{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T00:41:58Z","timestamp":1792802518627,"version":"4.5.0"},"reference-count":62,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T00:00:00Z","timestamp":1643760000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012774","name":"Innovation Fund Denmark","doi-asserted-by":"crossref","award":["7039-00068B"],"award-info":[{"award-number":["7039-00068B"]}],"id":[{"id":"10.13039\/100012774","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Vitrolife","id":[{"id":"https:\/\/ror.org\/01f55nv10","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Vitrolife","id":[{"id":"https:\/\/ror.org\/01f55nv10","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Vitrolife","id":[{"id":"https:\/\/ror.org\/01f55nv10","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Harrison.AI"},{"name":"Vitrolife","id":[{"id":"https:\/\/ror.org\/01f55nv10","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Assessing and selecting the most viable embryos for transfer is an essential part of in vitro fertilization (IVF). In recent years, several approaches have been made to improve and automate the procedure using artificial intelligence (AI) and deep learning. Based on images of embryos with known implantation data (KID), AI models have been trained to automatically score embryos related to their chance of achieving a successful implantation. However, as of now, only limited research has been conducted to evaluate how embryo selection models generalize to new clinics and how they perform in subgroup analyses across various conditions. In this paper, we investigate how a deep learning-based embryo selection model using only time-lapse image sequences performs across different patient ages and clinical conditions, and how it correlates with traditional morphokinetic parameters. The model was trained and evaluated based on a large dataset from 18 IVF centers consisting of 115,832 embryos, of which 14,644 embryos were transferred KID embryos. In an independent test set, the AI model sorted KID embryos with an area under the curve (AUC) of a receiver operating characteristic curve of 0.67 and all embryos with an AUC of 0.95. A clinic hold-out test showed that the model generalized to new clinics with an AUC range of 0.60\u20130.75 for KID embryos. Across different subgroups of age, insemination method, incubation time, and transfer protocol, the AUC ranged between 0.63 and 0.69. Furthermore, model predictions correlated positively with blastocyst grading and negatively with direct cleavages. The fully automated iDAScore v1.0 model was shown to perform at least as good as a state-of-the-art manual embryo selection model. Moreover, full automatization of embryo scoring implies fewer manual evaluations and eliminates biases due to inter- and intraobserver variation.<\/jats:p>","DOI":"10.1371\/journal.pone.0262661","type":"journal-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T13:32:00Z","timestamp":1643808720000},"page":"e0262661","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":158,"title":["Robust and generalizable embryo selection based on artificial intelligence and time-lapse image sequences"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5976-1002","authenticated-orcid":true,"given":"J\u00f8rgen","family":"Berntsen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jens","family":"Rimestad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob Theilgaard","family":"Lassen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dang","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0829-1450","authenticated-orcid":true,"given":"Mikkel Fly","family":"Kragh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,2,2]]},"reference":[{"issue":"4","key":"pone.0262661.ref001","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1016\/j.rbmo.2010.04.015","article-title":"Pregnancy achieved by transfer of a single blastocyst selected by time-lapse monitoring","volume":"21","author":"C Pribenszky","year":"2010","journal-title":"Reproductive BioMedicine Online"},{"issue":"12","key":"pone.0262661.ref002","doi-asserted-by":"crossref","first-page":"2650","DOI":"10.1093\/humrep\/deu278","article-title":"Proposed guidelines on the nomenclature and annotation of dynamic human embryo monitoring by a time-lapse user group","volume":"29","author":"HN Ciray","year":"2014","journal-title":"Human Reproduction"},{"issue":"4","key":"pone.0262661.ref003","doi-asserted-by":"crossref","first-page":"1030","DOI":"10.1016\/j.fertnstert.2013.01.089","article-title":"Selection