{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T02:27:30Z","timestamp":1773196050431,"version":"3.50.1"},"reference-count":149,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"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":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s13042-024-02345-7","type":"journal-article","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T11:02:26Z","timestamp":1724670146000},"page":"1435-1460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Beyond traditional visual object tracking: a survey"],"prefix":"10.1007","volume":"16","author":[{"given":"Omar","family":"Abdelaziz","sequence":"first","affiliation":[]},{"given":"Mohamed","family":"Shehata","sequence":"additional","affiliation":[]},{"given":"Mohamed","family":"Mohamed","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,26]]},"reference":[{"issue":"2","key":"2345_CR1","doi-asserted-by":"publisher","first-page":"2269","DOI":"10.1007\/s11042-018-6347-0","volume":"78","author":"Y Yang","year":"2019","unstructured":"Yang Y, Wu Y, Chen N (2019) Explorations on visual localization from active to passive. Multimedia Tools Appl 78(2):2269\u20132309","journal-title":"Multimedia Tools Appl"},{"key":"2345_CR2","doi-asserted-by":"publisher","unstructured":"Mathur G, Somwanshi D, Bundele MM (2018) Intelligent video surveillance based on object tracking. In: 2018 3rd international conference and workshops on rcent advances and innovations in engineering (ICRAIE), pp. 1\u20136. https:\/\/doi.org\/10.1109\/ICRAIE.2018.8710421","DOI":"10.1109\/ICRAIE.2018.8710421"},{"issue":"16","key":"2345_CR3","doi-asserted-by":"publisher","first-page":"3234","DOI":"10.3390\/rs13163234","volume":"13","author":"J Cao","year":"2021","unstructured":"Cao J, Song C, Song S, Xiao F, Zhang X, Liu Z, Ang MH Jr (2021) Robust object tracking algorithm for autonomous vehicles in complex scenes. Remote Sens 13(16):3234","journal-title":"Remote Sens"},{"key":"2345_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107618","volume":"205","author":"Z Zheng","year":"2023","unstructured":"Zheng Z, Zhang X, Qin L, Yue S, Zeng P (2023) Cows\u2019 legs tracking and lameness detection in dairy cattle using video analysis and siamese neural networks. Comput Electron Agricult 205:107618","journal-title":"Comput Electron Agricult"},{"key":"2345_CR5","doi-asserted-by":"crossref","unstructured":"Chen K, Oldja R, Smolyanskiy N, Birchfield S, Popov A, Wehr D, Eden I, Pehserl J (2020) Mvlidarnet: Real-time multi-class scene understanding for autonomous driving using multiple views. In: 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp. 2288\u20132294. IEEE","DOI":"10.1109\/IROS45743.2020.9341450"},{"issue":"4","key":"2345_CR6","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/1177352.1177355","volume":"38","author":"A Yilmaz","year":"2006","unstructured":"Yilmaz A, Javed O, Shah M (2006) Object tracking: a survey. ACM Comput Surv 38(4):13. https:\/\/doi.org\/10.1145\/1177352.1177355","journal-title":"ACM Comput Surv"},{"issue":"7","key":"2345_CR7","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.1109\/TPAMI.2013.230","volume":"36","author":"AWM Smeulders","year":"2014","unstructured":"Smeulders AWM, Chu DM, Cucchiara R, Calderara S, Dehghan A, Shah M (2014) Visual tracking: an experimental survey. IEEE Trans Pattern Anal Mach Intell 36(7):1442\u20131468. https:\/\/doi.org\/10.1109\/TPAMI.2013.230","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"05","key":"2345_CR8","doi-asserted-by":"publisher","first-page":"6552","DOI":"10.1109\/TPAMI.2022.3212594","volume":"45","author":"S Javed","year":"2023","unstructured":"Javed S, Danelljan M, Khan F, Khan M, Felsberg M, Matas J (2023) Visual object tracking with discriminative filters and siamese networks: a survey and outlook. IEEE Trans Pattern Anal Mach Intell 45(05):6552\u20136574. https:\/\/doi.org\/10.1109\/TPAMI.2022.3212594","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2345_CR9","doi-asserted-by":"crossref","unstructured":"Kugarajeevan J, Kokul T, Ramanan A, Fernando, S (2023) Transformers in single object tracking: an experimental survey. IEEE Access","DOI":"10.1109\/ACCESS.2023.3298440"},{"key":"2345_CR10","doi-asserted-by":"publisher","unstructured":"Zhang Y, Wang T, Liu K, Zhang B, Chen L (2021) Recent advances of single-object tracking methods: a brief survey. Neurocomputing 455, 1\u201311 https:\/\/doi.org\/10.1016\/j.neucom.2021.05.011","DOI":"10.1016\/j.neucom.2021.05.011"},{"key":"2345_CR11","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: Transformers for image recognition at scale. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"2345_CR12","doi-asserted-by":"publisher","unstructured":"Wei X, Bai Y, Zheng Y, Shi D, Gong Y (2023) Autoregressive visual tracking. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 9697\u20139706. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00935","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"2345_CR13","doi-asserted-by":"crossref","unstructured":"Chen X, Peng H, Wang D, Lu H, Hu H (2023) Seqtrack: Sequence to sequence learning for visual object tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 14572\u201314581","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"2345_CR14","doi-asserted-by":"publisher","unstructured":"Zhang H, Liang J, Zhang J, Zhang T, Lin Y, Wang Y (2023) Attention-driven memory network for online visual tracking. IEEE Transactions on Neural Networks and Learning Systems, 1\u201314 https:\/\/doi.org\/10.1109\/TNNLS.2023.3299412","DOI":"10.1109\/TNNLS.2023.3299412"},{"key":"2345_CR15","doi-asserted-by":"publisher","unstructured":"Zhao X, Liu Y, Han G (2021) Cooperative use of recurrent neural network and siamese region proposal network for robust visual tracking. IEEE Access 9, 57704\u201357715 https:\/\/doi.org\/10.1109\/ACCESS.2021.3072778","DOI":"10.1109\/ACCESS.2021.3072778"},{"key":"2345_CR16","doi-asserted-by":"publisher","unstructured":"Gao J, Zhang T, Xu C (2019) Graph convolutional tracking. