{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:42:43Z","timestamp":1789468963366,"version":"build-2803163510"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the National Key R&D Program of China","award":["2021ZD0111902"],"award-info":[{"award-number":["2021ZD0111902"]}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s00530-026-02540-2","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T10:01:48Z","timestamp":1787565708000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-guided zero-shot localization of unseen object categories"],"prefix":"10.1007","volume":"32","author":[{"given":"Jingjing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinglin","family":"Piao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongzhi","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"2540_CR1","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Yuan, L., Liu, Z., Wang, L., Li, H., Fu, Y.: Rethinking classification and localization for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10186\u201310195 (2020)","DOI":"10.1109\/CVPR42600.2020.01020"},{"issue":"9","key":"2540_CR2","doi-asserted-by":"publisher","first-page":"5866","DOI":"10.1109\/TPAMI.2021.3074313","volume":"44","author":"D Zhang","year":"2022","unstructured":"Zhang, D., Han, J., Cheng, G., Yang, M.H.: Weakly supervised object localization and detection: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5866\u20135885 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3074313","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2540_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.104986","volume":"145","author":"B Li","year":"2024","unstructured":"Li, B., Ruan, H., Li, X., Wang, K.: Feature disparity learning for weakly supervised object localization. Image Vis. Comput. 145, 104986 (2024). https:\/\/doi.org\/10.1016\/j.imavis.2024.104986","journal-title":"Image Vis. Comput."},{"key":"2540_CR4","doi-asserted-by":"crossref","unstructured":"Wang, X., You, S., Li, X., Ma, H.: Weakly-supervised semantic segmentation by iteratively mining common object features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1354\u20131362 (2018)","DOI":"10.1109\/CVPR.2018.00147"},{"issue":"10","key":"2540_CR5","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/42.887613","volume":"19","author":"M Brejl","year":"2000","unstructured":"Brejl, M., Sonka, M.: Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples. IEEE Trans. Med. Imaging 19(10), 973\u2013985 (2000)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"2540_CR6","doi-asserted-by":"crossref","unstructured":"Cho, S., Huang, J., Nam, J., An, H., Kim, S., Lee, J.-Y.: Local all-pair correspondence for point tracking. In: Proceedings of the European Conference on Computer Vision, Springer, pp. 306\u2013325 (2024)","DOI":"10.1007\/978-3-031-72684-2_18"},{"key":"2540_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107193","volume":"101","author":"R Mu\u00f1oz-Salinas","year":"2020","unstructured":"Mu\u00f1oz-Salinas, R., Medina-Carnicer, R.: Ucoslam: simultaneous localization and mapping by fusion of keypoints and squared planar markers. Pattern Recogn. 101, 107193 (2020). https:\/\/doi.org\/10.1016\/j.patcog.2019.107193","journal-title":"Pattern Recogn."},{"issue":"7","key":"2540_CR8","doi-asserted-by":"publisher","first-page":"4804","DOI":"10.1109\/TCSVT.2021.3121987","volume":"32","author":"X Tian","year":"2022","unstructured":"Tian, X., Shao, J., Ouyang, D., Shen, H.T.: Uav-satellite view synthesis for cross-view geo-localization. IEEE Trans. Circuits Syst. Video Technol. 32(7), 4804\u20134815 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2540_CR9","doi-asserted-by":"crossref","unstructured":"Choi, J., Chun, D., Kim, H., Lee, H.-J.: Gaussian yolov3: an accurate and fast object detector using localization uncertainty for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision pp. 502\u2013511 (2019)","DOI":"10.1109\/ICCV.2019.00059"},{"issue":"4","key":"2540_CR10","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/MWC.2019.1800533","volume":"26","author":"Q Luo","year":"2019","unstructured":"Luo, Q., Cao, Y., Liu, J., Benslimane, A.: Localization and navigation in autonomous driving: threats and countermeasures. IEEE Wirel. Commun. 26(4), 38\u201345 (2019)","journal-title":"IEEE Wirel. Commun."},{"key":"2540_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102429","volume":"109","author":"DK Jain","year":"2024","unstructured":"Jain, D.K., Zhao, X., Gan, C., Shukla, P.K., Jain, A., Sharma, S.: Fusion-driven deep feature network for enhanced object detection and tracking in video surveillance systems. Inform. Fusion 109, 102429 (2024)","journal-title":"Inform. Fusion"},{"issue":"4","key":"2540_CR12","doi-asserted-by":"publisher","first-page":"974","DOI":"10.1109\/TAFFC.2019.2908837","volume":"12","author":"N Bosch","year":"2019","unstructured":"Bosch, N., D\u2019mello, S.K.: Automatic detection of mind wandering from video in the lab and in the classroom. IEEE Trans. Affect. Comput. 