{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T02:48:08Z","timestamp":1782355688497,"version":"3.54.5"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10044-026-01697-w","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T11:47:44Z","timestamp":1780660064000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-scale feature fusion with cross-view head re-identification module for crowd-counting"],"prefix":"10.1007","volume":"29","author":[{"given":"Avinash","family":"Rohra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoqun","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aakash","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajeet Kumar","family":"Bhatia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Izis","family":"Kanjarawy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,5]]},"reference":[{"key":"1697_CR1","doi-asserted-by":"crossref","unstructured":"Roig G, Boix X, Shitrit HB, Fua P (2011) Conditional random fields for multi-camera object detection, in International conference on computer vision, IEEE, pp. 563\u2013570","DOI":"10.1109\/ICCV.2011.6126289"},{"key":"1697_CR2","doi-asserted-by":"crossref","unstructured":"Yeo KN, Lau YL, Ng GW (2024) Data Fusion Pipeline for UAV-Based Real-Time Night Crowd Counting for Public Safety. In: 27th International Conference on Information Fusion (FUSION), 2024: IEEE, pp. 1\u20138","DOI":"10.23919\/FUSION59988.2024.10706297"},{"key":"1697_CR3","doi-asserted-by":"publisher","first-page":"101919","DOI":"10.1016\/j.ecoinf.2022.101919","volume":"75","author":"AM Roy","year":"2023","unstructured":"Roy AM, Bhaduri J, Kumar T, Raj K (2023) WilDect-YOLO: An efficient and robust computer vision-based accurate object localization model for automated endangered wildlife detection. Ecol Inf 75:101919","journal-title":"Ecol Inf"},{"key":"1697_CR4","unstructured":"Chandio A et al (2022) Precise single-stage detector, arXiv preprint arXiv:2210.04252"},{"issue":"1","key":"1697_CR5","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s10851-010-0258-7","volume":"41","author":"A Alahi","year":"2011","unstructured":"Alahi A, Jacques L, Boursier Y, Vandergheynst P (2011) Sparsity driven people localization with a heterogeneous network of cameras. J Math Imaging Vis 41(1):39\u201358","journal-title":"J Math Imaging Vis"},{"key":"1697_CR6","unstructured":"Yang T, Zhang X, Li Z, Zhang W, Sun J (2018) Metaanchor: Learning to detect objects with customized anchors. Adv Neural Inf Process Syst 31:318-328"},{"key":"1697_CR7","doi-asserted-by":"publisher","first-page":"7389","DOI":"10.1109\/TIP.2020.3002345","volume":"29","author":"T Kong","year":"2020","unstructured":"Kong T, Sun F, Liu H, Jiang Y, Li L, Shi J (2020) Foveabox: Beyound anchor-based object detection. IEEE Trans Image Process 29:7389\u20137398","journal-title":"IEEE Trans Image Process"},{"key":"1697_CR8","doi-asserted-by":"crossref","unstructured":"Xu Y, Liu X, Liu Y, Zhu S-C (2016) Multi-view people tracking via hierarchical trajectory composition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4256\u20134265","DOI":"10.1109\/CVPR.2016.461"},{"key":"1697_CR9","doi-asserted-by":"crossref","unstructured":"Hou Y, Zheng L, Gould S (2020) Multiview detection with feature perspective transformation. In: European conference on computer vision, Springer, pp. 1\u201318","DOI":"10.1007\/978-3-030-58571-6_1"},{"key":"1697_CR10","doi-asserted-by":"crossref","unstructured":"Hou Y, Zheng L (2021) Multiview detection with shadow transformer (and view-coherent data augmentation). In: Proceedings of the 29th ACM international conference on multimedia, pp. 1673\u20131682","DOI":"10.1145\/3474085.3475310"},{"key":"1697_CR11","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.engappai.2015.04.006","volume":"43","author":"M