{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:17:18Z","timestamp":1740147438181,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61801286","61801286","61801286","61801286"],"award-info":[{"award-number":["61801286","61801286","61801286","61801286"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s11760-024-03523-4","type":"journal-article","created":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T10:02:17Z","timestamp":1725271337000},"page":"8975-8986","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An advanced lightweight network with stepwise multiscale fusion in crowded scenes"],"prefix":"10.1007","volume":"18","author":[{"given":"Chunyuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,2]]},"reference":[{"key":"3523_CR1","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.inffus.2023.02.014","volume":"95","author":"DK Jain","year":"2023","unstructured":"Jain, D.K., Zhao, X., Gonz\u00e1lez-Almagro, G., et al.: Multimodal pedestrian detection using metaheuristics with deep convolutional neural network in crowded scenes. Inf. Fusion. 95, 401\u2013414 (2023)","journal-title":"Inf. Fusion."},{"issue":"4","key":"3523_CR2","doi-asserted-by":"publisher","first-page":"174329","DOI":"10.1007\/s11704-022-2050-4","volume":"17","author":"M Maqsood","year":"2023","unstructured":"Maqsood, M., Yasmin, S., Gillani, S., et al.: An effificient deep learning-assisted person re-identifification solution for intelligent video surveillance in smart cities. Front. Comp. Sci. 17(4), 174329 (2023)","journal-title":"Front. Comp. Sci."},{"issue":"12","key":"3523_CR3","doi-asserted-by":"publisher","first-page":"2037","DOI":"10.1109\/TPAMI.2006.244","volume":"28","author":"T Ahonen","year":"2006","unstructured":"Ahonen, T., Hadid, A., Pietikainen, M.: Face description with local binary patterns: application to face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 28(12), 2037\u20132041 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3523_CR4","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905). Vol. 1. IEEE, (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"3523_CR5","unstructured":"Wu, B., Ramakant N.: Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. Tenth IEEE international conference on computer vision (ICCV\u201905). Vol. 1. IEEE, 2005"},{"key":"3523_CR6","doi-asserted-by":"crossref","unstructured":"Ye, L., Eamonn K.: Time series shapelets: a new primitive for data mining. In: Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining. 2009","DOI":"10.1145\/1557019.1557122"},{"key":"3523_CR7","doi-asserted-by":"crossref","unstructured":"Lienhart, R., Jochen M.: An extended set of haar-like features for rapid object detection. In: Proceedings. international conference on image processing. Vol. 1. IEEE, 2002","DOI":"10.1109\/ICIP.2002.1038171"},{"key":"3523_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2014","DOI":"10.1109\/CVPR.2014.81"},{"key":"3523_CR9","doi-asserted-by":"crossref","unstructured":"Redmon, J., et al.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016","DOI":"10.1109\/CVPR.2016.91"},{"key":"3523_CR10","doi-asserted-by":"crossref","unstructured":"Tian, Z., et al.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2019","DOI":"10.1109\/ICCV.2019.00972"},{"key":"3523_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017","DOI":"10.1109\/CVPR.2017.106"},{"key":"3523_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Ali F.: YOLO9000: better, faster, stronger. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017","DOI":"10.1109\/CVPR.2017.690"},{"key":"3523_CR13","unstructured":"Redmon, J., Ali F.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"3523_CR14","unstructured":"Bochkovskiy, A., Wang, C.Y., Mark Liao, H.Y.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint (2020)"},{"key":"3523_CR15","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the ieee conference on computer vision and pattern recognition, Salt Lake City, UT, USA, 18\u201323 June 2018; pp. 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"3523_CR16","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C] In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023: 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"3523_CR17","doi-asserted-by":"publisher","first-page":"133936","DOI":"10.1109\/ACCESS.2022.3230894","volume":"10","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Wang, H., Xin, Z.: Efficient detection model of steel strip surface defects based on YOLO-V7. IEEE Access 10, 133936\u2013133944 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3230894","journal-title":"IEEE Access"},{"issue":"6","key":"3523_CR18","doi-asserted-by":"publisher","first-page":"1502","DOI":"10.3390\/electronics12061502","volume":"12","author":"F Tang","year":"2023","unstructured":"Tang, F., Yang, F., Tian, X.: Long-distance person detection based on YOLOv7. Electronics 12(6), 1502 (2023)","journal-title":"Electronics"},{"key":"3523_CR19","doi-asserted-by":"crossref","unstructured":"Han, K., et al.: Ghostnet: more features from cheap operations. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"3523_CR20","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q,V.: Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"3523_CR21","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks[C] In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3523_CR22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer vision\u2014ECCV 2018: 15th European conference, Munich, Germany, September 8\u201314, 2018, proceedings, Part VII","author":"S Woo","year":"2018","unstructured":"Woo, S., et al.: Cbam: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer vision\u2014ECCV 2018: 15th European conference, Munich, Germany, September 8\u201314, 2018, proceedings, Part VII, pp. 3\u201319. Springer International Publishing, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"3523_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Q.L., Yang, Y.B.: Sa-net: shuffle attention for deep convolutional neural networks [C]. In: ICASSP 2021\u20132021 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, 2021: 2235\u20132239","DOI":"10.1109\/ICASSP39728.2021.9414568"},{"key":"3523_CR24","unstructured":"Howard, A.G., Zhu, M., Chen, B., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications [J]. arXiv preprint arXiv:1704.04861, 2017"},{"key":"3523_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Z., Ji, S.: Smoothed dilated convolutions for improved dense prediction. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 2018 pp. 2486\u20132495","DOI":"10.1145\/3219819.3219944"},{"key":"3523_CR26","doi-asserted-by":"crossref","unstructured":"Yu F, Koltun V, Funkhouser T. Dilated residual networks [C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: pp. 472\u2013480.","DOI":"10.1109\/CVPR.2017.75"},{"key":"3523_CR27","doi-asserted-by":"crossref","unstructured":"Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Darrell, T.: Bdd100k: a diverse driving dataset for heterogeneous multitask learning. In: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), Seattle, WA, USA, 14\u201319 June 2020; pp. 2636\u20132645","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"3523_CR28","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","volume":"34","author":"P Dollar","year":"2011","unstructured":"Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34, 743\u2013761 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3523_CR29","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., et al. The cityscapes dataset for semantic urban scene understanding. In: proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 26 June\u20131 July 2016","DOI":"10.1109\/CVPR.2016.350"},{"key":"3523_CR30","unstructured":"Shao, S., Zhao, Z., Li, B., et al.: Crowdhuman: a benchmark for detecting human in a crowd [J]. arXiv preprint arXiv:1805.00123, (2018)"},{"issue":"2","key":"3523_CR31","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1007\/s11063-024-11558-4","volume":"56","author":"L Pan","year":"2024","unstructured":"Pan, L., Diao, J., Wang, Z., et al.: HF-YOLO: advanced pedestrian detection model with feature fusion and imbalance resolution. Neural Process. Lett. 56(2), 90 (2024)","journal-title":"Neural Process. Lett."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03523-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03523-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03523-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T07:21:12Z","timestamp":1730704872000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03523-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":31,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["3523"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03523-4","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2024,9,2]]},"assertion":[{"value":"9 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}