{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T14:59:03Z","timestamp":1771340343769,"version":"3.50.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"34","license":[{"start":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T00:00:00Z","timestamp":1709769600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T00:00:00Z","timestamp":1709769600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903195"],"award-info":[{"award-number":["61903195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-18769-w","type":"journal-article","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T07:02:31Z","timestamp":1709794951000},"page":"81831-81855","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Double multi-scale feature fusion network for crowd counting"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1815-0001","authenticated-orcid":false,"given":"Qian","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiongtao","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixiong","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cunbao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youwei","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,7]]},"reference":[{"issue":"6","key":"18769_CR1","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1109\/tmm.2016.2542585","volume":"18","author":"C Zhang","year":"2016","unstructured":"Zhang C, Kang K, Li H et al (2016) Data-driven crowd understanding: A baseline for a large-scale crowd dataset. IEEE Trans Multimedia 18(6):1048\u20131061. https:\/\/doi.org\/10.1109\/tmm.2016.2542585","journal-title":"IEEE Trans Multimedia"},{"key":"18769_CR2","doi-asserted-by":"publisher","unstructured":"Zhang C, Li H, Wang X, et\u00a0al (2015) Cross-scene crowd counting via deep convolutional neural networks. In: IEEE\/CVF conference on computer vision and pattern recognition, Boston, MA, USA. pp 833\u2013841 https:\/\/doi.org\/10.1109\/CVPR.2015.7298684","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"18769_CR3","doi-asserted-by":"publisher","unstructured":"Zhang Y, Zhou D, Chen S, et\u00a0al (2016) Single-image crowd counting via multi-column convolutional neural network. In: IEEE\/CVF conference on computer vision and pattern recognition, Las Vegas, NV, USA. pp 589\u2013597 https:\/\/doi.org\/10.1109\/cvpr.2016.70","DOI":"10.1109\/cvpr.2016.70"},{"key":"18769_CR4","doi-asserted-by":"publisher","unstructured":"Sindagi VA, Patel VM (2017) Generating high-quality crowd density maps using contextual pyramid cnns. In: IEEE\/CVF International Conference on Computer Vision, Venice, Italy, pp 1861\u20131870, https:\/\/doi.org\/10.1109\/iccv.2017.206","DOI":"10.1109\/iccv.2017.206"},{"key":"18769_CR5","doi-asserted-by":"publisher","unstructured":"Liu X, Van De\u00a0Weijer J, Bagdanov AD (2018) Leveraging unlabeled data for crowd counting by learning to rank. In: IEEE\/CVF conference on computer vision and pattern recognition, Salt Lake City, UT, USA. pp 7661\u20137669. https:\/\/doi.org\/10.1109\/cvpr.2018.00799","DOI":"10.1109\/cvpr.2018.00799"},{"key":"18769_CR6","doi-asserted-by":"publisher","unstructured":"Shen Z, Xu Y, Ni B, et\u00a0al (2018) Crowd counting via adversarial cross-scale consistency pursuit. In: IEEE\/CVF conference on computer vision and pattern recognition, Salt Lake City, UT, USA. pp 5245\u20135254 https:\/\/doi.org\/10.1109\/cvpr.2018.00550","DOI":"10.1109\/cvpr.2018.00550"},{"key":"18769_CR7","doi-asserted-by":"publisher","unstructured":"Li Y, Zhang X, Chen D (2018) Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes. In: IEEE\/CVF conference on computer vision and pattern recognition, Salt Lake City, UT, USA. pp 1091\u20131100 https:\/\/doi.org\/10.1109\/cvpr.2018.00120","DOI":"10.1109\/cvpr.2018.00120"},{"key":"18769_CR8","doi-asserted-by":"publisher","unstructured":"Cao X, Wang Z, Zhao Y, et\u00a0al (2018) Scale aggregation network for accurate and efficient crowd counting. In: European conference on computer vision, Munich, Germany. pp 734\u2013750 https:\/\/doi.org\/10.1007\/978-3-030-01228-1_45","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"18769_CR9","doi-asserted-by":"publisher","unstructured":"Sam DB, Babu RV (2018) Top-down feedback for crowd counting convolutional neural network. In: AAAI conference on artificial intelligence, New Orleans, Louisiana, USA. pp 7323\u20137330 https:\/\/doi.org\/10.1609\/aaai.v32i1.12290","DOI":"10.1609\/aaai.v32i1.12290"},{"key":"18769_CR10","doi-asserted-by":"publisher","unstructured":"Cheng Z, Li J, Dai Q, et\u00a0al (2019) Improving the learning of multi-column convolutional neural network for crowd counting. In: ACM international conference on multimedia, Nice, France. pp 1897\u20131906 https:\/\/doi.org\/10.1145\/3343031.3350898","DOI":"10.1145\/3343031.3350898"},{"key":"18769_CR11","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.neucom.2019.02.071","volume":"390","author":"B Yang","year":"2020","unstructured":"Yang B, Zhan W, Wang N et al (2020) Counting crowds using a scale-distribution-aware network and adaptive human-shaped kernel. Neurocomputing 390:207\u2013216. https:\/\/doi.org\/10.1016\/j.neucom.2019.02.071","journal-title":"Neurocomputing"},{"key":"18769_CR12","doi-asserted-by":"publisher","unstructured":"Yuan M, Wang Y, Wei X (2022) Translation, scale and rotation: Cross-modal alignment meets rgb-infrared vehicle detection. In: European conference on computer vision, Tel Aviv, Israel. pp 509\u2013525, https:\/\/doi.org\/10.1007\/978-3-031-20077-9_30","DOI":"10.1007\/978-3-031-20077-9_30"},{"issue":"12","key":"18769_CR13","doi-asserted-by":"publisher","first-page":"24540","DOI":"10.1109\/tits.2022.3203385","volume":"23","author":"W Zhou","year":"2022","unstructured":"Zhou W, Pan Y, Lei J et al (2022) Defnet: Dual-branch enhanced feature fusion network for rgb-t crowd counting. IEEE Trans Intell Transp Syst 23(12):24540\u201324549. https:\/\/doi.org\/10.1109\/tits.2022.3203385","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"18769_CR14","doi-asserted-by":"publisher","unstructured":"Tang H, Wang Y, Chau LP (2022) Tafnet: A three-stream adaptive fusion network for rgb-t crowd counting. In: IEEE international symposium on circuits and systems, Austin, TX, USA. pp 3299\u20133303, https:\/\/doi.org\/10.1109\/iscas48785.2022.9937583","DOI":"10.1109\/iscas48785.2022.9937583"},{"key":"18769_CR15","doi-asserted-by":"publisher","unstructured":"Dai M, Huang Z, Gao J, et\u00a0al (2023) Cross-head supervision for crowd counting with noisy annotations. In: IEEE international conference on acoustics, speech and signal processing, Rhodes Island, Greece. pp 1\u20135, https:\/\/doi.org\/10.1109\/icassp49357.2023.10095636","DOI":"10.1109\/icassp49357.2023.10095636"},{"key":"18769_CR16","doi-asserted-by":"publisher","unstructured":"Wang M, Cai H, Dai Y, et\u00a0al (2023) Dynamic mixture of counter network for location-agnostic crowd counting. In: IEEE\/CVF winter conference on applications of computer vision, Waikoloa, HI, USA. pp 167\u2013177 