Fu","year":"2015","unstructured":"Fu M, Xu P, Li X, Liu Q, Ye M, Zhu C (2015) Fast crowd density estimation with convolutional neural networks. Eng Appl Artif Intell 43:81\u201388","journal-title":"Eng Appl Artif Intell"},{"key":"1697_CR12","doi-asserted-by":"crossref","unstructured":"Wang C, Zhang H, Yang L, Liu S, Cao X (2015) Deep people counting in extremely dense crowds. In: Proceedings of the 23rd ACM international conference on Multimedia, pp. 1299\u20131302","DOI":"10.1145\/2733373.2806337"},{"key":"1697_CR13","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:10097-1105"},{"key":"1697_CR14","doi-asserted-by":"crossref","unstructured":"Walach E, Wolf L (2016) Learning to count with cnn boosting. In: European conference on computer vision, Springer, pp. 660\u2013676","DOI":"10.1007\/978-3-319-46475-6_41"},{"key":"1697_CR15","doi-asserted-by":"crossref","unstructured":"Zhang Y, Zhou D, Chen S, Gao S, Ma Y (2016) 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","DOI":"10.1109\/CVPR.2016.70"},{"key":"1697_CR16","doi-asserted-by":"crossref","unstructured":"Onoro-Rubio D, L\u00f3pez-Sastre RJ (2016) Towards perspective-free object counting with deep learning. In: European conference on computer vision, : Springer, pp. 615\u2013629","DOI":"10.1007\/978-3-319-46478-7_38"},{"key":"1697_CR17","doi-asserted-by":"crossref","unstructured":"Boominathan L, Kruthiventi SS, Babu RV (2016) Crowdnet: A deep convolutional network for dense crowd counting. In: Proceedings of the 24th ACM international conference on Multimedia, pp. 640\u2013644","DOI":"10.1145\/2964284.2967300"},{"key":"1697_CR18","doi-asserted-by":"crossref","unstructured":"Zhang A et al (2019) Relational attention network for crowd counting. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6788\u20136797","DOI":"10.1109\/ICCV.2019.00689"},{"key":"1697_CR19","doi-asserted-by":"crossref","unstructured":"Guo D, Li K, Zha Z-J, Wang M (2019) Dadnet: Dilated-attention-deformable convnet for crowd counting. In: Proceedings of the 27th ACM international conference on multimedia, pp. 1823\u20131832","DOI":"10.1145\/3343031.3350881"},{"key":"1697_CR20","doi-asserted-by":"publisher","first-page":"2593","DOI":"10.1109\/TMM.2025.3535330","volume":"27","author":"B Mu","year":"2025","unstructured":"Mu B, Shao F, Xie Z, Chen H, Zhu Z, Jiang Q (2025) MISF-Net: Modality-invariant and-specific fusion network for RGB-T crowd counting. IEEE Trans Multimedia 27:2593\u20132607","journal-title":"IEEE Trans Multimedia"},{"key":"1697_CR21","first-page":"1","volume":"73","author":"Z Xie","year":"2024","unstructured":"Xie Z et al (2024) Bgdfnet: bidirectional gated and dynamic fusion network for rgb-t crowd counting in smart city system. IEEE Trans Instrum Meas 73:1\u201316","journal-title":"IEEE Trans Instrum Meas"},{"key":"1697_CR22","doi-asserted-by":"crossref","unstructured":"Rohra A et al (2026) Multi-scale pyramid fusion with overlap density attention module for crowd counting. Neural Networks 201: 108983","DOI":"10.1016\/j.neunet.2026.108983"},{"issue":"8","key":"1697_CR23","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1109\/TCSVT.2016.2637379","volume":"28","author":"B Sheng","year":"2016","unstructured":"Sheng B, Shen C, Lin G, Li J, Yang W, Sun C (2016) Crowd counting via weighted VLAD on a dense attribute feature map. IEEE Trans Circuits Syst Video Technol 28(8):1788\u20131797","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"1697_CR24","doi-asserted-by":"crossref","unstructured":"Zhang L, Shi M, Chen Q Crowd counting via scale-adaptive convolutional neural network. In: (2018) IEEE winter conference on applications of computer vision (WACV), 2018: IEEE, pp. 