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 4644\u20134654 https:\/\/doi.org\/10.1109\/CVPR.2019.00478","DOI":"10.1109\/CVPR.2019.00478"},{"key":"2345_CR17","doi-asserted-by":"publisher","unstructured":"Wang Z, Zhou Z, Chen F, Xu J, Pei W, Lu G (2023) Robust tracking via fully exploring background prior knowledge. IEEE Transactions on Circuits and Systems for Video Technology, 1\u20131 https:\/\/doi.org\/10.1109\/TCSVT.2023.3323702","DOI":"10.1109\/TCSVT.2023.3323702"},{"key":"2345_CR18","doi-asserted-by":"publisher","unstructured":"Yang T, Chan AB (2017) Recurrent filter learning for visual tracking. In: 2017 IEEE International conference on computer vision workshops (ICCVW), pp. 2010\u20132019. https:\/\/doi.org\/10.1109\/ICCVW.2017.235","DOI":"10.1109\/ICCVW.2017.235"},{"key":"2345_CR19","doi-asserted-by":"publisher","unstructured":"Zhao H, Wang D, Lu H (2023) Representation learning for visual object tracking by masked appearance transfer. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 18696\u201318705. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01793","DOI":"10.1109\/CVPR52729.2023.01793"},{"key":"2345_CR20","doi-asserted-by":"publisher","unstructured":"Wu Q, Yang T, Liu Z, Wu B, Shan Y, Chan AB (2023) Dropmae: Masked autoencoders with spatial-attention dropout for tracking tasks. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 14561\u201314571. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01399","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"2345_CR21","doi-asserted-by":"publisher","unstructured":"Guo J, Xu T, Jiang S, Shen Z (2018) Generating reliable online adaptive templates for visual tracking. In: 2018 25th IEEE international conference on image processing (ICIP), pp. 226\u2013230. https:\/\/doi.org\/10.1109\/ICIP.2018.8451440","DOI":"10.1109\/ICIP.2018.8451440"},{"key":"2345_CR22","doi-asserted-by":"publisher","unstructured":"Song Y, Ma C, Wu X, Gong L, Bao L, Zuo W, Shen C, Lau R, Yang M-H (2018) Vital: visual tracking via adversarial learning, pp. 8990\u20138999. https:\/\/doi.org\/10.1109\/CVPR.2018.00937","DOI":"10.1109\/CVPR.2018.00937"},{"key":"2345_CR23","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1016\/j.neunet.2022.01.010","volume":"148","author":"B Yao","year":"2022","unstructured":"Yao B, Li J, Xue S, Wu J, Guan H, Chang J, Ding Z (2022) Garat: Generative adversarial learning for robust and accurate tracking. Neural Netw 148:206\u2013218. https:\/\/doi.org\/10.1016\/j.neunet.2022.01.010","journal-title":"Neural Netw"},{"issue":"2","key":"2345_CR24","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1109\/TASE.2019.2948402","volume":"17","author":"Y Yin","year":"2020","unstructured":"Yin Y, Xu D, Wang X, Zhang L (2020) Adversarial feature sampling learning for efficient visual tracking. IEEE Trans Auto Sci Eng 17(2):847\u2013857. https:\/\/doi.org\/10.1109\/TASE.2019.2948402","journal-title":"IEEE Trans Auto Sci Eng"},{"key":"2345_CR25","doi-asserted-by":"publisher","unstructured":"Zhang J, Zhang Y (2023) Siamese network for object tracking with diffusion model. ICDIP \u201923. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3604078.3604132","DOI":"10.1145\/3604078.3604132"},{"key":"2345_CR26","doi-asserted-by":"publisher","unstructured":"Wang X, Li C, Luo B, Tang J (2018) Sint++: Robust visual tracking via adversarial positive instance generation. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2018.00511","DOI":"10.1109\/CVPR.2018.00511"},{"key":"2345_CR27","doi-asserted-by":"publisher","unstructured":"Kwon J (2020) Robust visual tracking based on variational auto-encoding markov chain monte carlo. Inform Sci 512, 1308\u20131323 https:\/\/doi.org\/10.1016\/j.ins.2019.09.015","DOI":"10.1016\/j.ins.2019.09.015"},{"key":"2345_CR28","doi-asserted-by":"publisher","first-page":"110849","DOI":"10.1016\/j.knosys.2023.110849","volume":"278","author":"W Zhu","year":"2023","unstructured":"Zhu W, Xu L, Meng J (2023) Consistency-based self-supervised visual tracking by using query-communication transformer. Knowl-Based Syst 278:110849. https:\/\/doi.org\/10.1016\/j.knosys.2023.110849","journal-title":"Knowl-Based Syst"},{"key":"2345_CR29","unstructured":"Li X, Liu S, De\u00a0Mellow S, Wang X, Kautz J, Yang M-H (2019) Joint-task self-supervised learning for temporal correspondence. In: NeurIPS"},{"key":"2345_CR30","doi-asserted-by":"publisher","first-page":"109318","DOI":"10.1016\/j.knosys.2022.109318","volume":"251","author":"W Zhu","year":"2022","unstructured":"Zhu W, Wang Z, Xu L, Meng J (2022) Exploiting temporal coherence for self-supervised visual tracking by using vision transformer. Knowl-Based Syst 251:109318. https:\/\/doi.org\/10.1016\/j.knosys.2022.109318","journal-title":"Knowl-Based Syst"},{"key":"2345_CR31","doi-asserted-by":"publisher","unstructured":"Li X, Pei W, Wang Y, He Z, Lu H, Yang M-H (2022) Self-supervised tracking via target-aware data synthesis. IEEE transactions on neural networks and learning systems, 1\u201312 https:\/\/doi.org\/10.1109\/TNNLS.2022.3231537","DOI":"10.1109\/TNNLS.2022.3231537"},{"key":"2345_CR32","doi-asserted-by":"publisher","unstructured":"Yuan W, Wang M, Chen Q (2020) Self-supervised object tracking with cycle-consistent siamese networks, pp. 10351\u201310358. https:\/\/doi.org\/10.1109\/IROS45743.2020.9341621","DOI":"10.1109\/IROS45743.2020.9341621"},{"key":"2345_CR33","unstructured":"Wang Z, Zhao H, Li Y-L, Wang S, Torr P, Bertinetto L (2021) Do different tracking tasks require different appearance models? In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 726\u2013738. Curran Associates, Inc."},{"key":"2345_CR34","doi-asserted-by":"publisher","unstructured":"Wu Q, Wan J, Chan AB (2021) Progressive unsupervised learning for visual object tracking. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 2992\u20133001. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00301","DOI":"10.1109\/CVPR46437.2021.00301"},{"key":"2345_CR35","doi-asserted-by":"publisher","unstructured":"Wang N, Song Y, Ma C, Zhou W, Liu W, Li H (2019) Unsupervised deep tracking. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 1308\u20131317. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR.2019.00140","DOI":"10.1109\/CVPR.2019.00140"},{"key":"2345_CR36","doi-asserted-by":"crossref","unstructured":"Park E, Berg AC (2018) Meta-tracker: Fast and robust online adaptation for visual object trackers. In: Proceedings of the European Conference on Computer Vision (ECCV)","DOI":"10.1007\/978-3-030-01219-9_35"},{"key":"2345_CR37","doi-asserted-by":"crossref","unstructured":"Li P, Chen B, Ouyang W, Wang D, Yang X, Lu H (2019) Gradnet: Gradient-guided network for visual object tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00626"},{"key":"2345_CR38","doi-asserted-by":"crossref","unstructured":"Bhat G, Danelljan M, Gool LV, Timofte R (2019) Learning discriminative model prediction for tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"2345_CR39","doi-asserted-by":"crossref","unstructured":"Dong X, Shen J, Shao L, Porikli F (2020) Clnet: A compact latent network for fast adjusting siamese trackers. In: European conference on computer vision, pp. 378\u2013395. Springer","DOI":"10.1007\/978-3-030-58565-5_23"},{"key":"2345_CR40","doi-asserted-by":"publisher","unstructured":"Wu Q, Chan AB (2021) Meta-graph adaptation for visual object tracking. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. https:\/\/doi.org\/10.1109\/ICME51207.2021.9428441","DOI":"10.1109\/ICME51207.2021.9428441"},{"key":"2345_CR41","doi-asserted-by":"crossref","unstructured":"Paul M, Danelljan M, Mayer C, Van\u00a0Gool L (2022) Robust visual tracking by segmentation. In: European conference on computer vision, pp. 571\u2013588. Springer","DOI":"10.1007\/978-3-031-20047-2_33"},{"key":"2345_CR42","doi-asserted-by":"publisher","unstructured":"Zhang H, Zhu M, Zhang J, Zhuo L (2019) Long-term visual object tracking via continual learning. IEEE Access 7, 182548\u2013182558 https:\/\/doi.org\/10.1109\/ACCESS.2019.2960321","DOI":"10.1109\/ACCESS.2019.2960321"},{"key":"2345_CR43","doi-asserted-by":"publisher","unstructured":"Choi J, Baik S, Choi M, Kwon J, Lee KM (2022) Visual tracking by adaptive continual meta-learning. IEEE Access 10, 9022\u20139035 https:\/\/doi.org\/10.1109\/ACCESS.2022.3143809","DOI":"10.1109\/ACCESS.2022.3143809"},{"issue":"9","key":"2345_CR44","doi-asserted-by":"publisher","first-page":"2600","DOI":"10.1109\/TCSVT.2019.2923639","volume":"29","author":"H Li","year":"2019","unstructured":"Li H, Wang X, Shen F, Li Y, Porikli F, Wang M (2019) Real-time deep tracking via corrective domain adaptation. IEEE Trans Circ Syst Video Technol 29(9):2600\u20132612. https:\/\/doi.org\/10.1109\/TCSVT.2019.2923639","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"2345_CR45","doi-asserted-by":"publisher","unstructured":"Nam H, Han B (2016) Learning multi-domain convolutional neural networks for visual tracking. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp. 4293\u20134302. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR.2016.465","DOI":"10.1109\/CVPR.2016.465"},{"key":"2345_CR46","volume-title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","author":"Z Yang","year":"2019","unstructured":"Yang Z, Dai Z, Yang Y, Carbonell J, Salakhutdinov R, Le QV (2019) XLNet: Generalized Autoregressive Pretraining for Language Understanding. Curran Associates Inc., Red Hook, NY, USA"},{"key":"2345_CR47","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1007\/978-3-319-48881-3_56","volume-title":"Computer Vision\u2014ECCV 2016 Workshops","author":"L Bertinetto","year":"2016","unstructured":"Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PHS (2016) Fully-convolutional siamese networks for object tracking. In: Hua G, J\u00e9gou H (eds) Computer Vision\u2014ECCV 2016 Workshops. Springer, Cham, pp 850\u2013865"},{"key":"2345_CR48","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/978-3-031-20047-2_20","volume-title":"Computer Vision - ECCV 2022","author":"B Ye","year":"2022","unstructured":"Ye B, Chang H, Ma B, Shan S, Chen X (2022) Joint feature learning and relation modeling for tracking: A one-stream framework. In: Avidan S, Brostow G, Ciss\u00e9 M, Farinella GM, Hassner T (eds) Computer Vision - ECCV 2022. Springer, Cham, pp 341\u2013357"},{"key":"2345_CR49","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Lu, Polosukhin I (2017) Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc"},{"key":"2345_CR50","unstructured":"SHI X, Chen Z, Wang H, Yeung D-Y, Wong W-k, WOO W-c (2015) Convolutional lstm network: A machine learning approach for precipitation nowcasting. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates, Inc."},{"issue":"11","key":"2345_CR51","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"key":"2345_CR52","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=SJU4ayYgl"},{"key":"2345_CR53","doi-asserted-by":"publisher","unstructured":"Li B, Yan J, Wu W, Zhu Z, Hu X (2018) High performance visual tracking with siamese region proposal network. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp. 8971\u20138980. https:\/\/doi.org\/10.1109\/CVPR.2018.00935","DOI":"10.1109\/CVPR.2018.00935"},{"key":"2345_CR54","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates, Inc"},{"key":"2345_CR55","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Dollar P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2345_CR56","doi-asserted-by":"crossref","unstructured":"Kirillov A, Wu Y, He K, Girshick R (2020) Pointrend: Image segmentation as rendering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"2345_CR57","doi-asserted-by":"publisher","unstructured":"Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 5686\u20135696. https:\/\/doi.org\/10.1109\/CVPR.2019.00584","DOI":"10.1109\/CVPR.2019.00584"},{"key":"2345_CR58","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations"},{"key":"2345_CR59","doi-asserted-by":"publisher","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9, 1735\u201380 https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"2345_CR60","doi-asserted-by":"publisher","unstructured":"Zhang H, Zhang J, Nie G, Hu J, Zhang WJC (2022) Residual memory inference network for regression tracking with weighted gradient harmonized loss. Inform Sci 597, 105\u2013124 https:\/\/doi.org\/10.1016\/j.ins.2022.03.047","DOI":"10.1016\/j.ins.2022.03.047"},{"key":"2345_CR61","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2345_CR62","unstructured":"Kenton JDM-WC, Toutanova LK (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of naacL-HLT, vol. 1, p. 2"},{"key":"2345_CR63","doi-asserted-by":"crossref","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2020) Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp. 7871\u20137880","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"2345_CR64","unstructured":"Kitaev N, Kaiser L, Levskaya A (2020) Reformer: The efficient transformer. