 creator A5035031033 @default.
- W2899018466 creator A5066197216 @default.
- W2899018466 creator A5069037876 @default.
- W2899018466 date "2018-10-29" @default.
- W2899018466 modified "2023-09-27" @default.
- W2899018466 title "Enhanced wavelet convolutional neural networks for visual tracking" @default.
- W2899018466 cites W1915785815 @default.
- W2899018466 cites W1964846093 @default.
- W2899018466 cites W2069332137 @default.
- W2899018466 cites W2089961441 @default.
- W2899018466 cites W2117539524 @default.
- W2899018466 cites W2145607950 @default.
- W2899018466 cites W2154889144 @default.
- W2899018466 cites W2158592639 @default.
- W2899018466 cites W2161381512 @default.
- W2899018466 cites W2167089254 @default.
- W2899018466 cites W2211629196 @default.
- W2899018466 cites W2214352687 @default.
- W2899018466 cites W2280226538 @default.
- W2899018466 cites W2408241409 @default.
- W2899018466 cites W2473868734 @default.
- W2899018466 cites W2512452641 @default.
- W2899018466 cites W2557641257 @default.
- W2899018466 cites W2738318237 @default.
- W2899018466 doi "https://doi.org/10.1117/1.jei.27.5.053046" @default.
- W2899018466 hasPublicationYear "2018" @default.
- W2899018466 type Work @default.
- W2899018466 sameAs 2899018466 @default.
- W2899018466 citedByCount "2" @default.
- W2899018466 countsByYear W28990184662019 @default.
- W2899018466 countsByYear W28990184662020 @default.
- W2899018466 crossrefType "journal-article" @default.
- W2899018466 hasAuthorship W2899018466A5035031033 @default.
- W2899018466 hasAuthorship W2899018466A5066197216 @default.
- W2899018466 hasAuthorship W2899018466A5069037876 @default.
- W2899018466 hasConcept C108583219 @default.
- W2899018466 hasConcept C153180895 @default.
- W2899018466 hasConcept C154945302 @default.
- W2899018466 hasConcept C188441871 @default.
- W2899018466 hasConcept C196216189 @default.
- W2899018466 hasConcept C31972630 @default.
- W2899018466 hasConcept C41008148 @default.
- W2899018466 hasConcept C47432892 @default.
- W2899018466 hasConcept C52622490 @default.
- W2899018466 hasConcept C59404180 @default.
- W2899018466 hasConcept C70437156 @default.
- W2899018466 hasConcept C81363708 @default.
- W2899018466 hasConceptScore W2899018466C108583219 @default.
- W2899018466 hasConceptScore W2899018466C153180895 @default.
- W2899018466 hasConceptScore W2899018466C154945302 @default.
- W2899018466 hasConceptScore W2899018466C188441871 @default.
- W2899018466 hasConceptScore W2899018466C196216189 @default.
- W2899018466 hasConceptScore W2899018466C31972630 @default.
- W2899018466 hasConceptScore W2899018466C41008148 @default.
- W2899018466 hasConceptScore W2899018466C47432892 @default.
- W2899018466 hasConceptScore W2899018466C52622490 @default.
- W2899018466 hasConceptScore W2899018466C59404180 @default.
- W2899018466 hasConceptScore W2899018466C70437156 @default.
- W2899018466 hasConceptScore W2899018466C81363708 @default.
- W2899018466 hasLocation W28990184661 @default.
- W2899018466 hasOpenAccess W2899018466 @default.
- W2899018466 hasPrimaryLocation W28990184661 @default.
- W2899018466 hasRelatedWork W2043862168 @default.
- W2899018466 hasRelatedWork W2197757032 @default.
- W2899018466 hasRelatedWork W2280226538 @default.
- W2899018466 hasRelatedWork W2513684595 @default.
- W2899018466 hasRelatedWork W2734342834 @default.
- W2899018466 hasRelatedWork W2740934103 @default.
- W2899018466 hasRelatedWork W2770370628 @default.
- W2899018466 hasRelatedWork W2791884362 @default.
- W2899018466 hasRelatedWork W2889871149 @default.
- W2899018466 hasRelatedWork W2912197073 @default.
- W2899018466 hasRelatedWork W2917472036 @default.
- W2899018466 hasRelatedWork W2918797960 @default.
- W2899018466 hasRelatedWork W2931190429 @default.
- W2899018466 hasRelatedWork W2939634612 @default.
- W2899018466 hasRelatedWork W2963338304 @default.
- W2899018466 hasRelatedWork W2970200245 @default.
- W2899018466 hasRelatedWork W2976672964 @default.
- W2899018466 hasRelatedWork W3081270820 @default.
- W2899018466 hasRelatedWork W3098217967 @default.
- W2899018466 hasRelatedWork W3195718405 @default.
- W2899018466 isParatext "false" @default.
- W2899018466 isRetracted "false" @default.
- W2899018466 magId "2899018466" @default.
- W2899018466 workType "article" @default.