1113\u20131121","DOI":"10.1109\/WACV.2018.00127"},{"key":"1697_CR25","doi-asserted-by":"crossref","unstructured":"Shi Z et al (2018) Crowd counting with deep negative correlation learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5382\u20135390","DOI":"10.1109\/CVPR.2018.00564"},{"key":"1697_CR26","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang X, Chen D (2018) 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","DOI":"10.1109\/CVPR.2018.00120"},{"key":"1697_CR27","doi-asserted-by":"crossref","unstructured":"Aich S, Stavness I (2017) Leaf counting with deep convolutional and deconvolutional networks. In: Proceedings of the IEEE international conference on computer vision workshops, pp. 2080\u20132089","DOI":"10.1109\/ICCVW.2017.244"},{"key":"1697_CR28","doi-asserted-by":"crossref","unstructured":"Chen X, Bin Y, Sang N, Gao C (2019) Scale pyramid network for crowd counting. In: 2019 IEEE winter conference on applications of computer vision (WACV), : IEEE, pp. 1941\u20131950","DOI":"10.1109\/WACV.2019.00211"},{"key":"1697_CR29","doi-asserted-by":"crossref","unstructured":"Gawande U, Hajari K, Golhar Y (2020) Pedestrian detection and tracking in video surveillance system: issues, comprehensive review, and challenges, Recent Trends in Computational Intelligence, pp. 1\u201324","DOI":"10.5772\/intechopen.90810"},{"key":"1697_CR30","doi-asserted-by":"publisher","first-page":"2438","DOI":"10.1016\/j.procs.2023.01.219","volume":"218","author":"U Gawande","year":"2023","unstructured":"Gawande U, Hajari K, Golhar Y (2023) Real-time deep learning approach for pedestrian detection and suspicious activity recognition. Procedia Comput Sci 218:2438\u20132447","journal-title":"Procedia Comput Sci"},{"issue":"2","key":"1697_CR31","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/s10462-023-10630-0","volume":"57","author":"U Gawande","year":"2024","unstructured":"Gawande U, Hajari K, Golhar Y (2024) Novel person detection and suspicious activity recognition using enhanced YOLOv5 and motion feature map. Artif Intell Rev 57(2):16","journal-title":"Artif Intell Rev"},{"key":"1697_CR32","doi-asserted-by":"crossref","unstructured":"Mo H, Zhang X, Shi T, Wu Z (2026) Multi-View Crowd Counting with Self-Supervised Learning. In: ICASSP 2026\u20132026 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp. 10052\u201310056","DOI":"10.1109\/ICASSP55912.2026.11463004"},{"issue":"4","key":"1697_CR33","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s11263-026-02778-3","volume":"134","author":"Q Zhang","year":"2026","unstructured":"Zhang Q, Chen D, Gong Y, Huang H (2026) SynMVCrowd: a large synthetic benchmark for multi-view crowd counting and localization. Int J Comput Vision 134(4):191","journal-title":"Int J Comput Vision"},{"key":"1697_CR34","unstructured":"Mo H, Zhang X, Shi T, Wu Z (2025) Multi-View Crowd Counting With Self-Supervised Learning, arXiv preprint arXiv:2509.21918,"},{"key":"1697_CR35","doi-asserted-by":"crossref","unstructured":"Chavdarova T, Fleuret F (2017) Deep multi-camera people detection. In: 16th IEEE international conference on machine learning and applications (ICMLA), 2017: IEEE, pp. 848\u2013853","DOI":"10.1109\/ICMLA.2017.00-50"},{"issue":"5","key":"1697_CR36","doi-asserted-by":"publisher","first-page":"2246","DOI":"10.1109\/TPAMI.2020.3034435","volume":"44","author":"J Ong","year":"2020","unstructured":"Ong J, Vo B-T, Vo B-N, Kim DY, Nordholm S (2020) A Bayesian filter for multi-view 3D multi-object tracking with occlusion handling. IEEE Trans Pattern Anal Mach Intell 44(5):2246\u20132263","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1697_CR37","doi-asserted-by":"crossref","unstructured":"Baqu\u00e9 P, Fleuret F, Fua P (2017) Deep occlusion reasoning for multi-camera multi-target