of high potential embryos using time-lapse imaging: the era of morphokinetics","volume":"99","author":"J Herrero","year":"2013","journal-title":"Fertility and sterility"},{"issue":"10","key":"pone.0262661.ref004","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1093\/humrep\/dew188","article-title":"Development of a generally applicable morphokinetic algorithm capable of predicting the implantation potential of embryos transferred on Day 3","volume":"31","author":"BM Petersen","year":"2016","journal-title":"Human Reproduction"},{"issue":"10","key":"pone.0262661.ref005","doi-asserted-by":"crossref","first-page":"2658","DOI":"10.1093\/humrep\/der256","article-title":"The use of morphokinetics as a predictor of embryo implantation","volume":"26","author":"M Meseguer","year":"2011","journal-title":"Human Reproduction"},{"issue":"2","key":"pone.0262661.ref006","doi-asserted-by":"crossref","first-page":"R37","DOI":"10.1530\/REP-17-0004","article-title":"Time-lapse imaging of cleavage divisions in embryo quality assessment","volume":"154","author":"R Milewski","year":"2017","journal-title":"Reproduction"},{"key":"pone.0262661.ref007","doi-asserted-by":"crossref","first-page":"S38","DOI":"10.1016\/j.fertnstert.2007.07.135","article-title":"Automated detection of cell division and movement in time-lapse images of developing bovine embryos can improve selection of viable embryos","volume":"88","author":"NB Ramsing","year":"2007","journal-title":"Fertility and Sterility"},{"issue":"2","key":"pone.0262661.ref008","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1016\/j.fertnstert.2013.04.021","article-title":"Improving embryo selection using a computer-automated time-lapse image analysis test plus day 3 morphology: results from a prospective multicenter trial","volume":"100","author":"J Conaghan","year":"2013","journal-title":"Fertility and sterility"},{"issue":"2","key":"pone.0262661.ref009","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1016\/j.fertnstert.2015.11.001","article-title":"Morphokinetic analysis and embryonic prediction for blastocyst formation through an integrated time-lapse system","volume":"105","author":"Y Motato","year":"2016","journal-title":"Fertility and sterility"},{"issue":"5","key":"pone.0262661.ref010","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.rbmo.2013.02.006","article-title":"Modelling a risk classification of aneuploidy in human embryos using non-invasive morphokinetics","volume":"26","author":"A Campbell","year":"2013","journal-title":"Reproductive BioMedicine Online"},{"issue":"2","key":"pone.0262661.ref011","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.rbmo.2013.04.013","article-title":"Retrospective analysis of outcomes after IVF using an aneuploidy risk model derived from time-lapse imaging without PGS","volume":"27","author":"A Campbell","year":"2013","journal-title":"Reproductive biomedicine online"},{"issue":"10","key":"pone.0262661.ref012","first-page":"2245","volume":"31","author":"MG Minasi","year":"2016","journal-title":"Correlation between aneuploidy, standard morphology evaluation and morphokinetic development in 1730 biopsied blastocysts: a consecutive case series study"},{"key":"pone.0262661.ref013","article-title":"Evolution of embryo selection for IVF from subjective morphology assessment to objective time-lapse algorithms improves chance of live birth","author":"S Fishel","year":"2019","journal-title":"Reproductive biomedicine online"},{"issue":"6","key":"pone.0262661.ref014","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.1016\/j.fertnstert.2019.07.1322","article-title":"Time of morulation and trophectoderm quality are predictors of a live birth after euploid blastocyst transfer: a multicenter study","volume":"112","author":"L Rienzi","year":"2019","journal-title":"Fertility and sterility"},{"issue":"11","key":"pone.0262661.ref015","doi-asserted-by":"crossref","first-page":"2279","DOI":"10.1007\/s10815-019-01567-x","article-title":"Performance of Day 5 KIDScore\u2122 morphokinetic prediction models of implantation and live birth after single blastocyst transfer","volume":"36","author":"A Reignier","year":"2019","journal-title":"Journal of Assisted Reproduction and Genetics"},{"issue":"5","key":"pone.0262661.ref016","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1016\/j.rbmo.2017.06.022","article-title":"Time-lapse culture with morphokinetic embryo selection improves pregnancy and live birth chances and reduces early pregnancy loss: a meta-analysis","volume":"35","author":"C