{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T20:10:05Z","timestamp":1755893405354,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T00:00:00Z","timestamp":1701993600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,8]]},"DOI":"10.1145\/3654446.3654520","type":"proceedings-article","created":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:00:57Z","timestamp":1714759257000},"page":"415-420","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Siamese Multi-level Feature Network for VIS and NIR Image Matching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0500-7932","authenticated-orcid":false,"given":"Xinyi","family":"Ma","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3591-9394","authenticated-orcid":false,"given":"Fan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2024,5,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Image registration methods: a survey [J]. Image and vision computing","author":"Zitova B","year":"2003","unstructured":"Zitova B, Flusser J. Image registration methods: a survey [J]. Image and vision computing, 2003, 21(11): 977-1000."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01359-2"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Aguilera C A Aguilera F J Sappa A D Learning cross-spectral similarity measures with deep convolutional neural networks [C]\/\/Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2016: 1-9.","DOI":"10.1109\/CVPRW.2016.40"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Balntas V Lenc K Vedaldi A HPatches: A benchmark and evaluation of handcrafted and learned local descriptors [C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 5173-5182.","DOI":"10.1109\/CVPR.2017.410"},{"key":"e_1_3_2_1_5_1","volume-title":"Zhou L","author":"Luo Z","year":"2019","unstructured":"Luo Z, Shen T, Zhou L, Contextdesc: Local descriptor augmentation with cross-modality context [C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019: 2527-2536."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Liu J Fan X Huang Z Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection [C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022: 5802-5811.","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.02.004"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2016.03.003"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2892432"},{"key":"e_1_3_2_1_10_1","first-page":"126","article-title":"Image registration between visible and infrared images for electrical equipment inspection robots based on quadrilateral features [C]\/\/2017 2nd International Conference on Robotics and Automation Engineering (ICRAE)","volume":"2017","author":"Chen Y","unstructured":"Chen Y, Dai J, Mao X, Image registration between visible and infrared images for electrical equipment inspection robots based on quadrilateral features [C]\/\/2017 2nd International Conference on Robotics and Automation Engineering (ICRAE). IEEE, 2017: 126-130.","journal-title":"IEEE"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs9090904"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.02.012"},{"issue":"07","key":"e_1_3_2_1_13_1","first-page":"641","article-title":"A review of research on infrared and visible light image registration technology [J]","volume":"44","author":"Li Yunhong","year":"2022","unstructured":"Li Yunhong, Liu Yudong, Su Xueping. A review of research on infrared and visible light image registration technology [J]. Infrared Technology, 2022, 44(07): 641-651.","journal-title":"Infrared Technology"},{"issue":"09","key":"e_1_3_2_1_14_1","first-page":"1848","article-title":"A review of multi-modal remote sensing image matching methods [J]","volume":"51","author":"Sui Haigang","year":"2022","unstructured":"Sui Haigang, Liu Chang, Gan Zhe, etc. A review of multi-modal remote sensing image matching methods [J]. Journal of Surveying and Mapping, 2022, 51(09): 1848-1861.","journal-title":"Journal of Surveying and Mapping"},{"key":"e_1_3_2_1_15_1","volume-title":"TS-NET: Combining modality specific and common features for multimodal patch matching [C]\/\/2018 25th IEEE International Conference on Image Processing (ICIP)","author":"En S","year":"2018","unstructured":"En S, Lechervy A, Jurie F. TS-NET: Combining modality specific and common features for multimodal patch matching [C]\/\/2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018: 3024-3028."},{"key":"e_1_3_2_1_16_1","volume-title":"LF-Net: Learning local features from images [J]. Advances in neural information processing systems","author":"Ono Y","year":"2018","unstructured":"Ono Y, Trulls E, Fua P, LF-Net: Learning local features from images [J]. Advances in neural information processing systems, 2018, 31."