{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T13:08:37Z","timestamp":1754399317457,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T00:00:00Z","timestamp":1618444800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T00:00:00Z","timestamp":1618444800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 61771420"],"award-info":[{"award-number":["No. 61771420"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of Hebei Province","award":["No. F2020203064"],"award-info":[{"award-number":["No. F2020203064"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["No. 2018M641674"],"award-info":[{"award-number":["No. 2018M641674"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012470","name":"Doctoral Program Foundation of Institutions of Higher Education of China","doi-asserted-by":"crossref","award":["No. BL18033"],"award-info":[{"award-number":["No. BL18033"]}],"id":[{"id":"10.13039\/501100012470","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1007\/s11760-021-01903-8","type":"journal-article","created":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T19:03:45Z","timestamp":1618513425000},"page":"1663-1670","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Cascade-guided multi-scale attention network for crowd counting"],"prefix":"10.1007","volume":"15","author":[{"given":"Shufang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0300-6144","authenticated-orcid":false,"given":"Zhengping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,15]]},"reference":[{"key":"1903_CR1","doi-asserted-by":"crossref","unstructured":"O\u00f1oro-Rubio, D., L\u00f3pez-Sastre, R.J.: Towards perspective-free object counting with deep learning. In: European Conference on Computer Vision, 11\u201314 October, Amsterdam, pp. 615\u2013629. Springer, Amsterdam (2016)","DOI":"10.1007\/978-3-319-46478-7_38"},{"key":"1903_CR2","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Patel, V.M.: Cnn-based cascaded multitask learning of high-level prior and density estimation for crowd counting. In: IEEE International Conference on Advanced Video and Signal Based Surveillance, 29 August\u20131 September, pp. 1\u20136. IEEE, Lecce (2017)","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"1903_CR3","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.image.2018.03.004","volume":"64","author":"B Yang","year":"2018","unstructured":"Yang, B., Cao, J., Wang, N., Zhang, Y., Zou, L.: Counting challenging crowds robustly using a multi-column multi-task convolutional neural network. Sig. Process. Image Commun. 64, 118\u2013129 (2018)","journal-title":"Sig. Process. Image Commun."},{"key":"1903_CR4","doi-asserted-by":"crossref","unstructured":"Liu, W., Salzmann, M., Fua, P.: Context-aware crowd counting. In: IEEE, CVF Conference on Computer Vision and Pattern Recognition, 15\u201320, Long Beach, pp. 5094\u20135103. IEEE, California (2019)","DOI":"10.1109\/CVPR.2019.00524"},{"key":"1903_CR5","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1109\/TII.2019.2935244","volume":"16","author":"J Li","year":"2020","unstructured":"Li, J., Xue, Y., Wang, W., Ouyang, G.: Cross-level parallel network for crowd counting. IEEE Trans. Ind. Inf. 16, 566\u2013576 (2020)","journal-title":"IEEE Trans. Ind. Inf."},{"key":"1903_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., Yi, M.: Single-image crowd counting via multi-column convolutional neural network. In: IEEE Conference on Computer Vision and Pattern Recognition, 27\u201330, Las Vegas, pp. 589\u2013597. IEEE, Nevada (2016)","DOI":"10.1109\/CVPR.2016.70"},{"key":"1903_CR7","unstructured":"Kang, D., Chan, A.: Crowd counting by adaptively fusing predictions from an image pyramid. In: 29th British Machine Vision Conference, pp. 2\u20136. Springer, Newcastle (2018)"},{"key":"1903_CR8","doi-asserted-by":"crossref","unstructured":"Liu, N., Long, Y., Zou, C.: ADCrowdNet: an attention-injective deformable convolutional network for crowd understanding. In: IEEE, CVF Conference on Computer Vision and Pattern Recognition, 15\u201320, Long Beach, pp. 3220\u20133229. IEEE, California (2019)","DOI":"10.1109\/CVPR.2019.00334"},{"key":"1903_CR9","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, X., Chen, D.: CSRNet: dilated convolutional neural networks for understanding the highly congested scenes. In: IEEE, CVF Conference on Computer Vision and Pattern Recognition, 18\u201322, Salt Lake, pp. 1091\u20131100. IEEE, Utah (2018)","DOI":"10.1109\/CVPR.2018.00120"},{"key":"1903_CR10","unstructured":"Zan, S., Yi, X., Ni, B., Wang, M., Yang, X.: Crowd counting via adversarial cross-scale consistency pursuit. In: IEEE, CVF Conference on Computer Vision and Pattern Recognition, 18\u201322, Salt Lake, pp. 5245\u20135254. IEEE, Utah (2018)"},{"key":"1903_CR11","doi-asserted-by":"publisher","first-page":"3486","DOI":"10.1109\/TCSVT.2019.2919139","volume":"30","author":"J Gao","year":"2019","unstructured":"Gao, J., Wang, Q., Li, X.: PCC Net: perspective crowd counting via spatial convolutional network. IEEE Trans. Circuits Syst. Video 30, 3486\u20133498 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video"},{"key":"1903_CR12","doi-asserted-by":"crossref","unstructured":"Pan, X., Shi, J., Luo, P., Wang, X., Tang, X.: Spatial as deep: spatial cnn for traffic scene understanding. In: 32nd AAAI Conference on Artificial Intelligence, 2\u20137, New Orleans, pp. 7276\u20137283. AAAI, Los Angeles (2018)","DOI":"10.1609\/aaai.v32i1.12301"},{"key":"1903_CR13","doi-asserted-by":"crossref","unstructured":"Miao, Y., Lin, Z., Ding, G., Han, J.: Shallow feature based dense attention network for crowd counting. In: 34th AAAI Conference on Artificial Intelligence, pp. 7\u201312. AAAI, New York (2020)","DOI":"10.1609\/aaai.v34i07.6848"},{"key":"1903_CR14","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: 31st Annual Conference on Neural Information Processing Systems, 4\u20139, Long Beach, pp. 5998\u20136008. NIPS, California (2017)"},{"key":"1903_CR15","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshich, R., Gupta, A., He, K.: Networks, non-local neural. In: IEEE, CVF Conference on Computer Vision and Pattern Recognition, 18\u201322, Salt Lake. IEEE, Utah (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1903_CR16","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: IEEE, CVF Conference on Computer Vision and Pattern Recognition, 15\u201320, Long Beach, pp. 3141\u20133149. IEEE, California (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1903_CR17","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Patel, V.M.: Generating high-quality crowd density maps using contextual pyramid CNNs. In: IEEE International Conference on Computer Vision, 22\u201329, Venice, pp. 1879\u20131888. IEEE, Italy (2017)","DOI":"10.1109\/ICCV.2017.206"},{"key":"1903_CR18","doi-asserted-by":"crossref","unstructured":"Sam, D.B., Surya, S., Babu, R.V.: Switching convolutional neural network for crowd counting. In: IEEE, CVF Conference on Computer Vision and Pattern Recognition, 21\u201326, Honolulu, pp. 4031\u20134039. IEEE, Hawaii (2017)","DOI":"10.1109\/CVPR.2017.429"},{"key":"1903_CR19","doi-asserted-by":"crossref","unstructured":"Cao, X., Wang, Z., Zhao, Y., Su, F.: Scale aggregation network for accurate and efficient crowd counting. In: European Conference on Computer Vision, 8\u201314 September, Munich, pp. 734\u2013750. Springer, Germany (2018)","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"1903_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2019.08.018","volume":"363","author":"J Gao","year":"2019","unstructured":"Gao, J., Wang, Q., Yuan, Y.: SCAR: spatial-\/channel-wise attention regression networks for crowd counting. Neurocomputing 363, 1\u20138 (2019)","journal-title":"Neurocomputing"},{"key":"1903_CR21","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: European Conference on Computer Vision, 8C14, Munich, pp. 3\u201319. Springer, Germany (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1903_CR22","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/j.neucom.2019.11.064","volume":"382","author":"J Chen","year":"2020","unstructured":"Chen, J., Su, W., Wang, Z.: Crowd counting with crowd attention convolutional neural network. Neurocomputing 382, 210\u2013220 (2020)","journal-title":"Neurocomputing"},{"key":"1903_CR23","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Patel, V.M.: Inverse attention guided deep crowd counting network. In: 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, 18\u201321, Taipei, pp. 1\u20138. AVSS, Taiwan (2019)","DOI":"10.1109\/AVSS.2019.8909889"},{"key":"1903_CR24","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.neucom.2019.12.070","volume":"384","author":"Z Dong","year":"2019","unstructured":"Dong, Z., Zhang, R., Shao, X., Li, Y.: Scale-recursive network with point supervision for crowd scene analysis. Neurocomputing 384, 314\u2013324 (2019)","journal-title":"Neurocomputing"},{"key":"1903_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, X., Xiao, Z., Zhang, B., Zhen, X., Cao, X., Doermann, D.S., Shao, L.: Crowd counting and density estimation by trellis encoder-decoder networks. In: IEEE, CVF Conference on Computer Vision and Pattern Recognition, 15\u201320, Long Beach, pp. 6133\u20136142. IEEE, California (2019)","DOI":"10.1109\/CVPR.2019.00629"},{"key":"1903_CR26","doi-asserted-by":"publisher","first-page":"3499","DOI":"10.1109\/TCSVT.2020.2978717","volume":"30","author":"U Sajid","year":"2020","unstructured":"Sajid, U., Sajid, H., Wang, H., Wang, G.: Zoom count: a zooming mechanism for crowd counting in static images. IEEE Trans. Circuits Syst. Video 30, 3499\u20133512 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video"},{"key":"1903_CR27","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 640\u2013651 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1903_CR28","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2007","unstructured":"Ren, S., He, K., Girshick, R., Jian, S.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1903_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations, 7\u20139, San Diego. ICLR, California (2015)"},{"key":"1903_CR30","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37, 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1903_CR31","doi-asserted-by":"crossref","unstructured":"Idrees, H., Saleemi, I., Seibert, C., Shah, M.: Multi-source multi-scale counting in extremely dense crowd images. In: IEEE, CVF Conference on Computer Vision and Pattern Recognition, 23\u201328, Portland, pp. 2547\u20132554. IEEE, Oregon (2013)","DOI":"10.1109\/CVPR.2013.329"},{"key":"1903_CR32","doi-asserted-by":"crossref","unstructured":"Idrees, H., Tayyab, M., Athrey, K., Dong, Z., Shah, M.: Composition loss for counting, density map estimation and localization in dense crowds. In: European Conference on Computer Vision, 8\u201314 September, Munich, pp. 544\u2013559. Springer, Germany (2018)","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"1903_CR33","unstructured":"Zhang, C., Li, H., Wang, X., Yang, X.: Cross-scene crowd counting via deep convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, 7\u201312, Boston, pp. 833\u2013841. IEEE, MA (2015)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-01903-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-021-01903-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-01903-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T12:54:59Z","timestamp":1724849699000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-021-01903-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,15]]},"references-count":33,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["1903"],"URL":"https:\/\/doi.org\/10.1007\/s11760-021-01903-8","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2021,4,15]]},"assertion":[{"value":"23 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}