detection. In: Proceedings of the IEEE international conference on computer vision, pp. 271\u2013279","DOI":"10.1109\/ICCV.2017.38"},{"issue":"7","key":"1697_CR38","doi-asserted-by":"publisher","first-page":"2300706","DOI":"10.1002\/aisy.202300706","volume":"6","author":"S Ul Amin","year":"2024","unstructured":"Ul Amin S, Kim B, Jung Y, Seo S, Park S (2024) Video anomaly detection utilizing efficient spatiotemporal feature fusion with 3D convolutions and long short-term memory modules. Adv Intell Syst 6(7):2300706","journal-title":"Adv Intell Syst"},{"key":"1697_CR39","doi-asserted-by":"crossref","unstructured":"Haider ZA, Amin SU, Fayaz M, Khan FM, Moon H, Seo S (2025) A comprehensive approach for image quality assessment using quality-centric embedding and ranking networks. Pattern Recogn 173: 112890","DOI":"10.1016\/j.patcog.2025.112890"},{"key":"1697_CR40","doi-asserted-by":"publisher","first-page":"154080","DOI":"10.1109\/ACCESS.2024.3480205","volume":"12","author":"NF Khan","year":"2024","unstructured":"Khan NF, Amin SU, Jan Z, Yan C (2024) Detection of violent scenes in cartoon movies using a deep learning approach. IEEE Access 12:154080\u2013154091","journal-title":"IEEE Access"},{"key":"1697_CR41","doi-asserted-by":"publisher","first-page":"111655","DOI":"10.1016\/j.engappai.2025.111655","volume":"159","author":"SU Amin","year":"2025","unstructured":"Amin SU, Jung Y, Fayaz M, Kim B, Seo S (2025) Enhancing pine wilt disease detection with synthetic data and external attention-based transformers. Eng Appl Artif Intell 159:111655","journal-title":"Eng Appl Artif Intell"},{"key":"1697_CR42","doi-asserted-by":"publisher","first-page":"108866","DOI":"10.1016\/j.patcog.2022.108866","volume":"131","author":"X Gao","year":"2022","unstructured":"Gao X, Xiong Y, Zhang G, Deng H, Kou K (2022) Exploiting key points supervision and grouped feature fusion for multiview pedestrian detection. Pattern Recogn 131:108866","journal-title":"Pattern Recogn"},{"key":"1697_CR43","doi-asserted-by":"publisher","first-page":"187536","DOI":"10.1109\/ACCESS.2024.3470122","volume":"12","author":"T Kumar","year":"2024","unstructured":"Kumar T, Brennan R, Mileo A, Bendechache M (2024) Image data augmentation approaches: a comprehensive survey and future directions. IEEE Access 12:187536\u2013187571","journal-title":"Ieee Access"},{"key":"1697_CR44","doi-asserted-by":"crossref","unstructured":"Kumar T, Mileo A, Brennan R, Bendechache M (2023) RSMDA: Random slices mixing data augmentation. Appl Sci 13:1711","DOI":"10.3390\/app13031711"},{"key":"1697_CR45","doi-asserted-by":"crossref","unstructured":"Kumar T, Mileo A, Bendechache M (2024) Keeporiginalaugment: Single image-based better information-preserving data augmentation approach. In: IFIP international conference on artificial intelligence applications and innovations, Springer, pp. 27\u201340","DOI":"10.1007\/978-3-031-63223-5_3"},{"key":"1697_CR46","doi-asserted-by":"crossref","unstructured":"Aleem S, Kumar T, Little S, Bendechache M, Brennan R, McGuinness K (2022) Random data augmentation based enhancement: a generalized enhancement approach for medical datasets, arXiv preprint arXiv:2210.00824,","DOI":"10.56541\/FUMF3414"},{"key":"1697_CR47","unstructured":"Kumar T, Park J, Bae S-H (2020) Intra-Class Random Erasing (ICRE) augmentation for audio classification, \ud55c\uad6d\ubc29\uc1a1\ubbf8\ub514\uc5b4\uacf5\ud559\ud68c \ud559\uc220\ubc1c\ud45c\ub300\ud68c \ub17c\ubb38\uc9d1, pp. 246\u2013249"},{"key":"1697_CR48","doi-asserted-by":"crossref","unstructured":"Kumar T, Mileo A, Bendechache M RandSaliencyAug++: saliency-based data augmentation for improved generalization across diverse tasks, IMVIP (2025), p. 38, p. 