},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Object matching between visible and infrared images using a Siamese network [J]","volume":"2022","author":"Li W","unstructured":"Li W, Chen Q, Gu G, Object matching between visible and infrared images using a Siamese network [J]. Applied Intelligence, 2022: 1-13.","journal-title":"Applied Intelligence"},{"key":"e_1_3_2_1_18_1","article-title":"Siamese network for keypoint detection in optical and SAR images [J]","author":"Zhang S","year":"2023","unstructured":"Zhang S, Fu Z, Liu J, Multilevel attention Siamese network for keypoint detection in optical and SAR images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2023.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"DeTone D Malisiewicz T Rabinovich A. Superpoint: Self-supervised interest point detection and description [C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2018: 224-236.","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Shen X Wang C Li X RF-Net: An end-to-end image matching network based on receptive field [C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019: 8132-8140.","DOI":"10.1109\/CVPR.2019.00832"},{"key":"e_1_3_2_1_21_1","first-page":"1150","article-title":"Object recognition from local scale-invariant features[C]\/\/Proceedings of the seventh IEEE international conference on computer vision","volume":"2","author":"Lowe D G","year":"1999","unstructured":"Lowe D G. Object recognition from local scale-invariant features[C]\/\/Proceedings of the seventh IEEE international conference on computer vision. Ieee, 1999, 2: 1150-1157.","journal-title":"Ieee"},{"key":"e_1_3_2_1_22_1","volume-title":"Speeded-up robust features (SURF) [J]. Computer vision and image understanding","author":"Bay H","year":"2008","unstructured":"Bay H, Ess A, Tuytelaars T, Speeded-up robust features (SURF) [J]. Computer vision and image understanding, 2008, 110(3): 346-359."},{"key":"e_1_3_2_1_23_1","volume-title":"Siamese neural networks for one-shot image recognition[C]\/\/ICML deep learning workshop","author":"Koch G","year":"2015","unstructured":"Koch G, Zemel R, Salakhutdinov R. Siamese neural networks for one-shot image recognition[C]\/\/ICML deep learning workshop. 2015, 2(1)."},{"key":"e_1_3_2_1_24_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale [J]. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy A","year":"2020","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, An image is worth 16x16 words: Transformers for image recognition at scale [J]. arXiv preprint arXiv:2010.11929, 2020."},{"key":"e_1_3_2_1_25_1","volume-title":"Multispectral interest points for RGB-NIR image registration [C]\/\/2011 18th IEEE international conference on image processing","author":"Firmenichy D","year":"2011","unstructured":"Firmenichy D, Brown M, S\u00fcsstrunk S. Multispectral interest points for RGB-NIR image registration [C]\/\/2011 18th IEEE international conference on image processing. IEEE, 2011: 181-184."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/s120912661"},{"key":"e_1_3_2_1_27_1","volume-title":"Toledo R. LGHD: A feature descriptor for matching across non-linear intensity variations [C]\/\/2015 IEEE International Conference on Image Processing (ICIP)","author":"Aguilera C A","year":"2015","unstructured":"Aguilera C A, Sappa A D, Toledo R. LGHD: A feature descriptor for matching across non-linear intensity variations [C]\/\/2015 IEEE International Conference on Image Processing (ICIP). IEEE, 2015: 178-181."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Zagoruyko S Komodakis N. Learning to compare image patches via convolutional neural networks [C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 4353-4361.","DOI":"10.1109\/CVPR.2015.7299064"},{"key":"e_1_3_2_1_29_1","volume-title":"Scalable high-performance image registration framework by unsupervised deep feature representations learning[J]","author":"Wu G","year":"2015","unstructured":"Wu G, Kim M, Wang Q, Scalable high-performance image registration framework by unsupervised deep feature representations learning[J]. IEEE transactions on biomedical engineering, 2015, 63(7): 1505-1516."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Tian Y Fan B Wu F. L2-net: Deep learning of discriminative patch descriptor in euclidean space [C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 661-669.","DOI":"10.1109\/CVPR.2017.649"},{"key":"e_1_3_2_1_31_1","volume-title":"Working hard to know your neighbor's margins: Local descriptor learning loss [J]. Advances in neural information processing systems","author":"Mishchuk A","year":"2017","unstructured":"Mishchuk A, Mishkin D, Radenovic F, Working hard to know your neighbor's margins: Local descriptor learning loss [J]. Advances in neural information processing systems, 2017, 30."},{"key":"e_1_3_2_1_32_1","volume-title":"Jia Y","author":"Han X","year":"2015","unstructured":"Han X, Leung T, Jia Y, Matchnet: Unifying feature and metric learning for patch-based matching [C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 3279-3286."