12(4), 974\u2013988 (2019)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2540_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110260","volume":"149","author":"B Li","year":"2024","unstructured":"Li, B., Zhang, Y., Zhang, C., Piao, X., Hu, Y., Yin, B.: Multi-scale hypergraph-based feature alignment network for cell localization. Pattern Recogn. 149, 110260 (2024)","journal-title":"Pattern Recogn."},{"issue":"11s","key":"2540_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3519022","volume":"54","author":"S Antonelli","year":"2022","unstructured":"Antonelli, S., Cacace, M.G., Zappella, G., Lippiello, F.R., De Palma, P.P., Perna, M.D.: Few-shot object detection: a survey. ACM Comput. Surv. 54(11s), 1\u201337 (2022)","journal-title":"ACM Comput. Surv."},{"key":"2540_CR15","doi-asserted-by":"crossref","unstructured":"Fan, Z., Ma, Y., Li, Z., Sun, J.: Generalized few-shot object detection without forgetting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4527\u20134536 (2021)","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"2540_CR16","doi-asserted-by":"crossref","unstructured":"Zhu, C., Chen, F., Ahmed, U., Shen, Z., Savvides, M.: Semantic relation reasoning for shot-stable few-shot object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8782\u20138791 (2021)","DOI":"10.1109\/CVPR46437.2021.00867"},{"key":"2540_CR17","doi-asserted-by":"crossref","unstructured":"Kang, S., Moon, W., Kim, E., Heo, J.P.: Vlcounter: text-aware visual representation for zero-shot object counting. In: Proceedings of the ACM International Conference on Multimedia, pp. 2714\u20132722 (2024)","DOI":"10.1609\/aaai.v38i3.28050"},{"key":"2540_CR18","doi-asserted-by":"crossref","unstructured":"Shimada, K., Koyama, Y., Inoue, A.: Metric learning with background noise class for few-shot detection of rare sound events. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 616\u2013620 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054712"},{"key":"2540_CR19","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"2540_CR20","unstructured":"Lavoie, S., Kirichenko, P., Ibrahim, M., Assran, M., Wilson, A.G., Courville, A., Ballas, N.: Modeling caption diversity in contrastive vision-language pretraining. In: Proceedings of the International Conference on Machine Learning, pp. 26070\u201326084 (2024)"},{"key":"2540_CR21","doi-asserted-by":"crossref","unstructured":"Fan, Q., Pei, W., Tai, Y.W., Tang, C.K.: Self-support few-shot semantic segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 701\u2013719 (2022)","DOI":"10.1007\/978-3-031-19800-7_41"},{"key":"2540_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Shi, M., Zhao, Q., Wang, X.: Point in, box out: Beyond counting persons in crowds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6469\u20136478 (2019)","DOI":"10.1109\/CVPR.2019.00663"},{"key":"2540_CR23","doi-asserted-by":"crossref","unstructured":"Ma, Z., Yu, L., Chan, A.B.: Small instance detection by integer programming on object density maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp. 3689\u20133697 (2015)","DOI":"10.1109\/CVPR.2015.7298992"},{"key":"2540_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y., Hou, X., Chau, L.-P.: Dense point prediction: a simple baseline for crowd counting and localization. In: Proceedings of the IEEE International Conference on Multimedia, pp. 1\u20136 (2021)","DOI":"10.1109\/ICMEW53276.2021.9455954"},{"issue":"6","key":"2540_CR25","first-page":"1","volume":"19","author":"B Li","year":"2023","unstructured":"Li, B., Zhang, Y., Zhang, C., Piao, X., Yin, B.: Hypergraph association weakly supervised crowd counting. ACM Trans. Multimed. Comput. Commun. Appl. 19(6), 1\u201320 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"issue":"5","key":"2540_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3714413","volume":"21","author":"R Takezoe","year":"2025","unstructured":"Takezoe, R., Chen, H., Shen, G., Lv, X., Wang, Y., Zhang, S., Wang, X.: Context-assisted active learning for weakly supervised person search. ACM Trans. Multimedia Comput. Commun. Appl. 21(5), 1\u201320 (2025). https:\/\/doi.org\/10.1145\/3714413","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"2540_CR27","doi-asserted-by":"crossref","unstructured":"Liu, C., Weng, X., Mu, Y.: Recurrent attentive zooming for joint crowd counting and precise localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1217\u20131226 (2019)","DOI":"10.1109\/CVPR.2019.00131"},{"key":"2540_CR28","doi-asserted-by":"crossref","unstructured":"Tyagi, A.K., Mohapatra, C., Das, P., Makharia, G., Mehra, L., Mausam, P.A.P.: Degpr: deep guided posterior regularization for multi-class cell detection and counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23913\u201323923 (2023)","DOI":"10.1109\/CVPR52729.2023.02290"},{"key":"2540_CR29","doi-asserted-by":"crossref","unstructured":"Song, Q., Wang, C., Jiang, Z., Wang, Y., Tai, Y., Wang, C., Li, J., Huang, F., Wu, Y.: Rethinking counting and localization in crowds: A purely point-based framework. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3365\u20133374 (2021)","DOI":"10.1109\/ICCV48922.2021.00335"},{"issue":"12","key":"2540_CR30","doi-asserted-by":"publisher","first-page":"7530","DOI":"10.1109\/TCSVT.2023.3275382","volume":"33","author":"X Li","year":"2023","unstructured":"Li, X., Song, Q., Wu, J., Zhu, R., Ma, Z., Xue, J.-H.: Locally-enriched cross-reconstruction for few-shot fine-grained image classification. IEEE Trans. Circuits Syst. Video Technol. 33(12), 7530\u20137540 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"2540_CR31","first-page":"1","volume":"34","author":"M Lu","year":"2024","unstructured":"Lu, M., Yang, S., Lu, X., Liu, J.: Cross-modal contrastive pre-training for few-shot skeleton action recognition. IEEE Trans. Circuits Syst. Video Technol. 34(1), 1\u201312 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2540_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"},{"key":"2540_CR33","doi-asserted-by":"crossref","unstructured":"Nguyen, T., Pham, C., Nguyen, K., Hoai, M.: Few-shot object counting and detection. In: Proceedings of the European Conference on Computer Vision, Vol. 13680, pp. 348\u2013365 (2022)","DOI":"10.1007\/978-3-031-20044-1_20"},{"key":"2540_CR34","doi-asserted-by":"crossref","unstructured":"You, Z., Yang, K., Luo, W., Lu, X., Cui, L., Le, X.: Few-shot object counting with similarity-aware feature enhancement. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6315\u20136324 (2023)","DOI":"10.1109\/WACV56688.2023.00625"},{"key":"2540_CR35","unstructured":"Ren, Y., Li, B., Zhang, C., Zhang, Y., Yin, B.: Few-shot object localization, (2024) arXiv preprint arXiv:2403.12466"},{"issue":"3","key":"2540_CR36","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1109\/TCSVT.2022.3208071","volume":"33","author":"GS Xie","year":"2022","unstructured":"Xie, G.S., Zhang, Z., Xiong, H., Shao, L., Li, X.: Towards zero-shot learning: a brief review and an attention-based embedding network. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1181\u20131197 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2540_CR37","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 951\u2013958 (2009)","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"2540_CR38","unstructured":"Socher, R., Ganjoo, M., Manning, C.D., Ng, A.: Zero-shot learning through cross-modal transfer. In: Proceedings of the Neural Information Processing Systems, pp. 935\u2013943 (2013)"},{"issue":"3","key":"2540_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3617597","volume":"20","author":"A Baldrati","year":"2023","unstructured":"Baldrati, A., Bertini, M., Uricchio, T., Del Bimbo, A.: Composed image retrieval using contrastive learning and task-oriented clip-based features. ACM Trans. Multimed. Comput. Commun. Appl. 20(3), 1\u201324 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"2540_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wan, J., Chan, A.B.: Dynamic momentum adaptation for zero-shot cross-domain crowd counting. In: Proceedings of the ACM International Conference on Multimedia, pp. 658\u2013666 (2021)","DOI":"10.1145\/3474085.3475230"},{"key":"2540_CR41","doi-asserted-by":"crossref","unstructured":"Jiang, R., Liu, L., Chen, C.: Clip-count: towards text-guided zero-shot object counting. In: Proceedings of the ACM International Conference on Multimedia, pp. 4535\u20134545 (2023)","DOI":"10.1145\/3581783.3611789"},{"key":"2540_CR42","doi-asserted-by":"publisher","first-page":"48810","DOI":"10.52202\/079017-1547","volume":"37","author":"N Amini-Naieni","year":"2024","unstructured":"Amini-Naieni, N., Han, T., Zisserman, A.: Countgd: multi-modal open-world counting. Adv. Neural. Inf. Process. Syst. 37, 48810\u201348837 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2540_CR43","doi-asserted-by":"crossref","unstructured":"Huang, Z., Dai, M., Zhang, Y., et\u00a0al.: Point segment and count: a generalized framework for object counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17067\u201317076 (2024)","DOI":"10.1109\/CVPR52733.2024.01615"},{"key":"2540_CR44","doi-asserted-by":"publisher","unstructured":"Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Jiang, Q., Li, C., Yang, J., Su, H., Zhu, J., Zhang, L.: Grounding dino: marrying dino with grounded pre-training for open-set object detection, in: Proceedings of the European Conference on Computer Vision, pp. 38\u201355 (2024). https:\/\/doi.org\/10.1007\/978-3-031-72970-6_3","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"2540_CR45","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, L., Gustafson, T., Xiao, S., Whitehead, S., Berg, A.C., Lo, W.-Y., Dollar, P., Girshick, R.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2540_CR46","doi-asserted-by":"crossref","unstructured":"Dong, J., Koniusz, P., Qu, X., Ong, Y.