{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T16:16:35Z","timestamp":1788970595139,"version":"build-2803163510"},"reference-count":65,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0111902"],"award-info":[{"award-number":["2021ZD0111902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472014"],"award-info":[{"award-number":["62472014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.cviu.2026.104878","type":"journal-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:19:27Z","timestamp":1785338367000},"page":"104878","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["LocSAM: Modular SAM enhancement for dense object localization in complex scenes"],"prefix":"10.1016","volume":"271","author":[{"given":"Jingjing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0608-1502","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongli","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-9519","authenticated-orcid":false,"given":"Bob","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"22","key":"10.1016\/j.cviu.2026.104878_b1","doi-asserted-by":"crossref","first-page":"4175","DOI":"10.3390\/rs16224175","article-title":"Enhanced YOLOv8-based model with context enrichment module for crowd counting in complex drone imagery","volume":"16","author":"Alhawsawi","year":"2024","journal-title":"Remote. Sens."},{"key":"10.1016\/j.cviu.2026.104878_b2","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"640","article-title":"CrowdNet: A deep convolutional network for dense crowd counting","author":"Boominathan","year":"2016"},{"key":"10.1016\/j.cviu.2026.104878_b3","doi-asserted-by":"crossref","unstructured":"Cao,\u00a0X., Wang,\u00a0Z., Zhao,\u00a0Y., Su,\u00a0F., 2018. Scale aggregation network for accurate and efficient crowd counting. In: Proceedings of the European Conference on Computer Vision. ECCV, pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"10.1016\/j.cviu.2026.104878_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107089","article-title":"CrowdDCNN: Deep convolution neural network for real-time crowd counting on IoT edge","volume":"126","author":"Chavan","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.cviu.2026.104878_b5","unstructured":"Chen,\u00a0Z., Wang,\u00a0X., Jia,\u00a0K., 2022. AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 10976\u201310986."},{"key":"10.1016\/j.cviu.2026.104878_b6","doi-asserted-by":"crossref","first-page":"2862","DOI":"10.1109\/TIP.2021.3055631","article-title":"Decoupled two-stage crowd counting and beyond","volume":"30","author":"Cheng","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2026.104878_b7","series-title":"Learning independent instance maps for crowd localization","author":"Gao","year":"2020"},{"key":"10.1016\/j.cviu.2026.104878_b8","article-title":"Combining SAM with limited data for change detection in remote sensing","volume":"63","author":"Gao","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cviu.2026.104878_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112481","article-title":"Dynamic proxy domain generalizes the crowd localization by better binary segmentation","volume":"172","author":"Gao","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cviu.2026.104878_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111826","article-title":"COD-SAM: Camouflage object detection using SAM","volume":"168","author":"Gao","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cviu.2026.104878_b11","doi-asserted-by":"crossref","unstructured":"Han,\u00a0T., Bai,\u00a0L., Liu,\u00a0L., Ouyang,\u00a0W., 2023. Steerer: Resolving scale variations for counting and localization via selective inheritance learning. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 21848\u201321859.","DOI":"10.1109\/ICCV51070.2023.01997"},{"key":"10.1016\/j.cviu.2026.104878_b12","series-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"10.1016\/j.cviu.2026.104878_b13","doi-asserted-by":"crossref","unstructured":"Idrees,\u00a0H., Tayyab,\u00a0M., Athrey,\u00a0K., Zhang,\u00a0D., Almahairi,\u00a0S., Al-Senawi,\u00a0M., Rajpoot,\u00a0N., Shah,\u00a0M., 2018. Composition loss for counting, density map estimation and localization in dense crowds. In: Proceedings of the European Conference on Computer Vision. ECCV, Munich, Germany, pp. 532\u2013546.","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"10.1016\/j.cviu.2026.104878_b14","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.cviu.2026.104878_b15","unstructured":"Jiang,\u00a0W., Han,\u00a0X., Wei,\u00a0P., Xiong,\u00a0H., 2019. TEDnet: A trellis encoder-decoder network for crowd counting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 11358\u201311367."