{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T19:37:44Z","timestamp":1774640264698,"version":"3.50.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031234798","type":"print"},{"value":"9783031234804","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-23480-4_1","type":"book-chapter","created":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T09:09:35Z","timestamp":1674464975000},"page":"3-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Unsupervised Pose Estimation by\u00a0Means of\u00a0an\u00a0Innovative Vision Transformer"],"prefix":"10.1007","author":[{"given":"Nicolo\u2019","family":"Brandizzi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Fanti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Gallotta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuele","family":"Russo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Iocchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Napoli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,24]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Scape: shape completion and animation of people. In: ACM SIGGRAPH 2005, pp. 408\u2013416 (2005)","DOI":"10.1145\/1186822.1073207"},{"key":"1_CR3","unstructured":"Atito, S., Awais, M., Kittler, J.: SIT: self-supervised vision transformer (2021)"},{"key":"1_CR4","unstructured":"Avanzato, R., Beritelli, F., Russo, M., Russo, S., Vaccaro, M.: Yolov3-based mask and face recognition algorithm for individual protection applications, vol. 2768, pp. 41\u201345 (2020)"},{"issue":"1","key":"1_CR5","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1109\/JSEN.2019.2940612","volume":"20","author":"TL Baldi","year":"2019","unstructured":"Baldi, T.L., Farina, F., Garulli, A., Giannitrapani, A., Prattichizzo, D.: Upper body pose estimation using wearable inertial sensors and multiplicative Kalman filter. IEEE Sens. J. 20(1), 492\u2013500 (2019)","journal-title":"IEEE Sens. J."},{"key":"1_CR6","unstructured":"Brandizzi, N., Bianco, V., Castro, G., Russo, S., Wajda, A.: Automatic RGB inference based on facial emotion recognition, vol. 3092, pp. 66\u201374 (2021)"},{"issue":"2","key":"1_CR7","first-page":"45","volume":"13","author":"G Capizzi","year":"2016","unstructured":"Capizzi, G., Lo Sciuto, G., Napoli, C., Tramontana, E., Wozniak, M.: A novel neural networks-based texture image processing algorithm for orange defects classification. Int. J. Comput. Sci. Appl. 13(2), 45\u201360 (2016)","journal-title":"Int. J. Comput. Sci. Appl."},{"key":"1_CR8","unstructured":"Chalearn: Montalbano v2 dataset, eCCV 2014 (2014)"},{"key":"1_CR9","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020)"},{"issue":"4","key":"1_CR10","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.3390\/s20041074","volume":"20","author":"W Chen","year":"2020","unstructured":"Chen, W., et al.: A survey on hand pose estimation with wearable sensors and computer-vision-based methods. Sensors 20(4), 1074 (2020)","journal-title":"Sensors"},{"key":"1_CR11","unstructured":"Chithrananda, S., Grand, G., Ramsundar, B.: Chemberta: large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885 (2020)"},{"key":"1_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-030-58607-2_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Choutas","year":"2020","unstructured":"Choutas, V., Pavlakos, G., Bolkart, T., Tzionas, D., Black, M.J.: Monocular expressive body regression through body-driven attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 20\u201340. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_2"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Das, S., Kishore, P.S.R., Bhattacharya, U.: An end-to-end framework for unsupervised pose estimation of occluded pedestrians. In: 2020 IEEE International Conference on Image Processing (ICIP) (2020)","DOI":"10.1109\/ICIP40778.2020.9191147"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2021)"},{"key":"1_CR16","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition . In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Honari, S., Constantin, V., Rhodin, H., Salzmann, M., Fua, P.: Unsupervised learning on monocular videos for 3D human pose estimation (2021)","DOI":"10.1109\/TPAMI.2022.3215307"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Jaiswal, A., Babu, A.R., Zadeh, M.Z., Banerjee, D., Makedon, F.: A survey on contrastive self-supervised learning (2021)","DOI":"10.3390\/technologies9010002"},{"key":"1_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Liu, A.T., Li, S.W., Lee, H.Y.: Tera: self-supervised learning of transformer encoder representation for speech. arXiv preprint arXiv:2007.06028 (2020)","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, G., Hu, P., Duan, L.Y., Kot, A.C.: Global context-aware attention LSTM networks for 3D action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1647\u20131656 (2017)","DOI":"10.1109\/CVPR.2017.391"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"6","key":"1_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR25","unstructured":"Naseer, M., Ranasinghe, K., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Intriguing properties of vision transformers. arXiv preprint arXiv:2105.10497 (2021)"},{"issue":"4","key":"1_CR26","first-page":"1","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng, X.B., Abbeel, P., Levine, S., van de Panne, M.: Deepmimic: example-guided deep reinforcement learning of physics-based character skills. ACM Trans. Graph. (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR27","unstructured":"Perla, S., Das, S., Mukherjee, P., Bhattacharya, U.: Cluenet: a deep framework for occluded pedestrian pose estimation. In: 30th British Machine Vision Conference, pp. 1\u201315 (2019)"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Rhodin, H., Salzmann, M., Fua, P.: Unsupervised geometry-aware representation for 3D human pose estimation (2018)","DOI":"10.1007\/978-3-030-01249-6_46"},{"key":"1_CR29","unstructured":"Sigal, L., Black, M.J.: Humaneva: synchronized video and motion capture dataset for evaluation of articulated human motion. Brown Univertsity TR 120(2) (2006)"},{"issue":"1","key":"1_CR30","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR31","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-319-39384-1_19","volume-title":"Artificial Intelligence and Soft Computing","author":"JT Starczewski","year":"2016","unstructured":"Starczewski, J.T., Pabiasz, S., Vladymyrska, N., Marvuglia, A., Napoli, C., Wo\u017aniak, M.: Self organizing maps for 3D face understanding. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2016. LNCS (LNAI), vol. 9693, pp. 210\u2013217. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-39384-1_19"},{"issue":"4","key":"1_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459881","volume":"40","author":"S Starke","year":"2021","unstructured":"Starke, S., Zhao, Y., Zinno, F., Komura, T.: Neural animation layering for synthesizing martial arts movements. ACM Trans. Graph. (TOG) 40(4), 1\u201316 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR33","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"1_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need (2017)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Huang, M., Zhu, X., Zhao, L.: Attention-based LSTM for aspect-level sentiment classification. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 606\u2013615 (2016)","DOI":"10.18653\/v1\/D16-1058"},{"key":"1_CR36","doi-asserted-by":"publisher","unstructured":"Wozniak, M., Polap, D., Kosmider, L., Napoli, C., Tramontana, E.: A novel approach toward X-ray images classifier, pp. 1635\u20131641 (2015). https:\/\/doi.org\/10.1109\/SSCI.2015.230","DOI":"10.1109\/SSCI.2015.230"},{"key":"1_CR37","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.eswa.2016.08.068","volume":"66","author":"M Wozniak","year":"2016","unstructured":"Wozniak, M., Polap, D., Napoli, C., Tramontana, E.: Graphic object feature extraction system based on cuckoo search algorithm. Expert Syst. Appl. 66, 20\u201331 (2016). https:\/\/doi.org\/10.1016\/j.eswa.2016.08.068","journal-title":"Expert Syst. Appl."},{"key":"1_CR38","unstructured":"Xie, Z., et al.: Self-supervised learning with swin transformers. arXiv preprint arXiv:2105.04553 (2021)"},{"key":"1_CR39","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation (2017)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Habermann, M., Habibie, I., Tewari, A., Theobalt, C., Xu, F.: Monocular real-time full body capture with inter-part correlations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4811\u20134822 (2021)","DOI":"10.1109\/CVPR46437.2021.00478"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence and Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-23480-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T09:09:58Z","timestamp":1674464998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-23480-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031234798","9783031234804"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-23480-4_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAISC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence and Soft Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zakopane","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaisc2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icaisc.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}