https:\/\/doi.org\/10.1109\/wacv56688.2023.00025","DOI":"10.1109\/wacv56688.2023.00025"},{"key":"18769_CR17","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1109\/tip.2023.3240839","volume":"32","author":"Z Zhao","year":"2023","unstructured":"Zhao Z, Li X (2023) Deformable density estimation via adaptive representation. IEEE Trans Image Process 32:1134\u20131144. https:\/\/doi.org\/10.1109\/tip.2023.3240839","journal-title":"IEEE Trans Image Process"},{"key":"18769_CR18","doi-asserted-by":"publisher","unstructured":"Guo H, Wang R, Zhang L et al (2023) Dual convolutional neural network for crowd counting. Multimed Tools Appl 1\u201323. https:\/\/doi.org\/10.1007\/s11042-023-16442-2","DOI":"10.1007\/s11042-023-16442-2"},{"issue":"4","key":"18769_CR19","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/tpami.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen LC, Papandreou G, Kokkinos I et al (2017) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848. https:\/\/doi.org\/10.1109\/tpami.2017.2699184","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"18769_CR20","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1109\/tcsvt.2016.2637379","volume":"28","author":"B Sheng","year":"2018","unstructured":"Sheng B, Shen C, Lin G et al (2018) Crowd counting via weighted vlad on a dense attribute feature map. IEEE Trans Circuits Syst Video Technol 28(8):1788\u20131797. https:\/\/doi.org\/10.1109\/tcsvt.2016.2637379","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"18769_CR21","doi-asserted-by":"publisher","unstructured":"Zhang A, Shen J, Xiao Z, et\u00a0al (2019) Relational attention network for crowd counting. In: IEEE\/CVF international conference on computer vision, Seoul, Korea. pp 6788\u20136797 https:\/\/doi.org\/10.1109\/iccv.2019.00689","DOI":"10.1109\/iccv.2019.00689"},{"key":"18769_CR22","doi-asserted-by":"publisher","unstructured":"Ma Z, Wei X, Hong X, et\u00a0al (2019) Bayesian loss for crowd count estimation with point supervision. In: IEEE\/CVF international conference on computer vision, Seoul, Korea. pp 6141\u20136150 https:\/\/doi.org\/10.1109\/iccv.2019.00624","DOI":"10.1109\/iccv.2019.00624"},{"key":"18769_CR23","doi-asserted-by":"publisher","unstructured":"Cheng Z, Li J, Dai Q, et\u00a0al (2019) Learning spatial awareness to improve crowd counting. In: IEEE\/CVF international conference on computer vision, Seoul, Korea. pp 6151\u20136160 https:\/\/doi.org\/10.1109\/ICCV.2019.00625","DOI":"10.1109\/ICCV.2019.00625"},{"key":"18769_CR24","doi-asserted-by":"publisher","unstructured":"Chen X, Bin Y, Sang N, et\u00a0al (2019) Scale pyramid network for crowd counting. In: IEEE winter conference on applications of computer vision, Waikoloa, HI, USA. pp 1941\u20131950 https:\/\/doi.org\/10.1109\/wacv.2019.00211","DOI":"10.1109\/wacv.2019.00211"},{"key":"18769_CR25","doi-asserted-by":"crossref","unstructured":"Miao Y, Lin Z, Ding G, et\u00a0al (2020) Shallow feature based dense attention network for crowd counting. In: AAAI Conference on Artificial Intelligence, New York, USA, pp 11765\u201311772, 10.1609\/aaai.v34i07.6848","DOI":"10.1609\/aaai.v34i07.6848"},{"key":"18769_CR26","doi-asserted-by":"publisher","unstructured":"Oh MH, Olsen P, Ramamurthy KN (2020) Crowd counting with decomposed uncertainty. In: AAAI conference on artificial intelligence, New York, USA. pp 11799\u201311806 https:\/\/doi.org\/10.1609\/aaai.v34i07.6852","DOI":"10.1609\/aaai.v34i07.6852"},{"key":"18769_CR27","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.neucom.2020.04.139","volume":"404","author":"S