},{"key":"10.1016\/j.cviu.2026.104878_b16","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"4535","article-title":"CLIP-count: Towards text-guided zero-shot object counting","author":"Jiang","year":"2023"},{"issue":"1","key":"10.1016\/j.cviu.2026.104878_b17","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.2991\/ijcis.d.210326.001","article-title":"Multi-scale person localization with multi-stage deep sequential framework","volume":"14","author":"Khan","year":"2021","journal-title":"Int. J. Comput. Intell. Syst."},{"issue":"8","key":"10.1016\/j.cviu.2026.104878_b18","doi-asserted-by":"crossref","first-page":"2127","DOI":"10.1007\/s00371-020-01974-7","article-title":"Scale and density invariant head detection deep model for crowd counting in pedestrian crowds","volume":"37","author":"Khan","year":"2021","journal-title":"Vis. Comput."},{"key":"10.1016\/j.cviu.2026.104878_b19","series-title":"2023 IEEE\/CVF International Conference on Computer Vision","first-page":"3992","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.cviu.2026.104878_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108898","article-title":"Cross-modal misalignment-robust feature fusion for crowd counting","volume":"136","author":"Kong","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.cviu.2026.104878_b21","series-title":"Advances in Neural Information Processing Systems","first-page":"1324","article-title":"Learning to count objects in images","volume":"Vol. 23","author":"Lempitsky","year":"2010"},{"issue":"12","key":"10.1016\/j.cviu.2026.104878_b22","doi-asserted-by":"crossref","first-page":"9904","DOI":"10.1109\/TPAMI.2021.3132068","article-title":"CTNet: Context-based tandem network for semantic segmentation","volume":"44","author":"Li","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104878_b23","doi-asserted-by":"crossref","unstructured":"Li,\u00a0Y., Zhang,\u00a0X., Chen,\u00a0D., 2018. CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 1091\u20131100.","DOI":"10.1109\/CVPR.2018.00120"},{"issue":"7","key":"10.1016\/j.cviu.2026.104878_b24","doi-asserted-by":"crossref","first-page":"2671","DOI":"10.1007\/s00371-022-02485-3","article-title":"CCST: Crowd counting with swin transformer","volume":"39","author":"Li","year":"2023","journal-title":"Vis. Comput."},{"key":"10.1016\/j.cviu.2026.104878_b25","unstructured":"Li,\u00a0K., Zhang,\u00a0L., Yang,\u00a0D., 2023. GMS: Geometry-aware multi-scale learning for crowd counting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR."},{"issue":"6","key":"10.1016\/j.cviu.2026.104878_b26","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-021-3445-y","article-title":"TransCrowd: Weakly-supervised crowd counting with transformers","volume":"65","author":"Liang","year":"2022","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.cviu.2026.104878_b27","doi-asserted-by":"crossref","unstructured":"Liang,\u00a0D., Xie,\u00a0J., Zou,\u00a0Z., Ye,\u00a0X., Xu,\u00a0W., Bai,\u00a0X., 2023a. CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 2893\u20132903.","DOI":"10.1109\/CVPR52729.2023.00283"},{"key":"10.1016\/j.cviu.2026.104878_b28","doi-asserted-by":"crossref","first-page":"6040","DOI":"10.1109\/TMM.2022.3203870","article-title":"Focal inverse distance transform maps for crowd localization","volume":"25","author":"Liang","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104878_b29","first-page":"1","article-title":"Consistency-aware anchor pyramid network for crowd localization","author":"Liu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104878_b30","doi-asserted-by":"crossref","unstructured":"Liu,\u00a0C., Lu,\u00a0H., Cao,\u00a0Z., Liu,\u00a0T., 2023. Point-query quadtree for crowd counting, localization, and more. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 1676\u20131685.","DOI":"10.1109\/ICCV51070.2023.00161"},{"key":"10.1016\/j.cviu.2026.104878_b31","doi-asserted-by":"crossref","unstructured":"Liu,\u00a0L., Wei,\u00a0H., Xu,\u00a0C., Zhu,\u00a0H., Bai,\u00a0X., 2019. Point in, box out: Beyond counting persons in crowds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 6469\u20136478.","DOI":"10.1109\/CVPR.2019.00663"},{"key":"10.1016\/j.cviu.2026.104878_b32","doi-asserted-by":"crossref","unstructured":"Liu,\u00a0C., Weng,\u00a0X., Mu,\u00a0Y., 2019. 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.","DOI":"10.1109\/CVPR.2019.00131"},{"key":"10.1016\/j.cviu.2026.104878_b33","unstructured":"Liu,\u00a0Y., Wu,\u00a0Q., Wang,\u00a0P., Shen,\u00a0C., 2019. LOBB: Look once and boost counting. In: Proceedings of the IEEE International Conference on Computer Vision. ICCV."},{"key":"10.1016\/j.cviu.2026.104878_b34","series-title":"IEEE International Conference on Multimedia & Expo","article-title":"CLIP-EBC: CLIP can count accurately through enhanced blockwise classification","author":"Ma","year":"2025"},{"key":"10.1016\/j.cviu.2026.104878_b35","series-title":"VMambaCC: A visual state space model for crowd counting","author":"Ma","year":"2024"},{"key":"10.1016\/j.cviu.2026.104878_b36","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.cviu.2026.104878_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110620","article-title":"MixingMask: A contour-aware approach for joint object detection and instance segmentation","volume":"155","author":"Ouyang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cviu.2026.104878_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108054","article-title":"HSNet: Crowd counting via hierarchical scale calibration and spatial attention","volume":"133","author":"Qi","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.cviu.2026.104878_b39","unstructured":"Qian,\u00a0Y., Zhang,\u00a0L., Hong,\u00a0X., Donovan,\u00a0C., Arandjelovic,\u00a0O., 2022. Segmentation Assisted U-shaped Multi-scale Transformer for Crowd Counting. In: British Machine Vision Conference. p. 397."},{"key":"10.1016\/j.cviu.2026.104878_b40","doi-asserted-by":"crossref","unstructured":"Redmon,\u00a0J., Divvala,\u00a0S., Girshick,\u00a0R., Farhadi,\u00a0A., 2016. You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"10.1016\/j.cviu.2026.104878_b41","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104878_b42","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6472","article-title":"Locating objects without bounding boxes","author":"Ribera","year":"2019"},{"issue":"8","key":"10.1016\/j.cviu.2026.104878_b43","first-page":"2739","article-title":"Locate, size, and count: Accurately resolving people in dense crowds via detection","volume":"43","author":"Sam","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104878_b44","doi-asserted-by":"crossref","unstructured":"Sam,\u00a0D., Surya,\u00a0S., Babu,\u00a0R.V., 2017. Switching convolutional neural network for crowd counting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 4031\u20134039.","DOI":"10.1109\/CVPR.2017.429"},{"key":"10.1016\/j.cviu.2026.104878_b45","unstructured":"Shi,\u00a0W., Wang,\u00a0X., Lin,\u00a0L., 2021. LSC-CNN: A localization-sensitive crowd counting network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR."},{"key":"10.1016\/j.cviu.2026.104878_b46","series-title":"2021 IEEE\/CVF International Conference on Computer Vision","first-page":"3345","article-title":"Rethinking counting and localization in crowds: A purely point-based framework","author":"Song","year":"2021"},{"key":"10.1016\/j.cviu.2026.104878_b47","series-title":"Advances in Neural Information Processing Systems","first-page":"37484","article-title":"Singular value fine-tuning: Few-shot segmentation requires few-parameters fine-tuning","volume":"Vol. 35","author":"Sun","year":"2022"},{"key":"10.1016\/j.cviu.2026.104878_b48","doi-asserted-by":"crossref","first-page":"2147","DOI":"10.1109\/TIP.2025.3554410","article-title":"Exploring effective factors for improving visual in-context learning","volume":"34","author":"Sun","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2026.104878_b49","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23565","article-title":"VRP-SAM: SAM with visual reference prompt","author":"Sun","year":"2024"},{"key":"10.1016\/j.cviu.2026.104878_b50","series-title":"European Conference on Computer Vision","first-page":"478","article-title":"Robust zero-shot crowd counting and localization with adaptive resolution