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=rkgNKkHtvB"},{"key":"2345_CR65","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r P, Girshick R (2022) Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 16000\u201316009","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2345_CR66","doi-asserted-by":"publisher","unstructured":"Wang X, Zhao K, Zhang R, Ding S, Wang Y, Shen W (2022) Contrastmask: Contrastive learning to segment every thing. In: 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 11594\u201311603. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01131","DOI":"10.1109\/CVPR52688.2022.01131"},{"key":"2345_CR67","doi-asserted-by":"publisher","unstructured":"Chang H, Zhang H, Jiang L, Liu C, Freeman WT (2022) Maskgit: Masked generative image transformer. In: 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 11305\u201311315. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01103","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"2345_CR68","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: Detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp. 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"2345_CR69","doi-asserted-by":"publisher","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial networks. Adv Neural Inform Process Syst 3https:\/\/doi.org\/10.1145\/3422622","DOI":"10.1145\/3422622"},{"key":"2345_CR70","doi-asserted-by":"crossref","unstructured":"Liu S, Wang T, Bau D, Zhu J-Y, Torralba A (2020) Diverse image generation via self-conditioned gans. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.01429"},{"key":"2345_CR71","doi-asserted-by":"crossref","unstructured":"Wang Y, Wu C, Herranz L, Weijer J, Gonzalez-Garcia A, Raducanu B (2018) Transferring gans: generating images from limited data. In: Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01231-1_14"},{"key":"2345_CR72","doi-asserted-by":"publisher","unstructured":"Han C, Hayashi H, Rundo L, Araki R, Shimoda W, Muramatsu S, Furukawa Y, Mauri G, Nakayama H (2018) Gan-based synthetic brain mr image generation. In: 2018 IEEE 15th International symposium on biomedical imaging (ISBI 2018), pp. 734\u2013738. https:\/\/doi.org\/10.1109\/ISBI.2018.8363678","DOI":"10.1109\/ISBI.2018.8363678"},{"key":"2345_CR73","doi-asserted-by":"crossref","unstructured":"Mustikovela SK, De\u00a0Mello S, Prakash A, Iqbal U, Liu S, Nguyen-Phuoc T, Rother C, Kautz J (2021) Self-supervised object detection via generative image synthesis. In: Proceedings of the IEEE\/CVF International conference on computer vision (ICCV), pp. 8609\u20138618","DOI":"10.1109\/ICCV48922.2021.00849"},{"key":"2345_CR74","doi-asserted-by":"crossref","unstructured":"Li J, Liang X, Wei Y, Xu T, Feng J, Yan S (2017) Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.211"},{"key":"2345_CR75","doi-asserted-by":"crossref","unstructured":"Souly N, Spampinato C, Shah M (2017) Semi supervised semantic segmentation using generative adversarial network. In: Proceedings of the IEEE international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2017.606"},{"issue":"12","key":"2345_CR76","doi-asserted-by":"publisher","first-page":"5404","DOI":"10.1109\/TNNLS.2021.3072883","volume":"32","author":"C Zhang","year":"2021","unstructured":"Zhang C, Tang Y, Zhao C, Sun Q, Ye Z, Kurths J (2021) Multitask gans for semantic segmentation and depth completion with cycle consistency. IEEE Trans Neural Netw Learn Syst 32(12):5404\u20135415. https:\/\/doi.org\/10.1109\/TNNLS.2021.3072883","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2345_CR77","doi-asserted-by":"publisher","unstructured":"Chopra S, Hadsell R, LeCun Y (2005) Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905), vol. 1, pp. 539\u20135461. https:\/\/doi.org\/10.1109\/CVPR.2005.202","DOI":"10.1109\/CVPR.2005.202"},{"key":"2345_CR78","doi-asserted-by":"publisher","unstructured":"Ning J, Yang J, Jiang S, Zhang L, Yang M-H (2016) Object tracking via dual linear structured svm and explicit feature map, pp. 4266\u20134274. https:\/\/doi.org\/10.1109\/CVPR.2016.462","DOI":"10.1109\/CVPR.2016.462"},{"issue":"2","key":"2345_CR79","doi-asserted-by":"publisher","DOI":"10.1117\/1.2912053","volume":"17","author":"A Suwendi","year":"2008","unstructured":"Suwendi A, Allebach JP (2008) Nearest-neighbor and bilinear resampling factor estimation to detect blockiness or blurriness of an image. J Electron Imaging 17(2):023005. https:\/\/doi.org\/10.1117\/1.2912053","journal-title":"J Electron Imaging"},{"key":"2345_CR80","unstructured":"Sohl-Dickstein J, Weiss E, Maheswaranathan N, Ganguli S (2015) Deep unsupervised learning using nonequilibrium thermodynamics. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 37, pp. 2256\u20132265. PMLR, Lille, France. https:\/\/proceedings.mlr.press\/v37\/sohl-dickstein15.html"},{"key":"2345_CR81","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851. Curran Associates, Inc"},{"key":"2345_CR82","doi-asserted-by":"crossref","unstructured":"Ho J, Saharia C, Chan W, Fleet DJ, Norouzi M, Salimans T (2022) Cascaded diffusion models for high fidelity image generation. J Mach Learn Res 23(1)","DOI":"10.1145\/3528233.3530757"},{"key":"2345_CR83","unstructured":"Dhariwal P, Nichol A (2021) Diffusion models beat gans on image synthesis. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 8780\u20138794. Curran Associates, Inc"},{"key":"2345_CR84","doi-asserted-by":"crossref","unstructured":"Gu S, Chen D, Bao J, Wen F, Zhang B, Chen D, Yuan L, Guo B (2022) Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 10696\u201310706","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"2345_CR85","doi-asserted-by":"crossref","unstructured":"Peng D, Hu P, Ke Q, Liu J (2023) Diffusion-based image translation with label guidance for domain adaptive semantic segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp. 808\u2013820","DOI":"10.1109\/ICCV51070.2023.00081"},{"key":"2345_CR86","doi-asserted-by":"crossref","unstructured":"Yang X, Wang X (2023) Diffusion model as representation learner. In: Proceedings of the IEEE\/CVF International conference on computer vision (ICCV), pp. 18938\u201318949","DOI":"10.1109\/ICCV51070.2023.01736"},{"key":"2345_CR87","doi-asserted-by":"crossref","unstructured":"Chen S, Sun P, Song Y, Luo P (2023) Diffusiondet: Diffusion model for object detection. In: Proceedings of the IEEE\/CVF International conference on computer vision (ICCV), pp. 19830\u201319843","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"2345_CR88","doi-asserted-by":"crossref","unstructured":"Luo R, Song Z, Ma L, Wei J, Yang W, Yang M (2023) Diffusiontrack: Diffusion model for multi-object tracking. arXiv preprint arXiv:2308.09905","DOI":"10.1609\/aaai.v38i5.28192"},{"key":"2345_CR89","unstructured":"Song J, Meng C, Ermon S (2021) Denoising diffusion implicit models. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, OpenReview.net, (2021). https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"2345_CR90","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"5","key":"2345_CR91","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2021","unstructured":"Huang L, Zhao X, Huang K (2021) Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans Pattern AnalMach Intell 43(5):1562\u20131577. https:\/\/doi.org\/10.1109\/TPAMI.2019.2957464","journal-title":"IEEE Trans Pattern AnalMach Intell"},{"key":"2345_CR92","doi-asserted-by":"publisher","unstructured":"Fan H, Lin L, Yang F, Chu P, Deng G, Yu S, Bai H, Xu Y, Liao C, Ling H (2019) Lasot: A high-quality benchmark for large-scale single object tracking. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5369\u20135378. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR.2019.00552","DOI":"10.1109\/CVPR.2019.00552"},{"key":"2345_CR93","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114"},{"issue":"1","key":"2345_CR94","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S Kullback","year":"1951","unstructured":"Kullback S, Leibler RA (1951) On information and sufficiency. Ann Math Stat 22(1):79\u201386","journal-title":"Ann Math Stat"},{"key":"2345_CR95","unstructured":"Razavi A, Oord A, Vinyals O (2019) Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems 32"},{"key":"2345_CR96","doi-asserted-by":"crossref","unstructured":"Cai L, Gao H, Ji S (2019) Multi-stage variational auto-encoders for coarse-to-fine image generation. In: Proceedings of the 2019 SIAM International Conference on Data Mining, pp. 630\u2013638. SIAM","DOI":"10.1137\/1.9781611975673.71"},{"key":"2345_CR97","doi-asserted-by":"crossref","unstructured":"Bao J, Chen D, Wen F, Li H, Hua G (2017) Cvae-gan: fine-grained image generation through asymmetric training. In: Proceedings of the IEEE international conference on computer vision, pp. 2745\u20132754","DOI":"10.1109\/ICCV.2017.299"},{"issue":"5","key":"2345_CR98","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1109\/TEVC.2020.3047220","volume":"25","author":"X Chen","year":"2020","unstructured":"Chen X, Sun Y, Zhang M, Peng D (2020) Evolving deep convolutional variational autoencoders for image classification. IEEE Trans Evol Comput 25(5):815\u2013829","journal-title":"IEEE Trans Evol Comput"},{"issue":"21","key":"2345_CR99","doi-asserted-by":"publisher","first-page":"21916","DOI":"10.1109\/JIOT.2022.3182313","volume":"9","author":"LD Chamain","year":"2022","unstructured":"Chamain LD, Qi S, Ding Z (2022) End-to-end image classification and compression with variational autoencoders. IEEE Internet Things J 9(21):21916\u201321931","journal-title":"IEEE Internet Things J"},{"key":"2345_CR100","doi-asserted-by":"publisher","unstructured":"Tao R, Gavves E, Smeulders AWM (2016) Siamese instance search for tracking. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1420\u20131429. https:\/\/doi.org\/10.1109\/CVPR.2016.158","DOI":"10.1109\/CVPR.2016.158"},{"key":"2345_CR101","doi-asserted-by":"crossref","unstructured":"Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, Cehovin\u00a0Zajc L, Vojir T, Bhat G, Lukezic A, Eldesokey A, Fernandez G, Garcia-Martin A, Iglesias-Arias A, Aydin\u00a0Alatan A, Gonzalez-Garcia A, Petrosino A, Memarmoghadam A, Vedaldi A, Muhic A, He A, Smeulders A, Perera AG, Li B, Chen B, Kim C, Xu C, Xiong C, Tian C, Luo C, Sun C, Hao C, Kim D, Mishra D, Chen D, Wang D, Wee D, Gavves E, Gundogdu E, Velasco-Salido E, Shahbaz\u00a0Khan F, Yang F, Zhao F, Li F, Battistone F, De\u00a0Ath G, Subrahmanyam GRKS, Bastos G, Ling H, Kiani\u00a0Galoogahi H, Lee H, Li H, Zhao H, Fan H, Zhang H, Possegger H, Li H, Lu H, Zhi H, Li H, Lee H, Jin\u00a0Chang H, Drummond I, Valmadre J, Spencer\u00a0Martin J, Chahl J, Young\u00a0Choi J, Li J, Wang J, Qi J, Sung J, Johnander J, Henriques J, Choi J, Weijer J, Rodriguez\u00a0Herranz J, Martinez JM, Kittler J, Zhuang J, Gao J, Grm K, Zhang L, Wang L, Yang L, Rout L, Si L, Bertinetto L, Chu L, Che M, Edoardo\u00a0Maresca M, Danelljan M, Yang M-H, Abdelpakey M, Shehata M, Kang M, Lee N, Wang N, Miksik O, Moallem P, Vicente-Monivar P, Senna P, Li P, Torr P, Mariam\u00a0Raju P, Ruihe Q, Wang Q, Zhou Q, Guo Q, Martin-Nieto R, Krishna\u00a0Gorthi R, Tao R, Bowden R, Everson R, Wang R, Yun S, Choi S, Vivas S, Bai S, Huang S, Wu S, Hadfield S, Wang S, Golodetz S, Ming T, Xu T, Zhang T, Fischer T, Santopietro V, Struc V, Wei W, Zuo W, Feng W, Wu W, Zou W, Hu W, Zhou W, Zeng W, Zhang X, Wu X, Wu X-J, Tian X, Li Y, Lu Y, Wei\u00a0Law Y, Wu Y, Demiris Y, Yang Y, Jiao Y, Li Y, Zhang Y, Sun Y, Zhang Z, Zhu Z, Feng Z-H, Wang Z, He Z (2018) The sixth visual object tracking vot2018 challenge results. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops","DOI":"10.1007\/978-3-030-11009-3_1"},{"issue":"11","key":"2345_CR102","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1109\/TPAMI.2005.223","volume":"27","author":"Z Khan","year":"2005","unstructured":"Khan Z, Balch T, Dellaert F (2005) Mcmc-based particle filtering for tracking a variable number of interacting targets. IEEE Trans Pattern Anal Mach Intell 27(11):1805\u20131819. https:\/\/doi.org\/10.1109\/TPAMI.2005.223","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2345_CR103","unstructured":"Tomczak J, Welling M (2018) Vae with a vampprior. In: Storkey, A., Perez-Cruz, F. (eds.) Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 84, pp. 1214\u20131223. PMLR. https:\/\/proceedings.mlr.press\/v84\/tomczak18a.html"},{"issue":"6","key":"2345_CR104","doi-asserted-by":"publisher","first-page":"7099","DOI":"10.1109\/TPAMI.2022.3225573","volume":"45","author":"T Zhou","year":"2023","unstructured":"Zhou T, Porikli F, Crandall DJ, Van Gool L, Wang W (2023) A survey on deep learning technique for video segmentation. IEEE Trans Pattern Anal Mach Intell 45(6):7099\u20137122. https:\/\/doi.org\/10.1109\/TPAMI.2022.3225573","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2345_CR105","doi-asserted-by":"publisher","unstructured":"Xu J, Wang X (2021) Rethinking self-supervised correspondence learning: A video frame-level similarity perspective. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10055\u201310065. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00992","DOI":"10.1109\/ICCV48922.2021.00992"},{"key":"2345_CR106","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, Viola F, Green T, Back T, Natsev A, Suleyman M, Zisserman A (2017) The kinetics human action video dataset. abs\/1705.06950"},{"key":"2345_CR107","doi-asserted-by":"crossref","unstructured":"Vondrick C, Shrivastava A, Fathi A, Guadarrama S, Murphy K (2018) Tracking emerges by colorizing videos. In: Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01261-8_24"},{"issue":"3","key":"2345_CR108","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet Large Scale Visual Recognition Challenge. Int J Comput Vis (IJCV) 115(3):211\u2013252. https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int J Comput Vis (IJCV)"},{"key":"2345_CR109","doi-asserted-by":"publisher","unstructured":"Wu Y, Lim J, Yang M-H (2013) Online object tracking: A benchmark. In: 2013 IEEE Conference on computer vision and pattern recognition, pp. 2411\u20132418. https:\/\/doi.org\/10.1109\/CVPR.2013.312","DOI":"10.1109\/CVPR.2013.312"},{"key":"2345_CR110","doi-asserted-by":"publisher","unstructured":"Perazzi F, Pont-Tuset J, McWilliams B, Van\u00a0Gool L, Gross M, Sorkine-Hornung A (2016) A benchmark dataset and evaluation methodology for video object segmentation. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp. 724\u2013732. https:\/\/doi.org\/10.1109\/CVPR.2016.85","DOI":"10.1109\/CVPR.2016.85"},{"key":"2345_CR111","unstructured":"Milan A, Leal-Taix\u00e9 L, Reid ID, Roth S, Schindler K (2016) Mot16: A benchmark for multi-object tracking. ArXiv abs\/1603.00831"},{"key":"2345_CR112","doi-asserted-by":"publisher","unstructured":"Voigtlaender P, Krause M, Osep A, Luiten J, Sekar BBG, Geiger A, Leibe B (2019) Mots: Multi-object tracking and segmentation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7934\u20137943. https:\/\/doi.org\/10.1109\/CVPR.2019.00813","DOI":"10.1109\/CVPR.2019.00813"},{"key":"2345_CR113","doi-asserted-by":"publisher","unstructured":"Andriluka M, Iqbal U, Insafutdinov E, Pishchulin L, Milan A, Gall J, Schiele B (2018) Posetrack: A benchmark for human pose estimation and tracking. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp. 5167\u20135176. https:\/\/doi.org\/10.1109\/CVPR.2018.00542","DOI":"10.1109\/CVPR.2018.00542"},{"key":"2345_CR114","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H (2019) Deeper and wider siamese networks for real-time visual tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4591\u20134600","DOI":"10.1109\/CVPR.2019.00472"},{"key":"2345_CR115","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision - ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick CL, Doll\u00e1r P (2014) Edge boxes: Locating object proposals from edges. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision - ECCV 2014. Springer, Cham, pp 391\u2013405"},{"key":"2345_CR116","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 1597\u20131607. PMLR, https:\/\/proceedings.mlr.press\/v119\/chen20j.html"},{"key":"2345_CR117","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9729\u20139738","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2345_CR118","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 1126\u20131135. PMLR. https:\/\/proceedings.mlr.press\/v70\/finn17a.html"},{"key":"2345_CR119","doi-asserted-by":"publisher","unstructured":"Danelljan M, Bhat G, Khan F, Felsberg M (2019) Atom: Accurate tracking by overlap maximization. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 4655\u20134664. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR.2019.00479","DOI":"10.1109\/CVPR.2019.00479"},{"key":"2345_CR120","doi-asserted-by":"crossref","unstructured":"Li B, Wu W, Wang Q, Zhang F, Xing J, Yan J (2019) Siamrpn++: Evolution of siamese visual tracking with very deep networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"2345_CR121","doi-asserted-by":"crossref","unstructured":"Bhat G, Lawin FJ, Danelljan M, Robinson A, Felsberg M, Van\u00a0Gool L, Timofte R (2020) Learning what to learn for video object segmentation. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16, pp. 777\u2013794. Springer","DOI":"10.1007\/978-3-030-58536-5_46"},{"key":"2345_CR122","unstructured":"Hinton G Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531"},{"issue":"12","key":"2345_CR123","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2017","unstructured":"Li Z, Hoiem D (2017) Learning without forgetting. IEEE Trans Pattern Anal Mach Intell 40(12):2935\u20132947","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2345_CR124","doi-asserted-by":"publisher","unstructured":"Lin T, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2999\u20133007. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"issue":"1","key":"2345_CR125","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/34.655648","volume":"20","author":"K-K Sung","year":"1998","unstructured":"Sung K-K, Poggio T (1998) Example-based learning for view-based human face detection. IEEE Trans Pattern Anal Mach Intell 20(1):39\u201351. https:\/\/doi.org\/10.1109\/34.655648","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2345_CR126","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"2345_CR127","doi-asserted-by":"publisher","unstructured":"Ma C, Huang J-B, Yang X, Yang M-H (2015) Hierarchical convolutional features for visual tracking. In: 2015 IEEE international conference on computer vision (ICCV), pp. 3074\u20133082. https:\/\/doi.org\/10.1109\/ICCV.2015.352","DOI":"10.1109\/ICCV.2015.352"},{"issue":"3","key":"2345_CR128","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2015","unstructured":"Henriques JF, Caseiro R, Martins P, Batista J (2015) High-speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 37(3):583\u2013596. https:\/\/doi.org\/10.1109\/TPAMI.2014.2345390","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2345_CR129","doi-asserted-by":"publisher","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139. https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2345_CR130","doi-asserted-by":"publisher","unstructured":"Fan H, Bai H, Lin L, Yang F, Chu P, Deng G, Yu S, Harshit Huang M, Liu J, Xu Y, Liao C, Yuan L, Ling H (2021) Lasot: A high-quality large-scale single object tracking benchmark. Int. J. Comput. Vision 129(2), 439\u2013461 https:\/\/doi.org\/10.1007\/s11263-020-01387-y","DOI":"10.1007\/s11263-020-01387-y"},{"key":"2345_CR131","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1007\/978-3-030-01246-5_19","volume-title":"Computer Vision - ECCV 2018","author":"M Muller","year":"2018","unstructured":"Muller M, Bibi A, Giancola S, Alsubaihi S, Ghanem B (2018) Trackingnet: A large-scale dataset and benchmark for object tracking in the wild. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer Vision - ECCV 2018. Springer, Cham, pp 310\u2013327"},{"key":"2345_CR132","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision - ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision - ECCV 2014. Springer, Cham, pp 740\u2013755"},{"key":"2345_CR133","doi-asserted-by":"crossref","unstructured":"Mueller M, Smith N, Ghanem B (2016) A benchmark and simulator for uav tracking. In: Computer Vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 445\u2013461. Springer","DOI":"10.1007\/978-3-319-46448-0_27"},{"issue":"2","key":"2345_CR134","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1109\/TPAMI.2015.2417577","volume":"38","author":"A Li","year":"2016","unstructured":"Li A, Lin M, Wu Y, Yang M-H, Yan S (2016) Nus-pro: A new visual tracking challenge. IEEE Trans Pattern Anal Mach Intell 38(2):335\u2013349. https:\/\/doi.org\/10.1109\/TPAMI.2015.2417577","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2345_CR135","doi-asserted-by":"publisher","unstructured":"Galoogahi H, Fagg A, Huang C, Ramanan D, Lucey S (2017) Need for speed: A benchmark for higher frame rate object tracking. In: 2017 IEEE international conference on computer vision (ICCV), pp. 1134\u20131143. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/ICCV.2017.128","DOI":"10.1109\/ICCV.2017.128"},{"key":"2345_CR136","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision - ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: Fitzgibbon A, Lazebnik S, Perona P, Sato Y, Schmid C (eds) Computer Vision - ECCV 2012. Springer, Berlin, Heidelberg, pp 746\u2013760"},{"key":"2345_CR137","doi-asserted-by":"crossref","unstructured":"Xu N, Yang L, Fan Y, Yang J, Yue D, Liang Y, Price B, Cohen S, Huang T (2018) Youtube-vos: Sequence-to-sequence video object segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV)","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"2345_CR138","doi-asserted-by":"publisher","unstructured":"Real E, Shlens J, Mazzocchi S, Pan X, Vanhoucke V (2017) Youtube-boundingboxes: A large high-precision human-annotated data set for object detection in video. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7464\u20137473. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/CVPR.2017.789","DOI":"10.1109\/CVPR.2017.789"},{"key":"2345_CR139","doi-asserted-by":"publisher","unstructured":"Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, Zajc L, Voj\u00edr T, H\u00e4ger G, Luke\u017ei\u010d A, Fernandez\u00a0Dominguez G, Gupta A, Petrosino A, Memarmoghadam A, Garcia-Martin A, Montero A, Vedaldi A, Robinson A, Ma A, Varfolomieiev A, Chi Z (2016) The visual object tracking vot2016 challenge results, vol. 9914, pp. 777\u2013823. https:\/\/doi.org\/10.1007\/978-3-319-48881-3_54","DOI":"10.1007\/978-3-319-48881-3_54"},{"key":"2345_CR140","doi-asserted-by":"publisher","unstructured":"Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, Zajc LC, Voj\u00edr T, H\u00e4ger G, Luke\u017eic A, Eldesokey A, Fern\u00e1ndez G, Garcia-Martin A, Muhic A, Petrosino A, Memarmoghadam A, Vedaldi A, Manzanera A, Tran A, Alatan A, Mocanu B, Chen B, Huang C, Xu C, Sun C, Du D, Zhang D, Du D, Mishra D, Gundogdu E, Velasco-Salido E, Khan FS, Battistone F, Subrahmanyam GRKS, Bhat G, Huang G, Bastos G, Seetharaman G, Zhang H, Li H, Lu H, Drummond I, Valmadre J, Jeong J-c, Cho J-i, Lee J-Y, Noskova J, Zhu J, Gao J, Liu J, Kim J-W, Henriques JF, Mart\u00ednez JM, Zhuang J, Xing J, Gao J, Chen K, Palaniappan K, Lebeda K, Gao K, Kitani KM, Zhang L, Wang L, Yang L, Wen L, Bertinetto L, Poostchi M, Danelljan M, Mueller M, Zhang M, Yang M-H, Xie N, Wang N, Miksik O, Moallem P, Venugopal PM, Senna P, Torr PHS, Wang Q, Yu Q, Huang Q, Mart\u00edn-Nieto R, Bowden R, Liu R, Tapu R, Hadfield S, Lyu S, Golodetz S, Choi S, Zhang T, Zaharia T, Santopietro V, Zou W, Hu W, Tao W, Li W, Zhou W, Yu X, Bian X, Li Y, Xing Y, Fan Y, Zhu Z, Zhang Z, He Z (2017) The visual object tracking vot2017 challenge results. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1949\u20131972.https:\/\/doi.org\/10.1109\/ICCVW.2017.230","DOI":"10.1109\/ICCVW.2017.230"},{"key":"2345_CR141","doi-asserted-by":"publisher","unstructured":"Kristan, M., Matas, J., Leonardis, A., Felsberg, M., Pflugfelder, R., K\u00e4m\u00e4r\u00e4inen, J.