{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T03:41:22Z","timestamp":1781062882949,"version":"3.54.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:00:00Z","timestamp":1665187200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["951908"],"award-info":[{"award-number":["951908"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Estimating the preferences of consumers is of utmost importance for the fashion industry as appropriately leveraging this information can be beneficial in terms of profit. Trend detection in fashion is a challenging task due to the fast pace of change in the fashion industry. Moreover, forecasting the visual popularity of new garment designs is even more demanding due to lack of historical data. To this end, we propose MuQAR, a Multimodal Quasi-AutoRegressive deep learning architecture that combines two modules: (1) a multimodal multilayer perceptron processing categorical, visual and textual features of the product and (2) a Quasi-AutoRegressive neural network modelling the \u201ctarget\u201d time series of the product\u2019s attributes along with the \u201cexogenous\u201d time series of all other attributes. We utilize computer vision, image classification and image captioning, for automatically extracting visual features and textual descriptions from the images of new products. Product design in fashion is initially expressed visually and these features represent the products\u2019 unique characteristics without interfering with the creative process of its designers by requiring additional inputs (e.g. manually written texts). We employ the product\u2019s target attributes time series as a proxy of temporal popularity patterns, mitigating the lack of historical data, while exogenous time series help capture trends among interrelated attributes. We perform an extensive ablation analysis on two large-scale image fashion datasets, Mallzee-P and SHIFT15m to assess the adequacy of MuQAR and also use the Amazon Reviews: Home and Kitchen dataset to assess generalization to other domains. A comparative study on the VISUELLE dataset shows that MuQAR is capable of competing and surpassing the domain\u2019s current state of the art by 4.65% and 4.8% in terms of WAPE and MAE, respectively.<\/jats:p>","DOI":"10.1007\/s13735-022-00262-5","type":"journal-article","created":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T14:03:29Z","timestamp":1665237809000},"page":"717-729","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Multimodal Quasi-AutoRegression: forecasting the visual popularity of new fashion products"],"prefix":"10.1007","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1424-2647","authenticated-orcid":false,"given":"Stefanos-Iordanis","family":"Papadopoulos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christos","family":"Koutlis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Symeon","family":"Papadopoulos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioannis","family":"Kompatsiaris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,8]]},"reference":[{"key":"262_CR1","doi-asserted-by":"crossref","unstructured":"Al-Halah Z, Grauman K (2020) From Paris to Berlin: discovering fashion style influences around the world. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10136\u201310145","DOI":"10.1109\/CVPR42600.2020.01015"},{"key":"262_CR2","doi-asserted-by":"crossref","unstructured":"Al-Halah Z, Stiefelhagen R, Grauman K (2017) Fashion forward: forecasting visual style in fashion. In: Proceedings of the IEEE international conference on computer vision, pp 388\u2013397","DOI":"10.1109\/ICCV.2017.50"},{"key":"262_CR3","doi-asserted-by":"crossref","unstructured":"Billings SA (2013) Nonlinear system identification: NARMAX methods in the time, frequency, and spatio-temporal domains. Wiley, Hoboken, NJ","DOI":"10.1002\/9781118535561"},{"key":"262_CR4","doi-asserted-by":"publisher","unstructured":"Chang AA, Ramadhan JF, Adnan ZKS, et al. (2021) Fashion trend forecasting using machine learning techniques: a review. In: Proceedings of the computational methods in systems and software, Springer, pp 34\u201344. https:\/\/doi.org\/10.1007\/978-3-030-90321-3_5","DOI":"10.1007\/978-3-030-90321-3_5"},{"key":"262_CR5","unstructured":"Chang