38","DOI":"10.5220\/0013098700003912"},{"key":"1697_CR49","doi-asserted-by":"crossref","unstructured":"Idrees H, Saleemi I, Seibert C, Shah M (2013) Multi-source multi-scale counting in extremely dense crowd images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2547\u20132554","DOI":"10.1109\/CVPR.2013.329"},{"key":"1697_CR50","doi-asserted-by":"crossref","unstructured":"Idrees H et al (2018) Composition loss for counting, density map estimation and localization in dense crowds. In: Proceedings of the European conference on computer vision (ECCV), pp. 532\u2013546","DOI":"10.1007\/978-3-030-01216-8_33"},{"issue":"5","key":"1697_CR51","first-page":"2594","volume":"44","author":"VA Sindagi","year":"2020","unstructured":"Sindagi VA, Yasarla R, Patel VM (2020) Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method. IEEE Trans Pattern Anal Mach Intell 44(5):2594\u20132609","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1697_CR52","doi-asserted-by":"crossref","unstructured":"Chavdarova T et al (2018) Wildtrack: A multi-camera hd dataset for dense unscripted pedestrian detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5030\u20135039","DOI":"10.1109\/CVPR.2018.00528"},{"key":"1697_CR53","unstructured":"Srivastav V, Issenhuth T, Kadkhodamohammadi A, de Mathelin M, Gangi A, Padoy N (2018) MVOR: A multi-view RGB-D operating room dataset for 2D and 3D human pose estimation, arXiv preprint arXiv:1808.08180,"},{"key":"1697_CR54","doi-asserted-by":"crossref","unstructured":"Zhang C, Li H, Wang X, Yang X (2015) Cross-scene crowd counting via deep convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 833\u2013841","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"1697_CR55","doi-asserted-by":"crossref","unstructured":"Wan J, Liu Z, Chan AB (2021) A generalized loss function for crowd counting and localization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1974\u20131983","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"1697_CR56","first-page":"3386","volume":"33","author":"J Wan","year":"2020","unstructured":"Wan J, Chan A (2020) Modeling noisy annotations for crowd counting. Adv Neural Inf Process Syst 33:3386\u20133396","journal-title":"Adv Neural Inf Process Syst"},{"key":"1697_CR57","doi-asserted-by":"crossref","unstructured":"Abousamra S, Hoai M, Samaras D, Chen C (2021) Localization in the crowd with topological constraints. In: Proceedings of the AAAI conference on artificial intelligence, vol. 35, no. 2, pp. 872\u2013881","DOI":"10.1609\/aaai.v35i2.16170"},{"key":"1697_CR58","doi-asserted-by":"crossref","unstructured":"Ma Z, Wei X, Hong X, Lin H, Qiu Y, Gong Y (2021) Learning to count via unbalanced optimal transport. In: Proceedings of the AAAI conference on artificial intelligence, vol. 35, no. 3, pp. 2319\u20132327","DOI":"10.1609\/aaai.v35i3.16332"},{"key":"1697_CR59","doi-asserted-by":"crossref","unstructured":"Tian Y, Lei Y, Zhang J, Wang Z J. (2019) Padnet: Pan-density crowd counting. IEEE Trans Image Process 29:2714\u20132727","DOI":"10.1109\/TIP.2019.2952083"},{"key":"1697_CR60","first-page":"1595","volume":"33","author":"B Wang","year":"2020","unstructured":"Wang B, Liu H, Samaras D, Nguyen MH (2020) Distribution matching for crowd counting. Adv Neural Inf Process Syst 33:1595\u20131607","journal-title":"Adv Neural Inf Process Syst"},{"key":"1697_CR61","doi-asserted-by":"crossref","unstructured":"Kim N, Kwak S (2021) Robust crowd count via image enhancement dynamic feature selection BMVC 421","DOI":"10.5244\/C.35.380"},{"key":"1697_CR62","doi-asserted-by":"crossref","unstructured":"Peng Z, Chan S-HG (2024) Single domain generalization for crowd counting. