{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:13:36Z","timestamp":1778346816841,"version":"3.51.4"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T00:00:00Z","timestamp":1726185600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T00:00:00Z","timestamp":1726185600000},"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":["SIViP"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s11760-024-03538-x","type":"journal-article","created":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T17:02:30Z","timestamp":1726246950000},"page":"9179-9189","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Generative AI-based style recommendation using fashion item detection and classification"],"prefix":"10.1007","volume":"18","author":[{"given":"Aleksandr","family":"Kalinin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akbar Anbar","family":"Jafari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Egils","family":"Avots","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cagri","family":"Ozcinar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gholamreza","family":"Anbarjafari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,13]]},"reference":[{"key":"3538_CR1","unstructured":"Reid, M., Savinov, N., Teplyashin, D., Lepikhin, D., Lillicrap, T., Alayrac, J.-b., Soricut, R., Lazaridou, A., Firat, O., Schrittwieser, J., et\u00a0al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530, (2024)"},{"key":"3538_CR2","unstructured":"Templeton, A., Conerly, T., Marcus, J., Lindsey, J., Bricken, T., Chen, B., Pearce, A., Citro, C., Ameisen, E., Jones, A., et\u00a0al.: Scaling monosemanticity: extracting interpretable features from claude 3 sonnet. Transform. Circuits Thread (2024)"},{"key":"3538_CR3","unstructured":"Global fashion retail market analysis. https:\/\/tinyurl.com\/4na63vma, accessed: 2024-05-27"},{"key":"3538_CR4","doi-asserted-by":"crossref","unstructured":"Martinsson, J., Mogren, O.: Semantic segmentation of fashion images using feature pyramid networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 0\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00382"},{"issue":"1","key":"3538_CR5","doi-asserted-by":"publisher","first-page":"571","DOI":"10.3390\/jtaer18010029","volume":"18","author":"E Y\u0131ld\u0131z","year":"2023","unstructured":"Y\u0131ld\u0131z, E., G\u00fcng\u00f6r \u015een, C., I\u015f\u0131k, E.E.: A hyper-personalized product recommendation system focused on customer segmentation: an application in the fashion retail industry. J. Theor. Appl. Electron. Commer. Res. 18(1), 571\u2013596 (2023)","journal-title":"J. Theor. Appl. Electron. Commer. Res."},{"key":"3538_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Q., Zhang, T., Nie, M., Wang, Z., Xu, S., Shi, W., Cao, Z.: Fashion-GPT: integrating LLMS with fashion retrieval system. In: Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications, pp. 69\u201378 (2023)","DOI":"10.1145\/3607827.3616844"},{"key":"3538_CR7","doi-asserted-by":"crossref","unstructured":"Tian, H., Cao, Y., Mok, P.: Detr-based layered clothing segmentation and fine-grained attribute recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3534\u20133538 (2023)","DOI":"10.1109\/CVPRW59228.2023.00360"},{"issue":"10","key":"3538_CR8","doi-asserted-by":"publisher","first-page":"308","DOI":"10.3390\/info10100308","volume":"10","author":"HS Arslan","year":"2019","unstructured":"Arslan, H.S., Sirts, K., Fishel, M., Anbarjafari, G.: Multimodal sequential fashion attribute prediction. Information 10(10), 308 (2019)","journal-title":"Information"},{"key":"3538_CR9","doi-asserted-by":"publisher","first-page":"25829","DOI":"10.1007\/s11042-019-7739-5","volume":"78","author":"E Avots","year":"2019","unstructured":"Avots, E., Madadi, M., Escalera, S., Gonzalez, J., Baro, X., P\u00e4llin, P., Anbarjafari, G.: From 2d to 3d geodesic-based garment matching. Multimed. Tools Appl. 78, 25829\u201325853 (2019)","journal-title":"Multimed. Tools Appl."},{"key":"3538_CR10","doi-asserted-by":"crossref","unstructured":"Cychnerski, J., Brzeski, A., Boguszewski, A., Marmolowski, M., Trojanowicz, M.: Clothes detection and classification using convolutional neural networks. In: 22nd IEEE International Conference on Emerging Technologies and Factory Automation. IEEE , vol. 2017, pp. 1\u20138 (2017)","DOI":"10.1109\/ETFA.2017.8247638"},{"key":"3538_CR11","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics yolov8. [Online]. Available: https:\/\/github.com\/ultralytics\/ultralytics (2023)"},{"issue":"1","key":"3538_CR12","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1109\/TMM.2013.2285526","volume":"16","author":"S Liu","year":"2014","unstructured":"Liu, S., Feng, J., Domokos, C., Xu, H., Huang, J., Hu, Z., Yan, S.: Fashion parsing with weak color-category labels. IEEE Trans. Multimed. 