-S.: Stabilizing modality gap & lowering gradient norms improve zero-shot adversarial robustness of vlms. In: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1, pp. 236\u2013247 (2025)","DOI":"10.1145\/3690624.3709296"},{"key":"2540_CR47","doi-asserted-by":"crossref","unstructured":"Li, L.H., Zhang, P., Zhang, H., Yang, J., Li, C., Zhong, Y., Wang, L., Yuan, L., Zhang, L., Hwang, J.-N., Chang, K.-W., Gao, J.: Grounded Language-Image Pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10955\u201310965 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"2540_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, P., Hu, X., Chen, Y.-C., Li, L.H., Dai, X., Wang, L., Yuan, L., Hwang, J.-N., Gao, J.: GLIPv2: unifying localization and vision-language understanding. In: Advances in Neural Information Processing Systems, Vol.\u00a035, pp. 36067\u201336080 (2022)","DOI":"10.52202\/068431-2614"},{"key":"2540_CR49","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Jiang, Q., Li, C., Yang, J., Su, H., Zhu, J., Zhang, L.: Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection, in: European Conference on Computer Vision, Vol. 15105, Springer, pp. 38\u201355 (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"2540_CR50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409","volume":"162","author":"Y Li","year":"2025","unstructured":"Li, Y., Wang, H., Duan, Y., Zhang, J., Li, X.: A closer look at the explainability of contrastive language-image pre-training. Pattern Recogn. 162, 111409 (2025). https:\/\/doi.org\/10.1016\/j.patcog.2025.111409","journal-title":"Pattern Recogn."},{"key":"2540_CR51","doi-asserted-by":"crossref","unstructured":"Bousselham, W., Petersen, F., Ferrari, V., Kuehne, H.: Grounding Everything: Emerging localization properties in vision-language transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3828\u20133837 (2024)","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"2540_CR52","doi-asserted-by":"publisher","first-page":"6040","DOI":"10.1109\/TMM.2022.3203870","volume":"25","author":"D Liang","year":"2023","unstructured":"Liang, D., Xu, W., Zhu, Y., Zhou, Y.: Focal inverse distance transform maps for crowd localization. IEEE Trans. Multimedia 25, 6040\u20136052 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"2540_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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 589\u2013597 (2016)","DOI":"10.1109\/CVPR.2016.70"},{"key":"2540_CR54","doi-asserted-by":"crossref","unstructured":"Hsieh, M.-R., Lin, Y.-L., Hsu, W.\u00a0H.: Drone-based object counting by spatially regularized regional proposal network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4145\u20134153 (2017)","DOI":"10.1109\/ICCV.2017.446"},{"key":"2540_CR55","unstructured":"Gao, J., Han, T., Wang, Q., Yuan, Y., Li, X.: Learning independent instance maps for crowd localization, (2022). arXiv preprint arXiv:2012.04164"},{"key":"2540_CR56","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21848\u201321859 (2023)","DOI":"10.1109\/ICCV51070.2023.01997"},{"key":"2540_CR57","doi-asserted-by":"publisher","first-page":"1802","DOI":"10.1109\/TIP.2023.3251727","volume":"32","author":"J Wang","year":"2023","unstructured":"Wang, J., Gao, J., Yuan, Y., Wang, Q.: Crowd localization from gaussian mixture scoped knowledge and scoped teacher. IEEE Trans. Image Process. 32, 1802\u20131814 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"2540_CR58","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110540","volume":"153","author":"D Tabernik","year":"2024","unstructured":"Tabernik, D., Muhovi\u010d, J., Sko\u010daj, D.: Dense center-direction regression for object counting and localization with point supervision. Pattern Recogn. 153, 110540 (2024)","journal-title":"Pattern Recogn."},{"key":"2540_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, H., Zhao, Q.: Counting and locating anything: Class-agnostic few-shot object counting and localizatio. In: Proceedings of the IEEE International Conference on Multimedia and Expo, pp. 2921\u20132926 (2023)","DOI":"10.1109\/ICME55011.2023.00496"},{"key":"2540_CR60","doi-asserted-by":"publisher","unstructured":"Liu, X., et\u00a0al.: Dynamic example network for class agnostic counting and localization, available at SSRN: https:\/\/ssrn.com\/abstract=4882210 (2024). https:\/\/doi.org\/10.2139\/ssrn.4882210","DOI":"10.2139\/ssrn.4882210"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02540-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02540-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02540-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T09:14:48Z","timestamp":1789463688000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02540-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":60,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["2540"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02540-2","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"6 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"534"}}