Pribenszky","year":"2017","journal-title":"Reproductive BioMedicine Online"},{"issue":"6","key":"pone.0262661.ref017","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1007\/s00404-019-05335-1","article-title":"Effect of embryo selection based morphokinetics on IVF\/ICSI outcomes: evidence from a systematic review and meta-analysis of randomized controlled trials","volume":"300","author":"Y Magdi","year":"2019","journal-title":"Archives of gynecology and obstetrics"},{"issue":"3","key":"pone.0262661.ref018","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1016\/j.fertnstert.2016.11.014","article-title":"Examining the efficacy of six published time-lapse imaging embryo selection algorithms to predict implantation to demonstrate the need for the development of specific, in-house morphokinetic selection algorithms","volume":"107","author":"A Barrie","year":"2017","journal-title":"Fertility and Sterility"},{"issue":"5","key":"pone.0262661.ref019","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1016\/j.fertnstert.2014.07.1246","article-title":"Comprehensive evaluation of contemporary assisted reproduction technology laboratory operations to determine staffing levels that promote patient safety and quality care","volume":"102","author":"M Alikani","year":"2014","journal-title":"Fertility and Sterility"},{"issue":"12","key":"pone.0262661.ref020","doi-asserted-by":"crossref","first-page":"3215","DOI":"10.1093\/humrep\/det366","article-title":"Inter- and intra-observer variability of time-lapse annotations","volume":"28","author":"L Sundvall","year":"2013","journal-title":"Human Reproduction"},{"issue":"3","key":"pone.0262661.ref021","first-page":"228","article-title":"Morphology vs morphokinetics: A retrospective comparison of interobserver and intra-observer agreement between embryologists on blastocysts with known implantation outcome","volume":"22","author":"E Adolfsson","year":"2018","journal-title":"Jornal Brasileiro de Reproducao Assistida"},{"issue":"2","key":"pone.0262661.ref022","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1093\/humrep\/dew330","article-title":"Inter-observer and intra-observer agreement between embryologists during selection of a single Day 5 embryo for transfer: A multicenter study","volume":"32","author":"A Storr","year":"2017","journal-title":"Human Reproduction"},{"issue":"4","key":"pone.0262661.ref023","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1016\/j.fertnstert.2019.12.004","article-title":"Consistency and objectivity of automated embryo assessments using deep neural networks","volume":"113","author":"CL Bormann","year":"2020","journal-title":"Fertility and sterility"},{"key":"pone.0262661.ref024","doi-asserted-by":"crossref","unstructured":"Giusti A, Corani G, Gambardella L, Magli C, Gianaroli L. Blastomere segmentation and 3D morphology measurements of early embryos from hoffman modulation contrast image stacks. In: 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010\u2014Proceedings. 2010. p. 1261\u20134.","DOI":"10.1109\/ISBI.2010.5490225"},{"issue":"Pt 2","key":"pone.0262661.ref025","first-page":"460","article-title":"Automated embryo stage classification in Time-Lapse Microscopy Video of Early Human Embryo Development","volume":"16","author":"Y Wang","year":"2013","journal-title":"Medical image computing and computer-assisted intervention: MICCAI. International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"pone.0262661.ref026","doi-asserted-by":"crossref","first-page":"103494","DOI":"10.1016\/j.compbiomed.2019.103494","article-title":"Automatic grading of human blastocysts from time-lapse imaging","volume":"115","author":"MF Kragh","year":"2019","journal-title":"Computers in Biology and Medicine"},{"key":"pone.0262661.ref027","article-title":"Robust Automated Assessment of Human Blastocyst Quality using Deep Learning","author":"P Khosravi","year":"2018","journal-title":"bioRxiv"},{"issue":"1","key":"pone.0262661.ref028","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1038\/s41746-019-0096-y","article-title":"Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization","volume":"2","author":"P Khosravi","year":"2019","journal-title":"npj Digital Medicine"},{"key":"pone.0262661.ref029","unstructured":"Ng NH, McAuley J, Lipton ZC, Gingold JA, Desai N. Predicting embryo morphokinetics in videos with late fusion nets & dynamic decoders. In: 6th International Conference on Learning Representations, ICLR 2018\u2014Workshop Track Proceedings. 2018."