YY, Sun FY, Wu YH, et\u00a0al (2018) A memory-network based solution for multivariate time-series forecasting. Preprint arXiv:1809.02105"},{"issue":"4","key":"262_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447239","volume":"54","author":"WH Cheng","year":"2021","unstructured":"Cheng WH, Song S, Chen CY et al (2021) Fashion meets computer vision: a survey. ACM Comput Surveys (CSUR) 54(4):1\u201341. https:\/\/doi.org\/10.1145\/3447239","journal-title":"ACM Comput Surveys (CSUR)"},{"issue":"2","key":"262_CR7","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.2991\/ijcis.d.191122.002","volume":"12","author":"G Craparotta","year":"2019","unstructured":"Craparotta G, Thomassey S, Biolatti A (2019) A Siamese neural network application for sales forecasting of new fashion products using heterogeneous data. Int J Comput Intell Syst 12(2):1537\u20131546. https:\/\/doi.org\/10.2991\/ijcis.d.191122.002","journal-title":"Int J Comput Intell Syst"},{"key":"262_CR8","doi-asserted-by":"publisher","unstructured":"Ekambaram V, Manglik K, Mukherjee S, et al. (2020) Attention based multi-modal new product sales time-series forecasting. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp 3110\u20133118. https:\/\/doi.org\/10.1145\/3394486.3403362","DOI":"10.1145\/3394486.3403362"},{"key":"262_CR9","unstructured":"Graves A (2013) Generating sequences with recurrent neural networks. Preprint arXiv:1308.0850"},{"issue":"8","key":"262_CR10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"262_CR11","doi-asserted-by":"crossref","unstructured":"Hwang CL, Yoon K (1981) Methods for multiple attribute decision making. In: Multiple attribute decision making. Springer, pp 58\u2013191","DOI":"10.1007\/978-3-642-48318-9_3"},{"key":"262_CR12","doi-asserted-by":"publisher","unstructured":"Kimura M, Nakamura T, Saito Y (2021) Shift15m: multiobjective large-scale fashion dataset with distributional shifts. Preprint arXiv:2108.12992https:\/\/doi.org\/10.48550\/arXiv.2108.12992","DOI":"10.48550\/arXiv.2108.12992"},{"issue":"106","key":"262_CR13","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1016\/j.asoc.2020.106685","volume":"96","author":"C Koutlis","year":"2020","unstructured":"Koutlis C, Papadopoulos S, Schinas M et al (2020) Lavarnet: neural network modeling of causal variable relationships for multivariate time series forecasting. Appl Soft Comput 96(106):685. https:\/\/doi.org\/10.1016\/j.asoc.2020.106685","journal-title":"Appl Soft Comput"},{"key":"262_CR14","doi-asserted-by":"publisher","unstructured":"Lai G, Chang WC, Yang Y, et al. (2018) Modeling long-and short-term temporal patterns with deep neural networks. In: The 41st international ACM SIGIR conference on research & development in information retrieval, pp 95\u2013104. https:\/\/doi.org\/10.1145\/3209978.3210006","DOI":"10.1145\/3209978.3210006"},{"issue":"2194","key":"262_CR15","doi-asserted-by":"publisher","first-page":"20200209","DOI":"10.1098\/rsta.2020.0209","volume":"379","author":"B Lim","year":"2021","unstructured":"Lim B, Zohren S (2021) Time-series forecasting with deep learning: a survey. Philos Trans R Soc A 379(2194):20200209. https:\/\/doi.org\/10.1098\/rsta.2020.0209","journal-title":"Philos Trans R Soc A"},{"key":"262_CR16","doi-asserted-by":"publisher","unstructured":"Lo L, Liu CL, Lin RA, et\u00a0al (2019) Dressing for attention: outfit based fashion popularity prediction. In: 2019 IEEE international conference on image processing (ICIP), IEEE, pp 3222\u20133226. https:\/\/doi.org\/10.1109\/ICIP.2019.8803461","DOI":"10.1109\/ICIP.2019.8803461"},{"key":"262_CR17","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.dss.2018.08.010","volume":"114","author":"AL Loureiro","year":"2018","unstructured":"Loureiro AL, Migu\u00e9is VL, da Silva LF (2018) Exploring the use of deep neural networks for sales forecasting in fashion retail. Decisi Support Syst 114:81\u201393. https:\/\/doi.org\/10.1016\/j.dss.2018.08.010","journal-title":"Decisi Support Syst"},{"key":"262_CR18","doi-asserted-by":"publisher","unstructured":"Ma Y, Ding Y, Yang X, et\u00a0al (2020) Knowledge enhanced neural fashion trend forecasting. In: Proceedings of the 2020 international conference on multimedia retrieval, pp 82\u201390. https:\/\/doi.org\/10.1145\/3372278.3390677","DOI":"10.1145\/3372278.3390677"},{"key":"262_CR19","doi-asserted-by":"crossref","unstructured":"Mall U, Matzen K, Hariharan B, et al. (2019) Geostyle: discovering fashion trends and events. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 411\u2013420","DOI":"10.1109\/ICCV.2019.00050"},{"key":"262_CR20","doi-asserted-by":"publisher","unstructured":"McAuley J, Targett C, Shi Q, et al. (2015) Image-based recommendations on styles and substitutes. In: Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval, pp 43\u201352. https:\/\/doi.org\/10.1145\/2766462.2767755","DOI":"10.1145\/2766462.2767755"},{"issue":"4","key":"262_CR21","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1038\/s43017-020-0039-9","volume":"1","author":"K Niinim\u00e4ki","year":"2020","unstructured":"Niinim\u00e4ki K, Peters G, Dahlbo H et al (2020) The environmental price of fast fashion. Nat Rev Earth Environ 1(4):189\u2013200","journal-title":"Nat Rev Earth Environ"},{"key":"262_CR22","doi-asserted-by":"publisher","unstructured":"Papadopoulos SI, Koutlis C, Sudheer M, et al. (2022) Attentive hierarchical label sharing for enhanced garment and attribute classification of fashion imagery. In: Recommender systems in fashion and retail. Springer, pp 95\u2013115. https:\/\/doi.org\/10.1007\/978-3-030-94016-4_7","DOI":"10.1007\/978-3-030-94016-4_7"},{"key":"262_CR23","doi-asserted-by":"crossref","unstructured":"Qin Y, Song D, Chen H, et\u00a0al (2017) A dual-stage attention-based recurrent neural network for time series prediction. Preprint arXiv:1704.02971","DOI":"10.24963\/ijcai.2017\/366"},{"key":"262_CR24","unstructured":"Singh PK, Gupta Y, Jha N, et al. (2019) Fashion retail: forecasting demand for new items. Preprint arXiv:1907.01960"},{"key":"262_CR25","doi-asserted-by":"publisher","unstructured":"Skenderi G, Joppi C, Denitto M, et\u00a0al (2021) Well googled is half done: multimodal forecasting of new fashion product sales with image-based google trends. Preprint arXiv:2109.09824https:\/\/doi.org\/10.48550\/arXiv.2109.09824","DOI":"10.48550\/arXiv.2109.09824"},{"key":"262_CR26","doi-asserted-by":"publisher","unstructured":"Smith LN (2017) Cyclical learning rates for training neural networks. In: 2017 IEEE winter conference on applications of computer vision (WACV), IEEE, pp 464\u2013472. https:\/\/doi.org\/10.1109\/WACV.2017.58","DOI":"10.1109\/WACV.2017.58"},{"key":"262_CR27","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"262_CR28","unstructured":"Wang P, Yang A, Men R, et al. (2022) Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. Preprint arXiv:2202.03052"},{"key":"262_CR29","unstructured":"Xingjian S, Chen Z, Wang H, et al. (2015) Convolutional lstm network: a machine learning approach for precipitation nowcasting. In: Advances in neural information processing systems, pp 802\u2013810"},{"key":"262_CR30","doi-asserted-by":"publisher","unstructured":"Zhao B, Lu H, Chen S, et al. (2017) Convolutional neural networks for time series classification. J Syst Eng Electron 28(1):162\u2013169. https:\/\/doi.org\/10.21629\/JSEE.2017.01.18","DOI":"10.21629\/JSEE.2017.01.18"},{"key":"262_CR31","doi-asserted-by":"crossref","unstructured":"Zhou H, Zhang S, Peng J, et al. (2021) Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of AAAI","DOI":"10.1609\/aaai.v35i12.17325"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-022-00262-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13735-022-00262-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-022-00262-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T14:23:52Z","timestamp":1671287032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13735-022-00262-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,8]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["262"],"URL":"https:\/\/doi.org\/10.1007\/s13735-022-00262-5","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,8]]},"assertion":[{"value":"4 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2022","order":4,"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 conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}