{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T18:29:24Z","timestamp":1750271364425},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T00:00:00Z","timestamp":1683244800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T00:00:00Z","timestamp":1683244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11760-023-02579-y","type":"journal-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:02:22Z","timestamp":1683291742000},"page":"3545-3553","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Transformer fusion and histogram layer multispectral pedestrian detection network"],"prefix":"10.1007","volume":"17","author":[{"given":"Ying","family":"Zang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaotao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingshan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,5]]},"reference":[{"key":"2579_CR1","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., et al.: Multispectral pedestrian detection: benchmark dataset and baseline. In: Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition, pp. 1037\u20131045 (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"2579_CR2","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, S,, Wang, S., et al.: Multispectral deep neural networks for pedestrian detection. arXiv:1611.02644 (2016)","DOI":"10.5244\/C.30.73"},{"key":"2579_CR3","unstructured":"Li, C., Song, D., Tong, R., et al.: Multispectral pedestrian detection via simultaneous detection and segmentation. arXiv:1808.04818 (2018)"},{"key":"2579_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhu, X., Chen, X., et al.: Weakly aligned cross-modal learning for multispectral pedestrian detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5127\u20135137 (2019)","DOI":"10.1109\/ICCV.2019.00523"},{"key":"2579_CR5","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.patcog.2018.08.005","volume":"85","author":"C Li","year":"2019","unstructured":"Li, C., Song, D., Tong, R., et al.: Illumination-aware faster R-CNN for robust multispectral pedestrian detection. Pattern Recognit. 85, 161\u2013171 (2019)","journal-title":"Pattern Recognit."},{"key":"2579_CR6","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.inffus.2018.11.017","volume":"50","author":"D Guan","year":"2019","unstructured":"Guan, D., Cao, Y., Yang, J., et al.: Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection. Inf. Fus. 50, 148\u2013157 (2019)","journal-title":"Inf. Fus."},{"key":"2579_CR7","doi-asserted-by":"crossref","unstructured":"Zhou, K., Chen, L., Cao, X.: Improving multispectral pedestrian detection by addressing modality imbalance problems. In: European Conference On Computer Vision. Springer, Cham, pp. 787-803 (2020)","DOI":"10.1007\/978-3-030-58523-5_46"},{"issue":"4","key":"2579_CR8","doi-asserted-by":"publisher","first-page":"7846","DOI":"10.1109\/LRA.2021.3099870","volume":"6","author":"J Kim","year":"2021","unstructured":"Kim, J., Kim, H., Kim, T., et al.: MLPD: multi-label pedestrian detector in multispectral domain. IEEE Robot. Autom. Lett. 6(4), 7846\u20137853 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"4","key":"2579_CR9","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1109\/TAI.2021.3135804","volume":"3","author":"J Peeples","year":"2021","unstructured":"Peeples, J., Xu, W., Zare, A.: Histogram layers for texture analysis. IEEE Trans. Artif. Intell. 3(4), 541\u2013552 (2021)","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"5","key":"2579_CR10","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","volume":"28","author":"H Li","year":"2018","unstructured":"Li, H., Wu, X.J.: DenseFuse: a fusion approach to infrared and visible images. IEEE Trans. Image Process. 28(5), 2614\u20132623 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"2579_CR11","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.inffus.2021.02.023","volume":"73","author":"H Li","year":"2021","unstructured":"Li, H., Wu, X.J., Kittler, J.: RFN-Nest: an end-to-end residual fusion network for infrared and visible images. Inf. Fus. 73, 72\u201386 (2021)","journal-title":"Inf. Fus."},{"issue":"1","key":"2579_CR12","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","volume":"44","author":"H Xu","year":"2020","unstructured":"Xu, H., Ma, J., Jiang, J., et al.: U2Fusion: a unified unsupervised image fusion network. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 502\u2013518 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2579_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lef\u00e8vre, S., et al.: Multispectral fusion for object detection with cyclic fuse-and-refine blocks. