Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280526073> ?p ?o ?g. }
- W4280526073 endingPage "108945" @default.
- W4280526073 startingPage "108945" @default.
- W4280526073 abstract "Many Siamese-based RGBT trackers have been prevalently designed in recent years for fast-tracking. However, the correlation operation in them is a local linear matching process, which may easily lose semantic information required inevitably by high-precision trackers. In this paper, we propose a strong cross-modal model based on transformer for robust RGBT tracking. Specifically, a simple dual-flow convolutional network is designed to extract and fuse dual-modal features, with comparably lower complexity. Besides, to enhance the feature representation and deepen semantic features, a modal weight allocation strategy and a backbone feature extracted network based on modified Resnet-50 are designed, respectively. Also, an attention-based transformer feature fusion network is adopted to improve long-distance feature association to decrease the loss of semantic information. Finally, a classification regression subnetwork is investigated to accurately predict the state of the target. Sufficient experiments have been implemented on the RGBT234, RGBT210, GTOT and LasHeR datasets, demonstrating more outstanding tracking performance against the state-of-the-art RGBT trackers." @default.
- W4280526073 created "2022-05-22" @default.
- W4280526073 creator A5020462159 @default.
- W4280526073 creator A5084573070 @default.
- W4280526073 date "2022-08-01" @default.
- W4280526073 modified "2023-09-30" @default.
- W4280526073 title "Learning reliable modal weight with transformer for robust RGBT tracking" @default.
- W4280526073 cites W182940129 @default.
- W4280526073 cites W1857884451 @default.
- W4280526073 cites W2016802777 @default.
- W4280526073 cites W2117539524 @default.
- W4280526073 cites W2154889144 @default.
- W4280526073 cites W2214012879 @default.
- W4280526073 cites W2470394683 @default.
- W4280526073 cites W2518013266 @default.
- W4280526073 cites W2527415613 @default.
- W4280526073 cites W2557641257 @default.
- W4280526073 cites W2610871254 @default.
- W4280526073 cites W2737362155 @default.
- W4280526073 cites W2765667535 @default.
- W4280526073 cites W2775609985 @default.
- W4280526073 cites W2797812763 @default.
- W4280526073 cites W2799058067 @default.
- W4280526073 cites W2886910176 @default.
- W4280526073 cites W2888456413 @default.
- W4280526073 cites W2896228140 @default.
- W4280526073 cites W2909946038 @default.
- W4280526073 cites W2938696568 @default.
- W4280526073 cites W2945948323 @default.
- W4280526073 cites W2955983623 @default.
- W4280526073 cites W2962824803 @default.
- W4280526073 cites W2963534981 @default.
- W4280526073 cites W2963905288 @default.
- W4280526073 cites W2964069521 @default.
- W4280526073 cites W2964423614 @default.
- W4280526073 cites W2966759264 @default.
- W4280526073 cites W2969871771 @default.
- W4280526073 cites W2995936506 @default.
- W4280526073 cites W2996575194 @default.
- W4280526073 cites W2997131652 @default.
- W4280526073 cites W2997248655 @default.
- W4280526073 cites W2998756268 @default.
- W4280526073 cites W3001584168 @default.
- W4280526073 cites W3002567850 @default.
- W4280526073 cites W3005080107 @default.
- W4280526073 cites W3012425959 @default.
- W4280526073 cites W3035211844 @default.
- W4280526073 cites W3035571898 @default.
- W4280526073 cites W3041551881 @default.
- W4280526073 cites W3047800102 @default.
- W4280526073 cites W3064498204 @default.
- W4280526073 cites W3099681648 @default.
- W4280526073 cites W3102624093 @default.
- W4280526073 cites W3110562975 @default.
- W4280526073 cites W3123635396 @default.
- W4280526073 cites W3127317646 @default.
- W4280526073 cites W3132864630 @default.
- W4280526073 cites W3153607844 @default.
- W4280526073 cites W3167536469 @default.
- W4280526073 cites W3171106688 @default.
- W4280526073 cites W3172670627 @default.
- W4280526073 cites W3185777852 @default.
- W4280526073 cites W3187284461 @default.
- W4280526073 cites W3193488896 @default.
- W4280526073 cites W3198481905 @default.
- W4280526073 cites W3214586131 @default.
- W4280526073 cites W4226126595 @default.
- W4280526073 doi "https://doi.org/10.1016/j.knosys.2022.108945" @default.
- W4280526073 hasPublicationYear "2022" @default.
- W4280526073 type Work @default.
- W4280526073 citedByCount "9" @default.
- W4280526073 countsByYear W42805260732023 @default.
- W4280526073 crossrefType "journal-article" @default.
- W4280526073 hasAuthorship W4280526073A5020462159 @default.
- W4280526073 hasAuthorship W4280526073A5084573070 @default.
- W4280526073 hasConcept C119599485 @default.
- W4280526073 hasConcept C119857082 @default.
- W4280526073 hasConcept C121332964 @default.
- W4280526073 hasConcept C124101348 @default.
- W4280526073 hasConcept C127413603 @default.
- W4280526073 hasConcept C141353440 @default.
- W4280526073 hasConcept C153180895 @default.
- W4280526073 hasConcept C154945302 @default.
- W4280526073 hasConcept C165801399 @default.
- W4280526073 hasConcept C185592680 @default.
- W4280526073 hasConcept C188027245 @default.
- W4280526073 hasConcept C2780186347 @default.
- W4280526073 hasConcept C31258907 @default.
- W4280526073 hasConcept C38652104 @default.
- W4280526073 hasConcept C41008148 @default.
- W4280526073 hasConcept C56461940 @default.
- W4280526073 hasConcept C57501372 @default.
- W4280526073 hasConcept C59404180 @default.
- W4280526073 hasConcept C62520636 @default.
- W4280526073 hasConcept C66322947 @default.
- W4280526073 hasConcept C71139939 @default.
- W4280526073 hasConcept C88796919 @default.
- W4280526073 hasConceptScore W4280526073C119599485 @default.