Wang","year":"2020","unstructured":"Wang S, Lu Y, Zhou T et al (2020) Sclnet: Spatial context learning network for congested crowd counting. Neurocomputing 404:227\u2013239. https:\/\/doi.org\/10.1016\/j.neucom.2020.04.139","journal-title":"Neurocomputing"},{"key":"18769_CR28","doi-asserted-by":"publisher","unstructured":"Dai F, Liu H, Ma Y, et\u00a0al (2021) Dense scale network for crowd counting. In: International conference on multimedia retrieval, Taipei, Taiwan, China. pp 64\u201372 https:\/\/doi.org\/10.1145\/3460426.3463628","DOI":"10.1145\/3460426.3463628"},{"key":"18769_CR29","doi-asserted-by":"publisher","unstructured":"Thanasutives P, Fukui Ki, Numao M, et\u00a0al (2021) Encoder-decoder based convolutional neural networks with multi-scale-aware modules for crowd counting. In: IEEE International conference on pattern recognition, Milan, Italy. pp 2382\u20132389 https:\/\/doi.org\/10.1109\/icpr48806.2021.9413286","DOI":"10.1109\/icpr48806.2021.9413286"},{"key":"18769_CR30","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.neucom.2021.04.037","volume":"451","author":"S Amirgholipour","year":"2021","unstructured":"Amirgholipour S, Jia W, Liu L et al (2021) Pdanet: Pyramid density-aware attention based network for accurate crowd counting. Neurocomputing 451:215\u2013230. https:\/\/doi.org\/10.1016\/j.neucom.2021.04.037","journal-title":"Neurocomputing"},{"key":"18769_CR31","doi-asserted-by":"publisher","unstructured":"Wan J, Liu Z, Chan AB (2021) A generalized loss function for crowd counting and localization. In: IEEE\/CVF conference on computer vision and pattern recognition, Nashville, TN, USA. pp 1974\u20131983 https:\/\/doi.org\/10.1109\/cvpr46437.2021.00201","DOI":"10.1109\/cvpr46437.2021.00201"},{"key":"18769_CR32","doi-asserted-by":"publisher","unstructured":"Liu H, Zhao Q, Ma Y, et\u00a0al (2021) Bipartite matching for crowd counting with point supervision. In: International joint conference on artificial intelligence. online. pp 860\u2013866 https:\/\/doi.org\/10.24963\/ijcai.2021\/119","DOI":"10.24963\/ijcai.2021\/119"},{"key":"18769_CR33","doi-asserted-by":"publisher","unstructured":"Song Q, Wang C, Wang Y, et\u00a0al (2021) To choose or to fuse? scale selection for crowd counting. In: AAAI conference on artificial intelligence. online. pp 2576\u20132583 https:\/\/doi.org\/10.1609\/aaai.v35i3.16360","DOI":"10.1609\/aaai.v35i3.16360"},{"key":"18769_CR34","doi-asserted-by":"publisher","unstructured":"Zhang J, Cheng ZQ, Wu X, et\u00a0al (2022) Crossnet: Boosting crowd counting with localization. In: ACM international conference on multimedia, Lisboa, Portugal. pp 6436\u20136444 https:\/\/doi.org\/10.1145\/3503161.3547863","DOI":"10.1145\/3503161.3547863"},{"key":"18769_CR35","doi-asserted-by":"publisher","first-page":"104563","DOI":"10.1016\/j.engappai.2021.104563","volume":"108","author":"S Zhang","year":"2022","unstructured":"Zhang S, Zhang X, Li H et al (2022) Hierarchical pyramid attentive network with spatial separable convolution for crowd counting. Eng Appl Artif Intell 108:104563. https:\/\/doi.org\/10.1016\/j.engappai.2021.104563","journal-title":"Eng Appl Artif Intell"},{"key":"18769_CR36","doi-asserted-by":"publisher","unstructured":"Cheng ZQ, Dai Q, Li H, et\u00a0al (2022) Rethinking spatial invariance of convolutional networks for object counting. In: IEEE\/CVF conference on computer vision and pattern recognition, New Orleans, LA, USA. pp 19606\u201319616 