-K., Zajc, L.C., Drbohlav, O., Lukezic, A., Berg, A., Eldesokey, A., K\u00e4pyl\u00e4, J., Fern\u00e1ndez, G., Gonzalez-Garcia, A., Memarmoghadam, A., Lu, A., He, A., Varfolomieiev, A., Chan, A., Tripathi, A.S., Smeulders, A., Pedasingu, B.S., Chen, B.X., Zhang, B., Wu, B., Li, B., He, B., Yan, B., Bai, B., Li, B., Li, B., Kim, B.H., Ma, C., Fang, C., Qian, C., Chen, C., Li, C., Zhang, C., Tsai, C.-Y., Luo, C., Micheloni, C., Zhang, C., Tao, D., Gupta, D., Song, D., Wang, D., Gavves, E., Yi, E., Khan, F.S., Zhang, F., Wang, F., Zhao, F., Ath, G.D., Bhat, G., Chen, G., Wang, G., Li, G., Cevikalp, H., Du, H., Zhao, H., Saribas, H., Jung, H.M., Bai, H., Yu, H., Peng, H., Lu, H., Li, H., Li, J., Li, J., Fu, J., Chen, J., Gao, J., Zhao, J., Tang, J., Li, J., Wu, J., Liu, J., Wang, J., Qi, J., Zhang, J., Tsotsos, J.K., Lee, J.H., Weijer, J.v.d., Kittler, J., Lee, J.H., Zhuang, J., Zhang, K., Wang, K., Dai, K., Chen, L., Liu, L., Guo, L., Zhang, L., Wang, L., Wang, L., Zhang, L., Wang, L., Zhou, L., Zheng, L., Rout, L., Gool, L.V., Bertinetto, L., Danelljan, M., Dunnhofer, M., Ni, M., Kim, M.Y., Tang, M., Yang, M.-H., Paluru, N., Martinel, N., Xu, P., Zhang, P., Zheng, P., Zhang, P., Torr, P.H.S., Wang, Q.Z.Q., Guo, Q., Timofte, R., Gorthi, R.K., Everson, R., Han, R., Zhang, R., You, S., Zhao, S.-C., Zhao, S., Li, S., Li, S., Ge, S., Bai, S., Guan, S., Xing, T., Xu, T., Yang, T., Zhang, T., Vojir, T., Feng, W., Hu, W., Wang, W., Tang, W., Zeng, W., Liu, W., Chen, X., Qiu, X., Bai, X., Wu, X.-J., Yang, X., Chen, X., Li, X., Sun, X., Chen, X., Tian, X., Tang, X., Zhu, X.-F., Huang, Y., Chen, Y., Lian, Y., Gu, Y., Liu, Y., Chen, Y., Zhang, Y., Xu, Y., Wang, Y., Li, Y., Zhou, Y., Dong, Y., Xu, Y., Zhang, Y., Li, Y., Luo, Z.W.Z., Zhang, Z., Feng, Z.-H., He, Z., Song, Z., Chen, Z., Zhang, Z., Wu, Z., Xiong, Z., Huang, Z., Teng, Z., Ni, Z.: The seventh visual object tracking vot2019 challenge results. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 2206\u20132241 (2019). https:\/\/doi.org\/10.1109\/ICCVW.2019.00276","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"2345_CR142","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1007\/978-3-030-68238-5_39","volume-title":"Computer Vision - ECCV 2020 Workshops","author":"M Kristan","year":"2020","unstructured":"Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, K\u00e4m\u00e4r\u00e4inen J-K, Danelljan M, Zajc L\u010c, Luke\u017ei\u010d A, Drbohlav O, He L, Zhang Y, Yan S, Yang J, Fern\u00e1ndez G, Hauptmann A, Memarmoghadam A, Garc\u00eda-Mart\u00edn \u00c1, Robinson A, Varfolomieiev A, Gebrehiwot AH, Uzun B, Yan B, Li B, Qian C, Tsai C-Y, Micheloni C, Wang D, Wang F, Xie F, Lawin FJ, Gustafsson F, Foresti GL, Bhat G, Chen G, Ling H, Zhang H, Cevikalp H, Zhao H, Bai H, Kuchibhotla HC, Saribas H, Fan H, Ghanei-Yakhdan H, Li H, Peng H, Lu H, Li H, Khaghani J, Bescos J, Li J, Fu J, Yu J, Xu J, Kittler J, Yin J, Lee J, Yu K, Liu K, Yang K, Dai K, Cheng L, Zhang L, Wang L, Wang L, Van Gool L, Bertinetto L, Dunnhofer M, Cheng M, Dasari MM, Wang N, Wang N, Zhang P, Torr PHS, Wang Q, Timofte R, Gorthi RKS, Choi S, Marvasti-Zadeh SM, Zhao S, Kasaei S, Qiu S, Chen S, Sch\u00f6n TB, Xu T, Lu W, Hu W, Zhou W, Qiu X, Ke X, Wu X-J, Zhang X, Yang X, Zhu X, Jiang Y, Wang Y, Chen Y, Ye Y, Li Y, Yao Y, Lee Y, Gu Y, Wang Z, Tang Z, Feng Z-H, Mai Z, Zhang Z, Wu Z, Ma Z (2020) The eighth visual object tracking vot2020 challenge results. In: Bartoli A, Fusiello A (eds) Computer Vision - ECCV 2020 Workshops. Springer, Cham, pp 547\u2013601"},{"key":"2345_CR143","doi-asserted-by":"crossref","unstructured":"Li Z, Tao R, Gavves E, Snoek CGM, Smeulders AWM (2017) Tracking by natural language specification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2017.777"},{"key":"2345_CR144","doi-asserted-by":"crossref","unstructured":"Li Y, Yu J, Cai Z, Pan Y (2022) Cross-modal target retrieval for tracking by natural language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 4931\u20134940","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"2345_CR145","doi-asserted-by":"crossref","unstructured":"Zhou L, Zhou Z, Mao K, He Z (2023) Joint visual grounding and tracking with natural language specification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 23151\u201323160","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"2345_CR146","doi-asserted-by":"publisher","unstructured":"Li X, Huang Y, He Z, Wang Y, Lu H, Yang M (2023) Citetracker: Correlating image and text for visual tracking. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9940\u20139949. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00915","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"2345_CR147","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler D, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901. Curran Associates, Inc.,"},{"key":"2345_CR148","doi-asserted-by":"crossref","unstructured":"Chen K, Liu Z, Hong L, Xu H, Li Z, Yeung D-Y (2023) Mixed autoencoder for self-supervised visual representation learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 22742\u201322751","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"2345_CR149","doi-asserted-by":"crossref","unstructured":"Dave IR, Jenni S, Shah M (2023) No More Shortcuts: Realizing the Potential of Temporal Self-Supervision","DOI":"10.1609\/aaai.v38i2.27913"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02345-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02345-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02345-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T10:43:34Z","timestamp":1738665814000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02345-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,26]]},"references-count":149,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["2345"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02345-7","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,26]]},"assertion":[{"value":"25 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2024","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 have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors consent to publish this work in the International Journal of Machine Learning and Cybernetics.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}