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 28025\u201328034","DOI":"10.1109\/CVPR52733.2024.02647"},{"issue":"1","key":"1697_CR63","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s10044-024-01385-7","volume":"28","author":"A Rohra","year":"2025","unstructured":"Rohra A, Yin B, Bilal H, Kumar A, Ali M, Li Y (2025) MSFFNet: multi-scale feature fusion network with semantic optimization for crowd counting. Pattern Anal Appl 28(1):21","journal-title":"Pattern Anal Appl"},{"issue":"9","key":"1697_CR64","doi-asserted-by":"publisher","first-page":"5056","DOI":"10.1109\/TPAMI.2021.3069237","volume":"44","author":"K Zhou","year":"2021","unstructured":"Zhou K, Yang Y, Cavallaro A, Xiang T (2021) Learning generalisable omni-scale representations for person re-identification. IEEE Trans Pattern Anal Mach Intell 44(9):5056\u20135069","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1697_CR65","doi-asserted-by":"crossref","unstructured":"Gan Y, Han R, Yin L, Feng W, Wang S (2021) Self-supervised multi-view multi-human association and tracking. In: Proceedings of the 29th ACM international conference on multimedia, pp. 282\u2013290","DOI":"10.1145\/3474085.3475177"},{"key":"1697_CR66","doi-asserted-by":"crossref","unstructured":"Cai Z et al (2020) Messytable: instance association in multiple camera views. In: European conference on computer vision. Springer, pp. 1\u201316","DOI":"10.1007\/978-3-030-58621-8_1"},{"issue":"2","key":"1697_CR67","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1109\/TCSVT.2022.3207223","volume":"33","author":"E Luna","year":"2022","unstructured":"Luna E, SanMiguel JC, Mart\u00ednez JM, Carballeira P (2022) Graph neural networks for cross-camera data association. IEEE Trans Circuits Syst Video Technol 33(2):589\u2013601","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"1697_CR68","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1109\/LSP.2020.2994815","volume":"27","author":"S Zhang","year":"2020","unstructured":"Zhang S, Zhang L, Wang W, Wu X (2020) AsNet: Asymmetrical network for learning rich features in person re-identification. IEEE Signal Process Lett 27:850\u2013854","journal-title":"IEEE Signal Process Lett"},{"key":"1697_CR69","doi-asserted-by":"crossref","unstructured":"Seo M, Lee H-J, Nguyen XT (2023) ViT-P3DE\u2217: vision transformer based multi-camera instance association with pseudo 3D position embeddings. In: IJCAI, pp. 1340\u20131350","DOI":"10.24963\/ijcai.2023\/149"},{"key":"1697_CR70","doi-asserted-by":"crossref","unstructured":"Chen K, Srivastav V, Mutter D, Padoy N (2025) Learning from synchronization: self-supervised uncalibrated multi-view person association in challenging scenes. In: Proceedings of the computer vision and pattern recognition conference, pp. 24419\u201324428","DOI":"10.1109\/CVPR52734.2025.02274"},{"key":"1697_CR71","doi-asserted-by":"publisher","first-page":"93615","DOI":"10.1109\/ACCESS.2022.3203106","volume":"10","author":"S Zhong","year":"2022","unstructured":"Zhong S, Xu W, Zhang T, Chen H (2022) Identification and depth localization of clustered pod pepper based on improved Faster R-CNN. IEEE Access 10:93615\u201393625","journal-title":"IEEE Access"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01697-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-026-01697-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01697-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T02:41:53Z","timestamp":1782355313000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-026-01697-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":71,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1697"],"URL":"https:\/\/doi.org\/10.1007\/s10044-026-01697-w","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"1 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2026","order":3,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"112"}}