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Zbontar J LeCun Y. Computing the stereo matching cost with a convolutional neural network [C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1592-1599.","DOI":"10.1109\/CVPR.2015.7298767"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Quan D Liang X Wang S AFD-Net: Aggregated feature difference learning for cross-spectral image patch matching [C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019: 3017-3026.","DOI":"10.1109\/ICCV.2019.00311"},{"key":"e_1_3_2_1_35_1","volume-title":"Lepetit V","author":"Yi K M","year":"2016","unstructured":"Yi K M, Trulls E, Lepetit V, Lift: Learned invariant feature transform [C]\/\/Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VI 14. Springer International Publishing, 2016: 467-483."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Dusmanu M Rocco I Pajdla T D2-net: A trainable cnn for joint description and detection of local features [C]\/\/Proceedings of the ieee\/cvf conference on computer vision and pattern recognition. 2019: 8092-8101.","DOI":"10.1109\/CVPR.2019.00828"},{"key":"e_1_3_2_1_37_1","volume-title":"Malisiewicz T","author":"Sarlin P E","year":"2020","unstructured":"Sarlin P E, DeTone D, Malisiewicz T, Superglue: Learning feature matching with graph neural networks [C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020: 4938-4947."},{"key":"e_1_3_2_1_38_1","volume-title":"Paying Attention to Multiscale Feature Maps in Multimodal Image Matching[J]. arXiv preprint arXiv:2103.11247","author":"Moreshet A","year":"2021","unstructured":"Moreshet A, Keller Y. Paying Attention to Multiscale Feature Maps in Multimodal Image Matching[J]. arXiv preprint arXiv:2103.11247, 2021."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Szegedy C Liu W Jia Y Going deeper with convolutions [C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S Deep residual learning for image recognition [C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3234531"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3034752"},{"key":"e_1_3_2_1_43_1","first-page":"1","article-title":"A multilevel spectral-spatial transformer network for hyperspectral image classification [J]","volume":"60","author":"Yu H","year":"2022","unstructured":"Yu H, Xu Z, Zheng K, MSTNet: A multilevel spectral-spatial transformer network for hyperspectral image classification [J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-13.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_44_1","volume-title":"Lee K","author":"Devlin J","year":"1810","unstructured":"Devlin J, Chang M W, Lee K, Bert: Pre-training of deep bidirectional transformers for language understanding [J]. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Schroff F Kalenichenko D Philbin J. Facenet: A unified embedding for face recognition and clustering [C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 815-823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_46_1","volume-title":"Discriminative learning of local image descriptors [J]","author":"Brown M","year":"2010","unstructured":"Brown M, Hua G, Winder S. Discriminative learning of local image descriptors [J]. IEEE transactions on pattern analysis and machine intelligence, 2010, 33(1): 43-57."},{"key":"e_1_3_2_1_47_1","volume-title":"Ba J. Adam: A method for stochastic optimization [J]. arXiv preprint arXiv:1412.6980","author":"Kingma D P","year":"2014","unstructured":"Kingma D P, Ba J. Adam: A method for stochastic optimization [J]. arXiv preprint arXiv:1412.6980, 2014."},{"key":"e_1_3_2_1_48_1","volume-title":"large minibatch sgd: Training imagenet in 1 hour [J]. arXiv preprint arXiv:1706.02677","author":"Goyal P","year":"2017","unstructured":"Goyal P, Doll\u00e1r P, Girshick R, Accurate, large minibatch sgd: Training imagenet in 1 hour [J]. arXiv preprint arXiv:1706.02677, 2017."},{"key":"e_1_3_2_1_49_1","first-page":"115","volume-title":"Perth, Australia","author":"Quan D","year":"2018","unstructured":"Quan D, Fang S, Liang X, Cross-spectral image patch matching by learning features of the spatially connected patches in a shared space[C]\/\/Computer Vision-ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2-6, 2018, Revised Selected Papers, Part II 14. Springer International Publishing, 2019: 115-130."}],"event":{"name":"SPCNC 2023: The 2nd International Conference on Signal Processing, Computer Networks and Communications","acronym":"SPCNC 2023","location":"Xiamen China"},"container-title":["Proceedings of the 2nd International Conference on Signal Processing, Computer Networks and Communications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654446.3654520","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654446.3654520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:36:46Z","timestamp":1755891406000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654446.3654520"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,8]]},"references-count":49,"alternative-id":["10.1145\/3654446.3654520","10.1145\/3654446"],"URL":"https:\/\/doi.org\/10.1145\/3654446.3654520","relation":{},"subject":[],"published":{"date-parts":[[2023,12,8]]},"assertion":[{"value":"2024-05-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}