SAM","author":"Wan","year":"2024"},{"issue":"9","key":"10.1016\/j.cviu.2026.104878_b51","doi-asserted-by":"crossref","first-page":"15233","DOI":"10.1109\/TITS.2021.3138896","article-title":"Crowd counting via segmentation guided attention networks and curriculum loss","volume":"23","author":"Wang","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.cviu.2026.104878_b52","article-title":"NWPU-Crowd: A large-scale benchmark for crowd counting and localization","author":"Wang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104878_b53","unstructured":"Wang,\u00a0L., Kong,\u00a0X., Xie,\u00a0Y., Wang,\u00a0Q., Tan,\u00a0M., Lin,\u00a0L., 2021. P2PNet: End-to-end people detection in dense crowd. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 18713\u201318722."},{"issue":"1","key":"10.1016\/j.cviu.2026.104878_b54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1746-4811-7-1","article-title":"TasselNet: Counting maize tassels in the wild via local counts regression network","volume":"16","author":"Wang","year":"2020","journal-title":"Plant Methods"},{"key":"10.1016\/j.cviu.2026.104878_b55","unstructured":"Wang,\u00a0J., Zhou,\u00a0H., Chen,\u00a0Y., Huang,\u00a0Q., 2022. CLTR: Crowd localization with transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 36, pp. 3051\u20133059."},{"issue":"2","key":"10.1016\/j.cviu.2026.104878_b56","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1007\/s11263-021-01542-z","article-title":"Autoscale: Learning to scale for crowd counting","volume":"130","author":"Xu","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cviu.2026.104878_b57","unstructured":"Xu,\u00a0Y., Liu,\u00a0X., Wang,\u00a0X., Tang,\u00a0X., 2021. TopoCount: Counting crowds with topological constraints. In: Proceedings of the International Conference on Computer Vision. ICCV."},{"key":"10.1016\/j.cviu.2026.104878_b58","unstructured":"Yang,\u00a0S., Luo,\u00a0P., Loy,\u00a0C.C., Tang,\u00a0X., 2017. Tiny faces: A large-scale dataset and detector for small faces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR."},{"key":"10.1016\/j.cviu.2026.104878_b59","series-title":"Customized segment anything model for medical image segmentation","author":"Zhang","year":"2023"},{"issue":"6","key":"10.1016\/j.cviu.2026.104878_b60","doi-asserted-by":"crossref","first-page":"4388","DOI":"10.1109\/TII.2025.3538070","article-title":"Small object few-shot segmentation for vision-based industrial inspection","volume":"21","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"issue":"10","key":"10.1016\/j.cviu.2026.104878_b61","article-title":"GLCrowd: A weakly supervised global-local attention model for congested crowd counting","volume":"51","author":"Zhang","year":"2024","journal-title":"Opto-Electron Eng"},{"key":"10.1016\/j.cviu.2026.104878_b62","article-title":"Integrating SAM with feature interaction for remote sensing change detection","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.cviu.2026.104878_b63","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0Y., Zhou,\u00a0D., Chen,\u00a0S., Gao,\u00a0S., Ma,\u00a0Y., 2016. Single-image crowd counting via multi-column convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 589\u2013597.","DOI":"10.1109\/CVPR.2016.70"},{"key":"10.1016\/j.cviu.2026.104878_b64","unstructured":"Zhao,\u00a0Y., Zeng,\u00a0C., Liu,\u00a0J., 2024. APGCC: Adaptive perspective-guided crowd counting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR."},{"key":"10.1016\/j.cviu.2026.104878_b65","unstructured":"Zhu,\u00a0J., Li,\u00a0K., Zeng,\u00a0Y., Wang,\u00a0B., 2025. DiffusionLoc: Diffusion models for precise crowd localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR."}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002456?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002456?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T15:48:12Z","timestamp":1788968892000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226002456"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":65,"alternative-id":["S1077314226002456"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104878","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LocSAM: Modular SAM enhancement for dense object localization in complex scenes","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104878","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104878"}}