{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T21:05:08Z","timestamp":1763499908204,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031479687"},{"type":"electronic","value":"9783031479694"}],"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\/978-3-031-47969-4_14","type":"book-chapter","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T20:02:06Z","timestamp":1701374526000},"page":"172-184","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Self-supervised Representation Learning for\u00a0Fine Grained Human Hand Action Recognition in\u00a0Industrial Assembly Lines"],"prefix":"10.1007","author":[{"given":"Fabian","family":"Sturm","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rahul","family":"Sathiyababu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harshitha","family":"Allipilli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elke","family":"Hergenroether","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Melanie","family":"Siegel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,1]]},"reference":[{"key":"14_CR1","unstructured":"Autoencoders, S.D.: Learning useful representations in a deep network with a local denoising criterion, Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio and Pierre-Antoine Manzagol. J. Mach. Learn. Res. ll, 3371\u20133408 (2010)"},{"key":"14_CR2","unstructured":"Cao, S., Xu, P., Clifton, D.A.: How to understand masked autoencoders. arXiv preprint arXiv:2202.03670 (2022)"},{"key":"14_CR3","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June 2019, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"14_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale (2021)"},{"key":"14_CR5","first-page":"35946","volume":"35","author":"C Feichtenhofer","year":"2022","unstructured":"Feichtenhofer, C., Li, Y., He, K., et al.: Masked autoencoders as spatiotemporal learners. Adv. Neural. Inf. Process. Syst. 35, 35946\u201335958 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR6","doi-asserted-by":"publisher","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense (2017). https:\/\/doi.org\/10.48550\/ARXIV.1706.04261, https:\/\/arxiv.org\/abs\/1706.04261","DOI":"10.48550\/ARXIV.1706.04261"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"14_CR8","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUS). arXiv preprint arXiv:1606.08415 (2016)"},{"issue":"7","key":"14_CR9","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527\u20131554 (2006)","journal-title":"Neural Comput."},{"key":"14_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Bach, F.R., Blei, D.M. (eds.) Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6\u201311 July 2015. JMLR Workshop and Conference Proceedings, vol. 37, pp. 448\u2013456. JMLR.org (2015). https:\/\/proceedings.mlr.press\/v37\/ioffe15.html"},{"key":"14_CR11","unstructured":"Li, Y., Si, S., Li, G., Hsieh, C.J., Bengio, S.: Learnable fourier features for multi-dimensional spatial positional encoding (2021)"},{"key":"14_CR12","doi-asserted-by":"publisher","unstructured":"Li, Y., Liu, M., Rehg, J.M.: In the eye of the beholder: gaze and actions in first person video (2020). https:\/\/doi.org\/10.48550\/ARXIV.2006.00626, https:\/\/arxiv.org\/abs\/2006.00626","DOI":"10.48550\/ARXIV.2006.00626"},{"key":"14_CR13","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. CoRR abs\/1612.03144 (2016). http:\/\/arxiv.org\/abs\/1612.03144"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. CoRR abs\/1708.02002 (2017). http:\/\/arxiv.org\/abs\/1708.02002","DOI":"10.1109\/ICCV.2017.324"},{"key":"14_CR15","unstructured":"Liu, M., Ren, S., Ma, S., Jiao, J., Chen, Y., Wang, Z., Song, W.: Gated transformer networks for multivariate time series classification. CoRR abs\/2103.14438 (2021). https:\/\/arxiv.org\/abs\/2103.14438"},{"key":"14_CR16","unstructured":"Mahdisoltani, F., Berger, G., Gharbieh, W., Fleet, D.J., Memisevic, R.: Fine-grained video classification and captioning. CoRR abs\/1804.09235 (2018). http:\/\/arxiv.org\/abs\/1804.09235"},{"key":"14_CR17","unstructured":"Ng, A.: Sparse autoencoder (NA). https:\/\/www.stanford.edu\/class\/cs294a\/sparseAutoencoder.pdf"},{"key":"14_CR18","series-title":"Lecture Notes in Networks and Systems","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1007\/978-3-031-37717-4_70","volume-title":"Intelligent Computing","author":"F Sturm","year":"2023","unstructured":"Sturm, F., Hergenroether, E., Reinhardt, J., Vojnovikj, P.S., Siegel, M.: Challenges of the creation of a dataset for vision based human hand action recognition in industrial assembly. In: Arai, K. (ed.) SAI 2023. LNNS, vol. 711, pp. 1079\u20131098. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-37717-4_70"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Tang, P., Zhang, X.: MTSMAE: masked autoencoders for multivariate time-series forecasting. In: 2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 982\u2013989. IEEE (2022)","DOI":"10.1109\/ICTAI56018.2022.00150"},{"key":"14_CR20","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural. Inf. Process. Syst. 35, 10078\u201310093 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR21","unstructured":"Trockman, A., Kolter, J.Z.: Patches are all you need? Trans. Mach. Learn. Res. 2023 (2022)"},{"key":"14_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"14_CR23","doi-asserted-by":"publisher","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096\u20131103 (2008). https:\/\/doi.org\/10.1145\/1390156.1390294","DOI":"10.1145\/1390156.1390294"},{"key":"14_CR24","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A., Bottou, L.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(12) (2010)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Anticipating visual representations from unlabeled video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 98\u2013106 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Shrivastava, A., Fathi, A., Guadarrama, S., Murphy, K.: Tracking emerges by colorizing videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 391\u2013408 (2018)","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Wu, W., Hua, Y., Wu, S., Chen, C., Lu, A., et al.: SkeletonMAE: spatial-temporal masked autoencoders for self-supervised skeleton action recognition. arXiv preprint arXiv:2209.02399 (2022)","DOI":"10.1109\/ICMEW59549.2023.00045"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9643\u20139653 (2021)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Zerveas, G., Jayaraman, S., Patel, D., Bhamidipaty, A., Eickhoff, C.: A transformer-based framework for multivariate time series representation learning. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 2114\u20132124 (2021)","DOI":"10.1145\/3447548.3467401"},{"key":"14_CR30","unstructured":"Zhang, F., et al.: MediaPipe hands: on-device real-time hand tracking. CoRR abs\/2006.10214 (2020). https:\/\/arxiv.org\/abs\/2006.10214"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47969-4_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T20:03:23Z","timestamp":1701374603000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47969-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031479687","9783031479694"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47969-4_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lake Tahoe, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.isvc.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"58","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"232% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43 (oral), 15 (poster),  25 (special tracks) out of 34 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}