Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313479110> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4313479110 endingPage "109295" @default.
- W4313479110 startingPage "109295" @default.
- W4313479110 abstract "Infrared and visible image fusion aims to obtain a synthetic image that can simultaneously exhibit salient objects and provide abundant texture details. However, existing deep learning-based methods generally depend on convolutional operations, which indeed have good local feature extraction ability, but the restricted receptive field limits its capability in modeling long-range dependencies. To conquer this dilemma, we propose an infrared and visible image fusion method based on Transformer and cross correlation, named TCCFusion. Specifically, we design a local feature extraction branch (LFEB) to preserve local complementary information, in which a dense-shape network is introduced to reuse the information that may be lost during the convolutional operation. To avoid the limitation of the receptive field and to fully extract the global significant information, a global feature extraction branch (GFEB) is devised that consists of three Transformer blocks for long-range relationship construction. In addition, LFEB and GFEB are arranged in a parallel fashion to maintain local and global useful information in a more effective way. Furthermore, we design a cross correlation loss to train the proposed fusion model in an unsupervised manner, with which the fusion result can obtain adequate thermal radiation information in an infrared image and ample texture details in a visible image. Massive experiments on two mainstream datasets illustrate that our TCCFusion outperforms state-of-the-art algorithms not only on visual quality but also on quantitative assessments. Ablation experiments on the network framework and objective function demonstrate the effectiveness of the proposed method." @default.
- W4313479110 created "2023-01-06" @default.
- W4313479110 creator A5018073672 @default.
- W4313479110 creator A5023106937 @default.
- W4313479110 creator A5054738516 @default.
- W4313479110 date "2023-05-01" @default.
- W4313479110 modified "2023-10-10" @default.
- W4313479110 title "TCCFusion: An infrared and visible image fusion method based on transformer and cross correlation" @default.
- W4313479110 cites W1970579918 @default.
- W4313479110 cites W1985275570 @default.
- W4313479110 cites W2014886478 @default.
- W4313479110 cites W2033557294 @default.
- W4313479110 cites W2034995331 @default.
- W4313479110 cites W2070371541 @default.
- W4313479110 cites W2074907730 @default.
- W4313479110 cites W2091649119 @default.
- W4313479110 cites W2117382194 @default.
- W4313479110 cites W2133665775 @default.
- W4313479110 cites W2146353910 @default.
- W4313479110 cites W2170245688 @default.
- W4313479110 cites W2266694576 @default.
- W4313479110 cites W2474462684 @default.
- W4313479110 cites W2559870345 @default.
- W4313479110 cites W2570835027 @default.
- W4313479110 cites W2890295690 @default.
- W4313479110 cites W2912147220 @default.
- W4313479110 cites W2962916298 @default.
- W4313479110 cites W3011768656 @default.
- W4313479110 cites W3014880876 @default.
- W4313479110 cites W3024215945 @default.
- W4313479110 cites W3105639468 @default.
- W4313479110 cites W3121751387 @default.
- W4313479110 cites W3133700567 @default.
- W4313479110 cites W3166069983 @default.
- W4313479110 cites W4210447104 @default.
- W4313479110 cites W4283732315 @default.
- W4313479110 cites W4285228203 @default.
- W4313479110 cites W4294713055 @default.
- W4313479110 doi "https://doi.org/10.1016/j.patcog.2022.109295" @default.
- W4313479110 hasPublicationYear "2023" @default.
- W4313479110 type Work @default.
- W4313479110 citedByCount "4" @default.
- W4313479110 countsByYear W43134791102023 @default.
- W4313479110 crossrefType "journal-article" @default.
- W4313479110 hasAuthorship W4313479110A5018073672 @default.
- W4313479110 hasAuthorship W4313479110A5023106937 @default.
- W4313479110 hasAuthorship W4313479110A5054738516 @default.
- W4313479110 hasConcept C153180895 @default.
- W4313479110 hasConcept C154945302 @default.
- W4313479110 hasConcept C31972630 @default.
- W4313479110 hasConcept C41008148 @default.
- W4313479110 hasConcept C52622490 @default.
- W4313479110 hasConcept C81363708 @default.
- W4313479110 hasConceptScore W4313479110C153180895 @default.
- W4313479110 hasConceptScore W4313479110C154945302 @default.
- W4313479110 hasConceptScore W4313479110C31972630 @default.
- W4313479110 hasConceptScore W4313479110C41008148 @default.
- W4313479110 hasConceptScore W4313479110C52622490 @default.
- W4313479110 hasConceptScore W4313479110C81363708 @default.
- W4313479110 hasFunder F4320321001 @default.
- W4313479110 hasFunder F4320324116 @default.
- W4313479110 hasFunder F4320336744 @default.
- W4313479110 hasLocation W43134791101 @default.
- W4313479110 hasOpenAccess W4313479110 @default.
- W4313479110 hasPrimaryLocation W43134791101 @default.
- W4313479110 hasRelatedWork W2059299633 @default.
- W4313479110 hasRelatedWork W2518599539 @default.
- W4313479110 hasRelatedWork W2613736958 @default.
- W4313479110 hasRelatedWork W2732542196 @default.
- W4313479110 hasRelatedWork W2811390910 @default.
- W4313479110 hasRelatedWork W2969680539 @default.
- W4313479110 hasRelatedWork W2977314777 @default.
- W4313479110 hasRelatedWork W2995914718 @default.
- W4313479110 hasRelatedWork W3093612317 @default.
- W4313479110 hasRelatedWork W4307883119 @default.
- W4313479110 hasVolume "137" @default.
- W4313479110 isParatext "false" @default.
- W4313479110 isRetracted "false" @default.
- W4313479110 workType "article" @default.