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 276-280 (2020)","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"2579_CR14","doi-asserted-by":"crossref","unstructured":"VS, V., Valanarasu, J.M.J., Oza, P., et al.: Image fusion transformer. arXiv:2107.09011 (2021)","DOI":"10.1109\/ICIP46576.2022.9897280"},{"key":"2579_CR15","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K., Geiger, A.: Multi-modal fusion transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7077\u20137087 (2021)","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"2579_CR16","doi-asserted-by":"crossref","unstructured":"Fang, QY., Han, DP., Wang, ZK.: Cross-modality fusion transformer for multispectral object detection. arXiv:2111.00273 (2021)","DOI":"10.2139\/ssrn.4227745"},{"key":"2579_CR17","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Vedaldi, A.: Deep filter banks for texture recognition and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3828\u20133836 (2015)","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"2579_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xue, J., Dana, K.: Deep ten: Texture encoding network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 708\u2013717 (2017)","DOI":"10.1109\/CVPR.2017.309"},{"key":"2579_CR19","doi-asserted-by":"crossref","unstructured":"Xue, J., Zhang, H., Dana, K.: Deep texture manifold for ground terrain recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 558\u2013567 (2018)","DOI":"10.1109\/CVPR.2018.00065"},{"key":"2579_CR20","doi-asserted-by":"crossref","unstructured":"Hu, Y., Long, Z., AlRegib, G.: Multi-level texture encoding and representation (multer) based on deep neural networks. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 4410\u20134414 (2019)","DOI":"10.1109\/ICIP.2019.8803640"},{"key":"2579_CR21","doi-asserted-by":"crossref","unstructured":"Zhai, W., Cao, Y., Zhang, J., et al.: Deep multiple-attribute-perceived network for real-world texture recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3613\u20133622 (2019)","DOI":"10.1109\/ICCV.2019.00371"},{"key":"2579_CR22","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, F., Quan, Y., et al.: Deep texture recognition via exploiting cross-layer statistical self-similarity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5231\u20135240 (2021)","DOI":"10.1109\/CVPR46437.2021.00519"},{"key":"2579_CR23","doi-asserted-by":"crossref","unstructured":"Basu, S., Karki, M., Mukhopadhyay, S., et al.: A theoretical analysis of Deep Neural Networks for texture classification. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 992\u2013999 (2016)","DOI":"10.1109\/IJCNN.2016.7727306"},{"key":"2579_CR24","doi-asserted-by":"crossref","unstructured":"Basu, S., Mukhopadhyay, S., Karki, M., et al.: Deep neural networks for texture classification: a theoretical analysis. Neural Netw. 97, 173\u2013182 (2018)","DOI":"10.1016\/j.neunet.2017.10.001"},{"key":"2579_CR25","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez, A., Fang, Z., Socarras, Y., et al.: Pedestrian detection at day\/night time with visible and FIR cameras: a comparison. Sensors 16(6), 820 (2016)","DOI":"10.3390\/s16060820"},{"key":"2579_CR26","doi-asserted-by":"crossref","unstructured":"Dollar, P., Wojek, C., Schiele, B., et al.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743\u2013761 (2011)","DOI":"10.1109\/TPAMI.2011.155"},{"key":"2579_CR27","doi-asserted-by":"crossref","unstructured":"Konig, D., Adam, M., Jarvers, C., et al.: Fully convolutional region proposal networks for multispectral person detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 49\u201356 (2017)","DOI":"10.1109\/CVPRW.2017.36"},{"key":"2579_CR28","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.patcog.2018.03.007","volume":"80","author":"K Park","year":"2018","unstructured":"Park, K., Kim, S., Sohn, K.: Unified multi-spectral pedestrian detection based on probabilistic fusion networks. Pattern Recognit. 80, 143\u2013155 (2018)","journal-title":"Pattern Recognit."},{"key":"2579_CR29","unstructured":"Choi, H., Kim, S., Park, K., et al.: Multi-spectral pedestrian detection based on accumulated object proposal with fully convolutional networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 621\u2013626 (2016)"},{"key":"2579_CR30","doi-asserted-by":"crossref","unstructured":"Adadi, A., Berrada, M., et al.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138\u201352160 (2018)","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"2579_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2019.106944","volume":"165","author":"G Aceto","year":"2019","unstructured":"Aceto, G., Ciuonzo, D., Montieri, A., et al.: MIMETIC: mobile encrypted traffic classification using multimodal deep learning. Comput. Netw. 165, 106944 (2019)","journal-title":"Comput. Netw."},{"issue":"4","key":"2579_CR32","doi-asserted-by":"publisher","first-page":"4225","DOI":"10.1109\/TNSM.2021.3098157","volume":"18","author":"A Nascita","year":"2021","unstructured":"Nascita, A., Montieri, A., Aceto, G., et al.: XAI meets mobile traffic classification: understanding and improving multimodal deep learning architectures. IEEE Trans. Netw. Serv. Manage. 18(4), 4225\u20134246 (2021)","journal-title":"IEEE Trans. Netw. Serv. Manage."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02579-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-023-02579-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02579-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T11:20:22Z","timestamp":1692271222000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-023-02579-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,5]]},"references-count":32,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["2579"],"URL":"https:\/\/doi.org\/10.1007\/s11760-023-02579-y","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,5]]},"assertion":[{"value":"6 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 March 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}