FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902767594> ?p ?o ?g. }

• W2902767594 endingPage "81" @default.
• W2902767594 startingPage "71" @default.
• W2902767594 abstract "Abstract Most thermal infrared (TIR) tracking methods are discriminative, treating the tracking problem as a classification task. However, the objective of the classifier (label prediction) is not coupled to the objective of the tracker (location estimation). The classification task focuses on the between-class difference of the arbitrary objects, while the tracking task mainly deals with the within-class difference of the same objects. In this paper, we cast the TIR tracking problem as a similarity verification task, which is coupled well to the objective of the tracking task. We propose a TIR tracker via a Hierarchical Spatial-aware Siamese Convolutional Neural Network (CNN), named HSSNet. To obtain both spatial and semantic features of the TIR object, we design a Siamese CNN that coalesces the multiple hierarchical convolutional layers. Then, we propose a spatial-aware network to enhance the discriminative ability of the coalesced hierarchical feature. Subsequently, we train this network end to end on a large visible video detection dataset to learn the similarity between paired objects before we transfer the network into the TIR domain. Next, this pre-trained Siamese network is used to evaluate the similarity between the target template and target candidates. Finally, we locate the candidate that is most similar to the tracked target. Extensive experimental results on the benchmarks VOT-TIR 2015 and VOT-TIR 2016 show that our proposed method achieves favorable performance compared to the state-of-the-art methods." @default.
• W2902767594 created "2018-12-11" @default.
• W2902767594 creator A5026086568 @default.
• W2902767594 creator A5029029467 @default.
• W2902767594 creator A5039269078 @default.
• W2902767594 creator A5049301997 @default.
• W2902767594 creator A5069054353 @default.
• W2902767594 date "2019-02-01" @default.
• W2902767594 modified "2023-10-17" @default.
• W2902767594 title "Hierarchical spatial-aware Siamese network for thermal infrared object tracking" @default.
• W2902767594 cites W1534421354 @default.
• W2902767594 cites W1727279473 @default.
• W2902767594 cites W1961006157 @default.
• W2902767594 cites W1965134664 @default.
• W2902767594 cites W1978969068 @default.
• W2902767594 cites W1982554717 @default.
• W2902767594 cites W1989267105 @default.
• W2902767594 cites W1999621311 @default.
• W2902767594 cites W2011138280 @default.
• W2902767594 cites W2031596661 @default.
• W2902767594 cites W2054846461 @default.
• W2902767594 cites W2059781288 @default.
• W2902767594 cites W2084438750 @default.
• W2902767594 cites W2117539524 @default.
• W2902767594 cites W2158827467 @default.
• W2902767594 cites W2215003561 @default.
• W2902767594 cites W2249334575 @default.
• W2902767594 cites W2297991835 @default.
• W2902767594 cites W2313938314 @default.
• W2902767594 cites W2315643162 @default.
• W2902767594 cites W2327699058 @default.
• W2902767594 cites W2343166405 @default.
• W2902767594 cites W2400262625 @default.
• W2902767594 cites W2507470109 @default.
• W2902767594 cites W2522601641 @default.
• W2902767594 cites W2564805107 @default.
• W2902767594 cites W2567804583 @default.
• W2902767594 cites W2568078565 @default.
• W2902767594 cites W2720578934 @default.
• W2902767594 cites W2737362155 @default.
• W2902767594 cites W2765594081 @default.
• W2902767594 cites W2775609985 @default.
• W2902767594 cites W2794208501 @default.
• W2902767594 cites W2797647736 @default.
• W2902767594 cites W2802896860 @default.
• W2902767594 cites W2884939247 @default.
• W2902767594 cites W2887556118 @default.
• W2902767594 doi "https://doi.org/10.1016/j.knosys.2018.12.011" @default.
• W2902767594 hasPublicationYear "2019" @default.
• W2902767594 type Work @default.
• W2902767594 sameAs 2902767594 @default.
• W2902767594 citedByCount "77" @default.
• W2902767594 countsByYear W29027675942019 @default.
• W2902767594 countsByYear W29027675942020 @default.
• W2902767594 countsByYear W29027675942021 @default.
• W2902767594 countsByYear W29027675942022 @default.
• W2902767594 countsByYear W29027675942023 @default.
• W2902767594 crossrefType "journal-article" @default.
• W2902767594 hasAuthorship W2902767594A5026086568 @default.
• W2902767594 hasAuthorship W2902767594A5029029467 @default.
• W2902767594 hasAuthorship W2902767594A5039269078 @default.
• W2902767594 hasAuthorship W2902767594A5049301997 @default.
• W2902767594 hasAuthorship W2902767594A5069054353 @default.
• W2902767594 hasBestOaLocation W29027675941 @default.
• W2902767594 hasConcept C120665830 @default.
• W2902767594 hasConcept C121332964 @default.
• W2902767594 hasConcept C154945302 @default.
• W2902767594 hasConcept C15744967 @default.
• W2902767594 hasConcept C158355884 @default.
• W2902767594 hasConcept C19417346 @default.
• W2902767594 hasConcept C2775936607 @default.
• W2902767594 hasConcept C2781238097 @default.
• W2902767594 hasConcept C31972630 @default.
• W2902767594 hasConcept C41008148 @default.
• W2902767594 hasConceptScore W2902767594C120665830 @default.
• W2902767594 hasConceptScore W2902767594C121332964 @default.
• W2902767594 hasConceptScore W2902767594C154945302 @default.
• W2902767594 hasConceptScore W2902767594C15744967 @default.
• W2902767594 hasConceptScore W2902767594C158355884 @default.
• W2902767594 hasConceptScore W2902767594C19417346 @default.
• W2902767594 hasConceptScore W2902767594C2775936607 @default.
• W2902767594 hasConceptScore W2902767594C2781238097 @default.
• W2902767594 hasConceptScore W2902767594C31972630 @default.
• W2902767594 hasConceptScore W2902767594C41008148 @default.
• W2902767594 hasFunder F4320321001 @default.
• W2902767594 hasFunder F4320321921 @default.
• W2902767594 hasLocation W29027675941 @default.
• W2902767594 hasLocation W29027675942 @default.
• W2902767594 hasOpenAccess W2902767594 @default.
• W2902767594 hasPrimaryLocation W29027675941 @default.
• W2902767594 hasRelatedWork W2352586926 @default.
• W2902767594 hasRelatedWork W2375636617 @default.
• W2902767594 hasRelatedWork W2385949326 @default.
• W2902767594 hasRelatedWork W2422898642 @default.
• W2902767594 hasRelatedWork W2534746541 @default.
• W2902767594 hasRelatedWork W2736053408 @default.
• W2902767594 hasRelatedWork W2789220062 @default.
• W2902767594 hasRelatedWork W2943102817 @default.

• next