https:\/\/doi.org\/10.1109\/cvpr52688.2022.01902","DOI":"10.1109\/cvpr52688.2022.01902"},{"key":"18769_CR37","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations, San Diego, CA. pp 1\u201314 https:\/\/iclr.cc\/archive\/www\/lib\/exe\/fetch.php%3Fmedia=iclr2015:simonyan-iclr2015.pdf"},{"key":"18769_CR38","doi-asserted-by":"publisher","unstructured":"Lin TY, Dollar P, Girshick R, et\u00a0al (2017) Feature pyramid networks for object detection. In: IEEE\/CVF conference on computer vision and pattern recognition, Honolulu, HI, USA. pp 2117\u20132125 https:\/\/doi.org\/10.1109\/cvpr.2017.106","DOI":"10.1109\/cvpr.2017.106"},{"key":"18769_CR39","doi-asserted-by":"publisher","unstructured":"Wang Q, Gao J, Lin W, et\u00a0al (2019) Learning from synthetic data for crowd counting in the wild. In: IEEE\/CVF conference on computer vision and pattern recognition, Long Beach, CA, USA. pp 8198\u20138207 https:\/\/doi.org\/10.1109\/cvpr.2019.00839","DOI":"10.1109\/cvpr.2019.00839"},{"issue":"8","key":"18769_CR40","doi-asserted-by":"publisher","first-page":"2739","DOI":"10.1109\/tpami.2020.2974830","volume":"43","author":"DB Sam","year":"2020","unstructured":"Sam DB, Peri SV, Sundararaman MN et al (2020) Locate, size, and count: accurately resolving people in dense crowds via detection. IEEE Trans Pattern Anal Mach Intell 43(8):2739\u20132751. https:\/\/doi.org\/10.1109\/tpami.2020.2974830","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"18769_CR41","doi-asserted-by":"publisher","first-page":"13637","DOI":"10.1007\/s11042-022-13957-y","volume":"82","author":"G Yang","year":"2023","unstructured":"Yang G, Zhu D (2023) Survey on algorithms of people counting in dense crowd and crowd density estimation. Multimed Tools Appl 82(9):13637\u201313648. https:\/\/doi.org\/10.1007\/s11042-022-13957-y","journal-title":"Multimed Tools Appl"},{"issue":"2","key":"18769_CR42","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1609\/aaai.v35i2.16170","volume":"35","author":"S Abousamra","year":"2021","unstructured":"Abousamra S, Hoai M, Samaras D et al (2021) Localization in the crowd with topological constraints. Proceedings of AAAI Conference on Artificial Intelligence 35(2):872\u2013881. https:\/\/doi.org\/10.1609\/aaai.v35i2.16170","journal-title":"Proceedings of AAAI Conference on Artificial Intelligence"},{"key":"18769_CR43","doi-asserted-by":"publisher","unstructured":"Wang L, Sindagi V, Patel V (2018) High-quality facial photo-sketch synthesis using multi-adversarial networks. In: IEEE international conference on automatic face & gesture recognition, Xi\u2019an, China. pp 83\u201390 https:\/\/doi.org\/10.1109\/fg.2018.00022","DOI":"10.1109\/fg.2018.00022"},{"key":"18769_CR44","doi-asserted-by":"publisher","unstructured":"Girshick R (2015) Fast r-cnn. In: IEEE\/CVF international conference on computer vision, Santiago, Chile. pp 1440\u20131448 https:\/\/doi.org\/10.1109\/iccv.2015.169","DOI":"10.1109\/iccv.2015.169"},{"key":"18769_CR45","doi-asserted-by":"publisher","unstructured":"Idrees H, Saleemi I, Seibert C, et\u00a0al (2013) Multi-source multi-scale counting in extremely dense crowd images. In: IEEE conference on computer vision and pattern recognition, Portland, OR, USA. pp 2547\u20132554 https:\/\/doi.org\/10.1109\/CVPR.2013.329","DOI":"10.1109\/CVPR.2013.329"},{"key":"18769_CR46","doi-asserted-by":"publisher","unstructured":"Idrees H, Tayyab M, Athrey K, et\u00a0al (2018) Composition loss for counting, density map estimation and localization in dense crowds. In: European conference on computer vision, Munich, Germany. pp 532\u2013546 