{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T00:55:20Z","timestamp":1763686520966,"version":"3.40.3"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729973"},{"type":"electronic","value":"9783031729980"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72998-0_27","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T18:01:58Z","timestamp":1727632918000},"page":"478-495","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Robust Zero-Shot Crowd Counting and\u00a0Localization With Adaptive Resolution SAM"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8198-1629","authenticated-orcid":false,"given":"Jia","family":"Wan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3847-7838","authenticated-orcid":false,"given":"Qiangqiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8425-956X","authenticated-orcid":false,"given":"Wei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2886-2513","authenticated-orcid":false,"given":"Antoni","family":"Chan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"27_CR1","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1007\/978-3-031-19821-2_11","volume-title":"Computer Vision \u2013 ECCV 2022","author":"D Babu Sam","year":"2022","unstructured":"Babu Sam, D., Agarwalla, A., Joseph, J., Sindagi, V.A., Babu, R.V., Patel, V.M.: Completely self-supervised crowd counting via distribution matching. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13691, pp. 186\u2013204. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_11"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Babu\u00a0Sam, D., Surya, S., Venkatesh\u00a0Babu, R.: Switching convolutional neural network for crowd counting. In: CVPR, pp. 5744\u20135752 (2017)","DOI":"10.1109\/CVPR.2017.429"},{"issue":"12","key":"27_CR3","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE TPAMI 39(12), 2481\u20132495 (2017)","journal-title":"IEEE TPAMI"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Chan, A.B., Liang, Z.S.J., Vasconcelos, N.: Privacy preserving crowd monitoring: counting people without people models or tracking. In: CVPR, pp.\u00a01\u20137. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Chan, A.B., Vasconcelos, N.: Bayesian poisson regression for crowd counting. In: CVPR, pp. 545\u2013551. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459191"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Change\u00a0Loy, C., Gong, S., Xiang, T.: From semi-supervised to transfer counting of crowds. In: ICCV, pp. 2256\u20132263 (2013)","DOI":"10.1109\/ICCV.2013.270"},{"key":"27_CR7","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19638\u201319648 (2022)","DOI":"10.1109\/CVPR52688.2022.01902"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Li, J.X., Dai, Q., Wu, X., Hauptmann, A.G.: Learning spatial awareness to improve crowd counting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6152\u20136161 (2019)","DOI":"10.1109\/ICCV.2019.00625"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Li, J.X., Dai, Q., Wu, X., He, J.Y., Hauptmann, A.G.: Improving the learning of multi-column convolutional neural network for crowd counting. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1897\u20131906 (2019)","DOI":"10.1145\/3343031.3350898"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Ge, W., Collins, R.T.: Marked point processes for crowd counting. In: CVPR, pp. 2913\u20132920. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206621"},{"key":"27_CR11","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":"27_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR13","unstructured":"Hobley, M., Prisacariu, V.: Learning to count anything: reference-less class-agnostic counting with weak supervision. arXiv preprint arXiv:2205.10203 (2022)"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Huang, S., Li, X., Cheng, Z.Q., Zhang, Z., Hauptmann, A.: Stacked pooling for boosting scale invariance of crowd counting. In: ICASSP, pp. 2578\u20132582. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053070"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Idrees, H., Saleemi, I., Seibert, C., Shah, M.: Multi-source multi-scale counting in extremely dense crowd images. In: CVPR, pp. 2547\u20132554 (2013)","DOI":"10.1109\/CVPR.2013.329"},{"key":"27_CR17","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"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, R., Liu, L., Chen, C.: Clip-count: towards text-guided zero-shot object counting. arXiv preprint arXiv:2305.07304 (2023)","DOI":"10.1145\/3581783.3611789"},{"key":"27_CR19","unstructured":"Kang, D., Chan, A.B.: Crowd counting by adaptively fusing predictions from an image pyramid. In: BMVC, pp. 89 (2018)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"LI, C., Hu, X., Abousamra, S., Chen, C.: Calibrating uncertainty for semi-supervised crowd counting. In: ICCV, pp. 16731\u201316741 (2023)","DOI":"10.1109\/ICCV51070.2023.01534"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, X., Chen, D.: Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1091\u20131100 (2018)","DOI":"10.1109\/CVPR.2018.00120"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Liang, D., Xie, J., Zou, Z., Ye, X., Xu, W., Bai, X.: Crowdclip: unsupervised crowd counting via vision-language model. In: CVPR, pp. 2893\u20132903 (2023)","DOI":"10.1109\/CVPR52729.2023.00283"},{"key":"27_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-031-19769-7_3","volume-title":"Computer Vision \u2013 ECCV 2022","author":"D Liang","year":"2022","unstructured":"Liang, D., Xu, W., Bai, X.: An end-to-end transformer model for crowd localization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. LNCS, vol. 13661, pp. 38\u201354. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_3"},{"key":"27_CR25","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":"27_CR26","doi-asserted-by":"crossref","unstructured":"Lin, W., Chan, A.B.: Optimal transport minimization: crowd localization on density maps for semi-supervised counting. In: CVPR, pp. 21663\u201321673 (2023)","DOI":"10.1109\/CVPR52729.2023.02075"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Liu, C., Lu, H., Cao, Z., Liu, T.: Point-query quadtree for crowd counting, localization, and more. In: ICCV, pp. 1676\u20131685 (2023)","DOI":"10.1109\/ICCV51070.2023.00161"},{"key":"27_CR28","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":"27_CR29","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":"27_CR30","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, X., Hong, X., Lin, H., Qiu, Y., Gong, Y.: learning to count via unbalanced optimal transport. In: AAAI. vol.35, pp. 2319\u20132327 (2021)","DOI":"10.1609\/aaai.v35i3.16332"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Meng, Y., Zhang, H., Zhao, Y., Yang, X., Qian, X., Huang, X., Zheng, Y.: Spatial uncertainty-aware semi-supervised crowd counting. In: ICCV, pp. 15549\u201315559 (2021)","DOI":"10.1109\/ICCV48922.2021.01526"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Sharma, U., Nguyen, T., Hoai, M.: Learning to count everything. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3394\u20133403 (2021)","DOI":"10.1109\/CVPR46437.2021.00340"},{"issue":"8","key":"27_CR33","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. IEEE TPAMI 43(8), 2739\u20132751 (2020)","journal-title":"IEEE TPAMI"},{"key":"27_CR34","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"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Patel, V.M.: Generating high-quality crowd density maps using contextual pyramid cnns. In: ICCV, pp. 1861\u20131870 (2017)","DOI":"10.1109\/ICCV.2017.206"},{"issue":"5","key":"27_CR36","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. IEEE TPAMI 44(5), 2594\u20132609 (2020)","journal-title":"IEEE TPAMI"},{"key":"27_CR37","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":"27_CR38","doi-asserted-by":"crossref","unstructured":"Wan, J., Chan, A.: Adaptive density map generation for crowd counting. In: ICCV, pp. 1130\u20131139 (2019)","DOI":"10.1109\/ICCV.2019.00122"},{"key":"27_CR39","first-page":"3386","volume":"33","author":"J Wan","year":"2020","unstructured":"Wan, J., Chan, A.: Modeling noisy annotations for crowd counting. NeurIPS 33, 3386\u20133396 (2020)","journal-title":"NeurIPS"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Wan, J., Liu, Z., Chan, A.B.: A generalized loss function for crowd counting and localization. In: CVPR, pp. 1974\u20131983 (2021)","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Wan, J., Luo, W., Wu, B., Chan, A.B., Liu, W.: Residual regression with semantic prior for crowd counting. In: CVPR, pp. 4036\u20134045 (2019)","DOI":"10.1109\/CVPR.2019.00416"},{"issue":"3","key":"27_CR42","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1109\/TPAMI.2020.3022878","volume":"44","author":"J Wan","year":"2020","unstructured":"Wan, J., Wang, Q., Chan, A.B.: Kernel-based density map generation for dense object counting. IEEE TPAMI 44(3), 1357\u20131370 (2020)","journal-title":"IEEE TPAMI"},{"issue":"12","key":"27_CR43","doi-asserted-by":"publisher","first-page":"15065","DOI":"10.1109\/TPAMI.2023.3299753","volume":"45","author":"J Wan","year":"2023","unstructured":"Wan, J., Wu, Q., Chan, A.B.: Modeling noisy annotations for point-wise supervision. IEEE TPAMI 45(12), 15065\u201315080 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3299753","journal-title":"IEEE TPAMI"},{"key":"27_CR44","first-page":"1595","volume":"33","author":"B Wang","year":"2020","unstructured":"Wang, B., Liu, H., Samaras, D., Nguyen, M.H.: Distribution matching for crowd counting. NeurIPS 33, 1595\u20131607 (2020)","journal-title":"Distribution matching for crowd counting. NeurIPS"},{"key":"27_CR45","unstructured":"Wang, H., Cheng, Z.Q., Du, Y., Zhang, L.: Ivac-p2l: leveraging irregular repetition priors for improving video action counting (2024). https:\/\/arxiv.org\/abs\/2403.11959"},{"key":"27_CR46","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":"27_CR47","doi-asserted-by":"publisher","first-page":"5220","DOI":"10.1109\/TIP.2023.3313490","volume":"32","author":"X Wei","year":"2023","unstructured":"Wei, X., Qiu, Y., Ma, Z., Hong, X., Gong, Y.: Semi-supervised crowd counting via multiple representation learning. IEEE TIP 32, 5220\u20135230 (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3313490","journal-title":"IEEE TIP"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wan, J., Chan, A.B.: Dynamic momentum adaptation for zero-shot cross-domain crowd counting. In: ACM MM, pp. 658\u2013666 (2021)","DOI":"10.1145\/3474085.3475230"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Xiong, F., Shi, X., Yeung, D.Y.: Spatiotemporal modeling for crowd counting in videos. In: ICCV, pp. 5151\u20135159 (2017)","DOI":"10.1109\/ICCV.2017.551"},{"key":"27_CR50","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Crowd counting with partial annotations in an image. In: ICCV, pp. 15570\u201315579 (2021)","DOI":"10.1109\/ICCV48922.2021.01528"},{"key":"27_CR51","unstructured":"Zhang, C., Li, H., Wang, X., Yang, X.: Cross-scene crowd counting via deep convolutional neural networks. In: CVPR, pp. 833\u2013841 (2015)"},{"key":"27_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, J., Cheng, Z.Q., Wu, X., Li, W., Qiao, J.J.: Crossnet: boosting crowd counting with localization. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 6436\u20136444 (2022)","DOI":"10.1145\/3503161.3547863"},{"key":"27_CR53","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":"27_CR54","unstructured":"Zhu, J., et al.: Tracking with human-intent reasoning (2023), https:\/\/arxiv.org\/abs\/2312.17448"},{"key":"27_CR55","unstructured":"Zou, X., Yang, J., Zhang, H., Li, F., Li, L., Gao, J., Lee, Y.J.: Segment everything everywhere all at once. arXiv preprint arXiv:2304.06718 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72998-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:28:23Z","timestamp":1732829303000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72998-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031729973","9783031729980"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72998-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}