Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386699372> ?p ?o ?g. }
- W4386699372 endingPage "5579" @default.
- W4386699372 startingPage "5564" @default.
- W4386699372 abstract "Recently, feature relation learning has attracted extensive attention in cross-spectral image patch matching. However, most feature relation learning methods can only extract shallow feature relations and are accompanied by the loss of useful discriminative features or the introduction of disturbing features. Although the latest multi-branch feature difference learning network can relatively sufficiently extract useful discriminative features, the multi-branch network structure it adopts has a large number of parameters. Therefore, we propose a novel two-branch feature interaction learning network (FIL-Net). Specifically, a novel feature interaction learning idea for cross-spectral image patch matching is proposed, and a new feature interaction learning module is constructed, which can effectively mine common and private features between cross-spectral image patches, and extract richer and deeper feature relations with invariance and discriminability. At the same time, we re-explore the feature extraction network for the cross-spectral image patch matching task, and a new two-branch residual feature extraction network with stronger feature extraction capabilities is constructed. In addition, we propose a new multi-loss strong-constrained optimization strategy, which can facilitate reasonable network optimization and efficient extraction of invariant and discriminative features. Furthermore, a public VIS-LWIR patch dataset and a public SEN1-2 patch dataset are constructed. At the same time, the corresponding experimental benchmarks are established, which are convenient for future research while solving few existing cross-spectral image patch matching datasets. Extensive experiments show that the proposed FIL-Net achieves state-of-the-art performance in three different cross-spectral image patch matching scenarios." @default.
- W4386699372 created "2023-09-14" @default.
- W4386699372 creator A5048012502 @default.
- W4386699372 creator A5053419806 @default.
- W4386699372 creator A5071607803 @default.
- W4386699372 creator A5075979415 @default.
- W4386699372 creator A5091521083 @default.
- W4386699372 date "2023-01-01" @default.
- W4386699372 modified "2023-10-12" @default.
- W4386699372 title "Feature Interaction Learning Network for Cross-Spectral Image Patch Matching" @default.
- W4386699372 cites W1832233747 @default.
- W4386699372 cites W1869500417 @default.
- W4386699372 cites W1955055330 @default.
- W4386699372 cites W1974450833 @default.
- W4386699372 cites W2012893378 @default.
- W4386699372 cites W2062415280 @default.
- W4386699372 cites W2085261163 @default.
- W4386699372 cites W2100766099 @default.
- W4386699372 cites W2117228865 @default.
- W4386699372 cites W2119605622 @default.
- W4386699372 cites W2138943513 @default.
- W4386699372 cites W2140935196 @default.
- W4386699372 cites W2151103935 @default.
- W4386699372 cites W2161969291 @default.
- W4386699372 cites W2163009106 @default.
- W4386699372 cites W2256359941 @default.
- W4386699372 cites W2294464339 @default.
- W4386699372 cites W2468674378 @default.
- W4386699372 cites W2530717046 @default.
- W4386699372 cites W2596901677 @default.
- W4386699372 cites W2612112834 @default.
- W4386699372 cites W2737260104 @default.
- W4386699372 cites W2913429812 @default.
- W4386699372 cites W2951019013 @default.
- W4386699372 cites W2951060728 @default.
- W4386699372 cites W2962708773 @default.
- W4386699372 cites W2962869940 @default.
- W4386699372 cites W2964305564 @default.
- W4386699372 cites W2973660294 @default.
- W4386699372 cites W2973665503 @default.
- W4386699372 cites W2984146633 @default.
- W4386699372 cites W2991831678 @default.
- W4386699372 cites W3033110441 @default.
- W4386699372 cites W3095367607 @default.
- W4386699372 cites W3128338494 @default.
- W4386699372 cites W3188774019 @default.
- W4386699372 cites W3189758472 @default.
- W4386699372 cites W3200493442 @default.
- W4386699372 cites W4221141078 @default.
- W4386699372 cites W4285255440 @default.
- W4386699372 cites W4285257031 @default.
- W4386699372 cites W4312052673 @default.
- W4386699372 cites W4317796378 @default.
- W4386699372 cites W4362654402 @default.
- W4386699372 cites W4377091052 @default.
- W4386699372 doi "https://doi.org/10.1109/tip.2023.3313488" @default.
- W4386699372 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37703149" @default.
- W4386699372 hasPublicationYear "2023" @default.
- W4386699372 type Work @default.
- W4386699372 citedByCount "0" @default.
- W4386699372 crossrefType "journal-article" @default.
- W4386699372 hasAuthorship W4386699372A5048012502 @default.
- W4386699372 hasAuthorship W4386699372A5053419806 @default.
- W4386699372 hasAuthorship W4386699372A5071607803 @default.
- W4386699372 hasAuthorship W4386699372A5075979415 @default.
- W4386699372 hasAuthorship W4386699372A5091521083 @default.
- W4386699372 hasConcept C105795698 @default.
- W4386699372 hasConcept C138885662 @default.
- W4386699372 hasConcept C153180895 @default.
- W4386699372 hasConcept C154945302 @default.
- W4386699372 hasConcept C165064840 @default.
- W4386699372 hasConcept C2776401178 @default.
- W4386699372 hasConcept C33923547 @default.
- W4386699372 hasConcept C41008148 @default.
- W4386699372 hasConcept C41895202 @default.
- W4386699372 hasConcept C52622490 @default.
- W4386699372 hasConcept C59404180 @default.
- W4386699372 hasConcept C83665646 @default.
- W4386699372 hasConcept C97931131 @default.
- W4386699372 hasConceptScore W4386699372C105795698 @default.
- W4386699372 hasConceptScore W4386699372C138885662 @default.
- W4386699372 hasConceptScore W4386699372C153180895 @default.
- W4386699372 hasConceptScore W4386699372C154945302 @default.
- W4386699372 hasConceptScore W4386699372C165064840 @default.
- W4386699372 hasConceptScore W4386699372C2776401178 @default.
- W4386699372 hasConceptScore W4386699372C33923547 @default.
- W4386699372 hasConceptScore W4386699372C41008148 @default.
- W4386699372 hasConceptScore W4386699372C41895202 @default.
- W4386699372 hasConceptScore W4386699372C52622490 @default.
- W4386699372 hasConceptScore W4386699372C59404180 @default.
- W4386699372 hasConceptScore W4386699372C83665646 @default.
- W4386699372 hasConceptScore W4386699372C97931131 @default.
- W4386699372 hasLocation W43866993721 @default.
- W4386699372 hasLocation W43866993722 @default.
- W4386699372 hasOpenAccess W4386699372 @default.
- W4386699372 hasPrimaryLocation W43866993721 @default.
- W4386699372 hasRelatedWork W2619127353 @default.
- W4386699372 hasRelatedWork W2786094008 @default.