},{"key":"pone.0262661.ref030","doi-asserted-by":"crossref","unstructured":"Rocha JC, da Silva DLB, dos Santos JGC, Whyte LB, Hickman C, Lavery S, et al. Using artificial intelligence to improve the evaluation of human blastocyst morphology. In: IJCCI 2017\u2014Proceedings of the 9th International Joint Conference on Computational Intelligence. SciTePress; 2017. p. 354\u20139.","DOI":"10.5220\/0006515803540359"},{"issue":"24","key":"pone.0262661.ref031","doi-asserted-by":"crossref","first-page":"4139","DOI":"10.1039\/C9LC00721K","article-title":"Development and evaluation of inexpensive automated deep learning-based imaging systems for embryology","volume":"19","author":"MK Kanakasabapathy","year":"2019","journal-title":"Lab on a chip"},{"issue":"4394","key":"pone.0262661.ref032","first-page":"1","article-title":"Predicting pregnancy test results after embryo transfer by image feature extraction and analysis using machine learning","volume":"10","author":"A Chavez-Badiola","year":"2020","journal-title":"Scientific Reports"},{"issue":"01","key":"pone.0262661.ref033","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1142\/S2661318219500051","article-title":"Using Deep Learning with Large Dataset of Microscope Images to Develop an Automated Embryo Grading System","volume":"01","author":"T-J Chen","year":"2019","journal-title":"Fertility & Reproduction"},{"issue":"10","key":"pone.0262661.ref034","doi-asserted-by":"crossref","first-page":"2000080","DOI":"10.1002\/aisy.202000080","article-title":"Automated Evaluation of Human Embryo Blastulation and Implantation Potential using Deep-Learning","volume":"2","author":"Y Kan-Tor","year":"2020","journal-title":"Advanced Intelligent Systems"},{"issue":"6","key":"pone.0262661.ref035","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1093\/humrep\/dez064","article-title":"Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer","volume":"34","author":"D Tran","year":"2019","journal-title":"Human reproduction"},{"key":"pone.0262661.ref036","first-page":"1","article-title":"Good practice recommendations for the use of time-lapse technology","author":"S Apter","year":"2020","journal-title":"Human Reproduction Open"},{"key":"pone.0262661.ref037","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. Vols. 2017-Janua, Proceedings\u201430th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. 2017. p. 4724\u201333. http:\/\/arxiv.org\/abs\/1705.07750","DOI":"10.1109\/CVPR.2017.502"},{"issue":"8","key":"pone.0262661.ref038","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"pone.0262661.ref039","unstructured":"Kingma DP, Ba JL. Adam: A method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015\u2014Conference Track Proceedings. 2015. p. 1\u201315."},{"key":"pone.0262661.ref040","doi-asserted-by":"crossref","unstructured":"Smith LN, Topin N. Super-convergence: very fast training of neural networks using large learning rates. In 2019. p. 36.","DOI":"10.1117\/12.2520589"},{"key":"pone.0262661.ref041","unstructured":"Goodfellow IJ, Warde-Farley D, Mirza M, Courville A, Bengio Y. Maxout networks. In: 30th International Conference on Machine Learning, ICML 2013. 2013. p. 2356\u201364."},{"key":"pone.0262661.ref042","volume-title":"Statistics for Biology and Health","author":"EW Steyerberg","year":"2019","edition":"2"},{"key":"pone.0262661.ref043","doi-asserted-by":"crossref","unstructured":"DeVries T, Taylor GW. Improved Regularization of Convolutional Neural Networks with Cutout. 2017 Aug 15;","DOI":"10.1109\/ICME.2017.8019402"},{"issue":"2","key":"pone.0262661.ref044","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal Loss for Dense Object Detection","volume":"42","author":"TY Lin","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"pone.0262661.ref045","unstructured":"Kajh\u00f8j TQ. The language of embryology is evolving\u2014a guide to understanding time-lapse nomenclature. 2016. https:\/\/blog.vitrolife.com\/togetheralltheway\/a-guide-to-understanding-time-lapse-nomenclature"},{"issue":"12","key":"pone.0262661.ref046","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0166398","article-title":"Direct unequal cleavages: Embryo developmental competence, genetic constitution and clinical outcome","volume":"11","author":"Q Zhan","year":"2016","journal-title":"PLoS ONE"},{"key":"pone.0262661.ref047","unstructured":"Vitrolife. KIDScore D5 decision support tool. 2019. p. 1\u20132. https:\/\/www.vitrolife.com\/globalassets\/support-documents\/tech-notes\/technote_kidscore-d5.3_v3_v2.pdf"},{"issue":"1","key":"pone.0262661.ref048","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1186\/1471-2105-12-77","article-title":"pROC: An