{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T02:48:19Z","timestamp":1769741299094,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556953","type":"print"},{"value":"9789819556960","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5696-0_15","type":"book-chapter","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T14:02:55Z","timestamp":1769695375000},"page":"211-224","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Boosting CNN Backbones for\u00a0Crowd Counting via\u00a0Mamba Learning Paradigm"],"prefix":"10.1007","author":[{"given":"Zhuohang","family":"Li","sequence":"first","affiliation":[]},{"given":"Song","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Mingjie","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, S., Zheng, X., Zhao, X., Kong, Y.: Crowd counting based on multiscale spatial guided perception aggregation network. TNNLS (2023)","DOI":"10.1109\/TNNLS.2023.3304348"},{"key":"15_CR2","first-page":"2862","volume":"30","author":"J Cheng","year":"2021","unstructured":"Cheng, J., Xiong, H., Cao, Z., Lu, H.: Decoupled two-stage crowd counting and beyond. TIP 30, 2862\u20132875 (2021)","journal-title":"TIP"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Dai, Q., Li, H., Song, J., Wu, X., Hauptmann, A.G.: Rethinking spatial invariance of convolutional networks for object counting. In: CVPR, pp. 19638\u201319648 (2022)","DOI":"10.1109\/CVPR52688.2022.01902"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Du, Z., Shi, M., Deng, J., Zafeiriou, S.: Redesigning multi-scale neural network for crowd counting. TIP (2023)","DOI":"10.1109\/TIP.2023.3289290"},{"key":"15_CR5","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Han, T., Bai, L., Liu, L., Ouyang, W.: Steerer: Resolving scale variations for counting and localization via selective inheritance learning. In: ICCV, pp. 21848\u201321859 (2023)","DOI":"10.1109\/ICCV51070.2023.01997"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Idrees, H., et al.: Composition loss for counting, density map estimation and localization in dense crowds. In: ECCV, pp. 532\u2013546 (2018)","DOI":"10.1007\/978-3-030-01216-8_33"},{"issue":"8","key":"15_CR8","first-page":"2705","volume":"31","author":"X Jiang","year":"2019","unstructured":"Jiang, X., et al.: Learning multi-level density maps for crowd counting. TNNLS 31(8), 2705\u20132715 (2019)","journal-title":"TNNLS"},{"key":"15_CR9","unstructured":"Jiang, X., et al.: Attention scaling for crowd counting. In: CVPR, pp. 4706\u20134715 (2020)"},{"key":"15_CR10","unstructured":"Kingma, D.P.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Lin, H., Ma, Z., Ji, R., Wang, Y., Hong, X.: Boosting crowd counting via multifaceted attention. In: CVPR, pp. 19628\u201319637 (2022)","DOI":"10.1109\/CVPR52688.2022.01901"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Liu, W., Salzmann, M., Fua, P.: Context-aware crowd counting. In: CVPR, pp. 5099\u20135108 (2019)","DOI":"10.1109\/CVPR.2019.00524"},{"key":"15_CR13","unstructured":"Ma, H.Y., Zhang, L., Shi, S.: Vmambacc: A visual state space model for crowd counting. arXiv preprint arXiv:2405.03978 (2024)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Ma, Y., Sanchez, V., Guha, T.: Fusioncount: Efficient crowd counting via multiscale feature fusion. In: ICIP, pp. 3256\u20133260. IEEE (2022)","DOI":"10.1109\/ICIP46576.2022.9897322"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Ma, Z., Hong, X., Wei, X., Qiu, Y., Gong, Y.: Towards a universal model for cross-dataset crowd counting. In: ICCV, pp. 3205\u20133214 (2021)","DOI":"10.1109\/ICCV48922.2021.00319"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, X., Hong, X., Gong, Y.: Bayesian loss for crowd count estimation with point supervision. In: ICCV, pp. 6142\u20136151 (2019)","DOI":"10.1109\/ICCV.2019.00624"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Miao, Y., Lin, Z., Ding, G., Han, J.: Shallow feature based dense attention network for crowd counting. In: AAAI. vol.\u00a034, pp. 11765\u201311772 (2020)","DOI":"10.1609\/aaai.v34i07.6848"},{"key":"15_CR18","unstructured":"Qian, Y., et al.: Segmentation assisted u-shaped multi-scale transformer for crowd counting. In: BMVC, p.\u00a0397 (2022)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Rong, L., Li, C.: Coarse-and fine-grained attention network with background-aware loss for crowd density map estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3675\u20133684 (2021)","DOI":"10.1109\/WACV48630.2021.00372"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Ruan, J., Xiang, S.: Vm-unet: Vision mamba Unet for medical image segmentation. arXiv preprint arXiv:2402.02491 (2024)","DOI":"10.1145\/3767748"},{"issue":"8","key":"15_CR21","first-page":"2739","volume":"43","author":"DB Sam","year":"2020","unstructured":"Sam, D.B., Peri, S.V., Sundararaman, M.N., Kamath, A., Babu, R.V.: Locate, size, and count: accurately resolving people in dense crowds via detection. TPAMI 43(8), 2739\u20132751 (2020)","journal-title":"TPAMI"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Shu, W., Wan, J., Tan, K.C., Kwong, S., Chan, A.B.: Crowd counting in the frequency domain. In: CVPR, pp. 19618\u201319627 (2022)","DOI":"10.1109\/CVPR52688.2022.01900"},{"issue":"5","key":"15_CR23","first-page":"2594","volume":"44","author":"VA Sindagi","year":"2020","unstructured":"Sindagi, V.A., Yasarla, R., Patel, V.M.: Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method. TPAMI 44(5), 2594\u20132609 (2020)","journal-title":"TPAMI"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Song, Q., et al.: Rethinking counting and localization in crowds: A purely point-based framework. In: ICCV, pp. 3365\u20133374 (2021)","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"15_CR25","unstructured":"Tran, N.H., et al.: Improving local features with relevant spatial information by vision transformer for crowd counting. In: BMVC, p.\u00a0729 (2022)"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Wan, J., Liu, Z., Chan, A.B.: A generalized loss function for crowd counting and localization. In: CVPRm pp. 1974\u20131983 (2021)","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"15_CR27","unstructured":"Wang, B., Liu, H., Samaras, D., Hoai, M.: Distribution matching for crowd counting. arXiv preprint arXiv:2009.13077 (2020)"},{"key":"15_CR28","first-page":"2074","volume":"25","author":"M Wang","year":"2022","unstructured":"Wang, M., Cai, H., Han, X.F., Zhou, J., Gong, M.: Stnet: Scale tree network with multi-level auxiliator for crowd counting. TMM 25, 2074\u20132084 (2022)","journal-title":"TMM"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Q., Gao, J., Lin, W., Yuan, Y.: Learning from synthetic data for crowd counting in the wild. In: CVPR, pp. 8198\u20138207 (2019)","DOI":"10.1109\/CVPR.2019.00839"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Xiong, H., Lu, H., Liu, C., Liu, L., Cao, Z., Shen, C.: From open set to closed set: Counting objects by spatial divide-and-conquer. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00845"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Yang, S., Guo, W., Ren, Y.: Crowdformer: An overlap patching vision transformer for top-down crowd counting. In: IJCAI. vol.\u00a01, p.\u00a02 (2022)","DOI":"10.24963\/ijcai.2022\/215"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: CVPR, pp. 589\u2013597 (2016)","DOI":"10.1109\/CVPR.2016.70"},{"key":"15_CR33","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5696-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T14:03:06Z","timestamp":1769695386000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5696-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556953","9789819556960"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5696-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"30 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}