16(1), 253\u2013265 (2014)","journal-title":"IEEE Trans. Multimed."},{"key":"3538_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: Deepfashion: powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1096\u20131104 (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"3538_CR14","doi-asserted-by":"crossref","unstructured":"Zou, X., Kong, X., Wong, W., Wang, C., Liu, Y., Cao, Y.: Fashionai: a hierarchical dataset for fashion understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 0\u20130 (2019)","DOI":"10.1109\/CVPRW.2019.00039"},{"key":"3538_CR15","doi-asserted-by":"crossref","unstructured":"Jia, M., Shi, M., Sirotenko, M., Cui, Y., Cardie, C., Hariharan, B., Adam, H., Belongie, S.: Fashionpedia: ontology, segmentation, and an attribute localization dataset. In: Computer Vision-ECCV: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16. Springer, vol. 2020, pp. 316\u2013332 (2020)","DOI":"10.1007\/978-3-030-58452-8_19"},{"key":"3538_CR16","doi-asserted-by":"crossref","unstructured":"Zheng, S., Yang, F., Kiapour, M.H., Piramuthu, R.: Modanet: a large-scale street fashion dataset with polygon annotations. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1670\u20131678 (2018)","DOI":"10.1145\/3240508.3240652"},{"key":"3538_CR17","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zhang, R., Wang, X., Tang, X., Luo, P.: Deepfashion2: a versatile benchmark for detection, pose estimation, segmentation and re-identification of clothing images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5337\u20135345 (2019)","DOI":"10.1109\/CVPR.2019.00548"},{"key":"3538_CR18","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"11","key":"3538_CR19","first-page":"125","volume":"12","author":"MC Andrea","year":"2023","unstructured":"Andrea, M.C., Noh, M.J., Lee, C.K.: Detection of traditional costumes: a computer vision approach. Smart Media J. 12(11), 125\u2013133 (2023)","journal-title":"Smart Media J."},{"key":"3538_CR20","doi-asserted-by":"crossref","unstructured":"Ji, S., Han, R., Wei, J., Wang, R.: Clothing image detection and recognition based on faster R-CNN. In: IOP Conference Series: Materials Science and Engineering, vol. 790, No.\u00a01, IOP Publishing, p. 012141 (2020)","DOI":"10.1088\/1757-899X\/790\/1\/012141"},{"key":"3538_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Q., Han, X., Lu, T., Liu, G.: Clothing image retrieval based on parts detection and segmentation. In: Proceedings of the 2021 3rd International Conference on Image Processing and Machine Vision, pp. 53\u201359 (2021)","DOI":"10.1145\/3469951.3469961"},{"key":"3538_CR22","unstructured":"Hendrycks, D., Gimpel, K.: Bridging nonlinearities and stochastic regularizers with gaussian error linear units. CoRR, vol. abs\/1606.08415. arXiv preprint arXiv:1606.08415, (2016)"},{"key":"3538_CR23","doi-asserted-by":"crossref","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. CoRR, vol. arXiv preprint arXiv:1702.03118, (2017)","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"3538_CR24","doi-asserted-by":"crossref","unstructured":"Rezatofighi, S.H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I.D., Savarese, S.: Generalized intersection over union: a metric and A loss for bounding box regression. CoRR, vol. arXiv preprint arXiv:1902.09630, (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"3538_CR25","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., Wang, W., Wu, L., Chen, S., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv. Neural Inf. Proces. Syst. 33, 21002\u201321012 (2020)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"3538_CR26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3538_CR27","unstructured":"Arslan, H.S., Fishel, M., Anbarjafari, G.: Doubly attentive transformer machine translation. arXiv preprint arXiv:1807.11605, (2018)"},{"key":"3538_CR28","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774, (2023)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03538-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03538-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03538-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T02:25:00Z","timestamp":1730687100000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03538-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,13]]},"references-count":28,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["3538"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03538-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4517638\/v1","asserted-by":"object"}]},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,13]]},"assertion":[{"value":"2 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2024","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 declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}