open-source package for R and S+ to analyze and compare ROC curves","volume":"12","author":"X Robin","year":"2011","journal-title":"BMC Bioinformatics"},{"issue":"5","key":"pone.0262661.ref049","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1016\/j.fertnstert.2020.09.159","article-title":"Evaluating predictive models in reproductive medicine","volume":"114","author":"CL Curchoe","year":"2020","journal-title":"Fertility and Sterility"},{"key":"pone.0262661.ref050","doi-asserted-by":"crossref","first-page":"1675","DOI":"10.1007\/s10815-021-02254-6","article-title":"Embryo selection with artificial intelligence: how to evaluate and compare methods?","volume":"38","author":"MF Kragh","year":"2021","journal-title":"Journal of Assisted Reproduction and Genetics"},{"key":"pone.0262661.ref051","first-page":"156","volume-title":"Reproductive BioMedicine Online","author":"K Kirkegaard","year":"2014"},{"issue":"4","key":"pone.0262661.ref052","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1093\/humupd\/dmz008","article-title":"The enigmatic morula: mechanisms of development, cell fate determination, self-correction and implications for ART","volume":"25","author":"G Coticchio","year":"2019","journal-title":"Human Reproduction Update"},{"issue":"2","key":"pone.0262661.ref053","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.fertnstert.2007.06.062","article-title":"Large blastocyst diameter, early blastulation, and low preovulatory serum progesterone are dominant predictors of clinical pregnancy in fresh autologous cycles","volume":"90","author":"BS Shapiro","year":"2008","journal-title":"Fertility and Sterility"},{"issue":"6","key":"pone.0262661.ref054","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1016\/S0015-0282(00)00518-5","article-title":"Blastocyst score affects implantation and pregnancy outcome: Towards a single blastocyst transfer","volume":"73","author":"DK Gardner","year":"2000","journal-title":"Fertility and Sterility"},{"issue":"12","key":"pone.0262661.ref055","doi-asserted-by":"crossref","first-page":"3289","DOI":"10.1093\/humrep\/der325","article-title":"Trophectoderm morphology: an important parameter for predicting live birth after single blastocyst transfer","volume":"26","author":"A Ahlstr\u00f6m","year":"2011","journal-title":"Human reproduction"},{"issue":"Suppl B","key":"pone.0262661.ref056","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/S0143-4004(03)00136-X","article-title":"Assessment of embryo viability: the ability to select a single embryo for transfer\u2014a review","volume":"24","author":"DK Gardner","year":"2003","journal-title":"Placenta"},{"key":"pone.0262661.ref057","first-page":"1","article-title":"Development of an artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF","author":"M VerMilyea","year":"2020","journal-title":"Human Reproduction"},{"issue":"2","key":"pone.0262661.ref058","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1093\/humrep\/dez263","article-title":"Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer","volume":"35","author":"A Chavez-Badiola","year":"2020","journal-title":"Human Reproduction"},{"key":"pone.0262661.ref059","article-title":"Predicting embryo viability based on self-supervised alignment of time-lapse videos","author":"MF Kragh","year":"2021","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pone.0262661.ref060","unstructured":"Caron M, Goyal P, Misra I, Bojanowski P, Mairal J, Joulin A. Unsupervised Learning of Visual Features by Contrasting Cluster Assignments. arXiv. 2020;(NeurIPS):1\u201323."},{"key":"pone.0262661.ref061","doi-asserted-by":"crossref","unstructured":"Arnab A, Dehghani M, Heigold G, Sun C, Lu\u010di\u0107 M, Schmid C. ViViT: A Video Vision Transformer. 2021; http:\/\/arxiv.org\/abs\/2103.15691","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"pone.0262661.ref062","unstructured":"Bertasius G, Wang H, Torresani L. Is Space-Time Attention All You Need for Video Understanding? 2021; http:\/\/arxiv.org\/abs\/2102.05095"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0262661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T16:07:14Z","timestamp":1726589234000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0262661"}},"subtitle":[],"editor":[{"given":"Marcelo F\u00e1bio Gouveia","family":"Nogueira","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,2,2]]},"references-count":62,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,2,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0262661","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,2]]}}}