https:\/\/doi.org\/10.1007\/978-3-030-01216-8_33","DOI":"10.1007\/978-3-030-01216-8_33"},{"issue":"5","key":"18769_CR47","doi-asserted-by":"publisher","first-page":"2594","DOI":"10.1109\/tpami.2020.3035969","volume":"44","author":"VA Sindagi","year":"2022","unstructured":"Sindagi VA, Yasarla R, Patel VM (2022) Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method. IEEE Trans Pattern Anal Mach Intell 44(5):2594\u20132609. https:\/\/doi.org\/10.1109\/tpami.2020.3035969","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"18769_CR48","doi-asserted-by":"publisher","unstructured":"Szegedy C, Liu W, Jia Y, et\u00a0al (2015) Going deeper with convolutions. In: IEEE\/CVF conference on computer vision and pattern recognition, Boston, MA, USA. pp 1\u20139 https:\/\/doi.org\/10.1109\/cvpr.2015.7298594","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"18769_CR49","unstructured":"Wan J, Chan A (2020) Modeling noisy annotations for crowd counting. In: Neural information processing systems, Vancouver, Canada. pp 3386\u20133396 https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/22bb543b251c39ccdad8063d486987bb-Paper.pdf"},{"key":"18769_CR50","doi-asserted-by":"publisher","unstructured":"Wang P, Chen P, Yuan Y, et\u00a0al (2018) Understanding convolution for semantic segmentation. In: IEEE winter conference on applications of computer vision, Lake Tahoe, NV, USA. pp 1451\u20131460 https:\/\/doi.org\/10.1109\/wacv.2018.00163","DOI":"10.1109\/wacv.2018.00163"},{"key":"18769_CR51","doi-asserted-by":"publisher","unstructured":"Wang X, Girshick R, Gupta A, et\u00a0al (2018) Non-local neural networks. In: IEEE\/CVF conference on computer vision and pattern recognition, Salt Lake City, UT, USA. pp 7794\u20137803 https:\/\/doi.org\/10.1109\/CVPR.2018.00813","DOI":"10.1109\/CVPR.2018.00813"},{"key":"18769_CR52","doi-asserted-by":"publisher","unstructured":"Li X, Wang W, Hu X, et\u00a0al (2019) Selective kernel networks. In: IEEE\/CVF conference on computer vision and pattern recognition, Long Beach, CA, USA. pp 510\u2013519 https:\/\/doi.org\/10.1109\/CVPR.2019.00060","DOI":"10.1109\/CVPR.2019.00060"},{"key":"18769_CR53","doi-asserted-by":"publisher","unstructured":"Khan MA, Menouar H, Hamila R (2023) Crowd density estimation using imperfect labels. In: IEEE international conference on consumer electronics, Las Vegas, NV, USA. pp 1\u20136 https:\/\/doi.org\/10.1109\/ICCE56470.2023.10043547","DOI":"10.1109\/ICCE56470.2023.10043547"},{"issue":"6","key":"18769_CR54","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun ACM"},{"key":"18769_CR55","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, et\u00a0al (2016) Deep residual learning for image recognition. In: IEEE\/CVF conference on computer vision and pattern recognition, Las Vegas, NV, USA. pp 770\u2013778 https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18769-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-18769-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18769-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T12:08:47Z","timestamp":1728475727000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-18769-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,7]]},"references-count":55,"journal-issue":{"issue":"34","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["18769"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-18769-w","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,7]]},"assertion":[{"value":"19 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}