{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:31:29Z","timestamp":1742999489596,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031424472"},{"type":"electronic","value":"9783031424489"}],"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\/978-3-031-42448-9_1","type":"book-chapter","created":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T23:02:21Z","timestamp":1694386941000},"page":"3-14","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Inception Models for\u00a0Fashion Image Captioning: An Extensive Study on\u00a0Multiple Datasets"],"prefix":"10.1007","author":[{"given":"Mirko","family":"Del Moro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serban Cristian","family":"Tudosie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Vannoni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9711-7042","authenticated-orcid":false,"given":"Andrea","family":"Galassi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1697-8586","authenticated-orcid":false,"given":"Federico","family":"Ruggeri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,11]]},"reference":[{"key":"1_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)"},{"key":"1_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"issue":"4","key":"1_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447239","volume":"54","author":"WH Cheng","year":"2021","unstructured":"Cheng, W.H., Song, S., Chen, C.Y., Hidayati, S.C., Liu, J.: Fashion meets computer vision: a survey. ACM Comput. Surv. 54(4), 1\u201341 (2021)","journal-title":"ACM Comput. Surv."},{"key":"1_CR4","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: ICML, pp. 1931\u20131942. PMLR (2021)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: Encoder-decoder approaches. In: SSST@EMNLP, pp. 103\u2013111 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Cucchiara, R.: Show, control and tell: a framework for generating controllable and grounded captions. In: CVPR, pp. 8307\u20138316 (2019)","DOI":"10.1109\/CVPR.2019.00850"},{"key":"1_CR7","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (1), pp. 4171\u20134186 (2019)"},{"key":"1_CR8","doi-asserted-by":"publisher","first-page":"8410","DOI":"10.1109\/TIP.2021.3115658","volume":"30","author":"J Dong","year":"2021","unstructured":"Dong, J., et al.: Fine-grained fashion similarity prediction by attribute-specific embedding learning. IEEE Trans. Image Process. 30, 8410\u20138425 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"1_CR9","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.ins.2020.05.094","volume":"540","author":"M Dong","year":"2020","unstructured":"Dong, M., Zeng, X., Koehl, L., Zhang, J.: An interactive knowledge-based recommender system for fashion product design in the big data environment. Inf. Sci. 540, 469\u2013488 (2020)","journal-title":"Inf. Sci."},{"issue":"10","key":"1_CR10","doi-asserted-by":"publisher","first-page":"4291","DOI":"10.1109\/TNNLS.2020.3019893","volume":"32","author":"A Galassi","year":"2021","unstructured":"Galassi, A., Lippi, M., Torroni, P.: Attention in natural language processing. IEEE Trans. Neural Netw. Learn. Syst. 32(10), 4291\u20134308 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1_CR11","unstructured":"Goyal, A., Lamb, A., Zhang, Y., Zhang, S., Courville, A.C., Bengio, Y.: Professor forcing: a new algorithm for training recurrent networks. In: NIPS, pp. 4601\u20134609 (2016)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Hacheme, G., Sayouti, N.: Neural fashion image captioning : accounting for data diversity. CoRR abs\/2106.12154 (2021)","DOI":"10.31730\/osf.io\/hwtpq"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"1_CR14","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.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Hu, X., et al.: Scaling up vision-language pre-training for image captioning. CoRR abs\/2111.12233 (2021)","DOI":"10.1109\/CVPR52688.2022.01745"},{"issue":"2","key":"1_CR16","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/MMUL.2014.25","volume":"21","author":"S Liu","year":"2014","unstructured":"Liu, S., Liu, L., Yan, S.: Fashion analysis: current techniques and future directions. IEEE Multimedia 21(2), 72\u201379 (2014)","journal-title":"IEEE Multimedia"},{"key":"1_CR17","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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: Bleu: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Popovic, M.: chrF: character n-gram F-score for automatic MT evaluation. In: WMT@EMNLP, pp. 392\u2013395 (2015)","DOI":"10.18653\/v1\/W15-3049"},{"key":"1_CR21","unstructured":"Rostamzadeh, N., et al.: Fashion-gen: the generative fashion dataset and challenge. CoRR (2018)"},{"issue":"3","key":"1_CR22","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1109\/MMUL.2018.2875860","volume":"25","author":"S Song","year":"2018","unstructured":"Song, S., Mei, T.: When multimedia meets fashion. IEEE Multimedia 25(3), 102\u2013108 (2018)","journal-title":"IEEE Multimedia"},{"issue":"1","key":"1_CR23","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1109\/TPAMI.2022.3148210","volume":"45","author":"M Stefanini","year":"2023","unstructured":"Stefanini, M., Cornia, M., Baraldi, L., Cascianelli, S., Fiameni, G., Cucchiara, R.: From show to tell: a survey on deep learning-based image captioning. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 539\u2013559 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"1_CR24","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1080\/17543266.2021.1958926","volume":"15","author":"E Sumarliah","year":"2022","unstructured":"Sumarliah, E., Usmanova, K., Mousa, K., Indriya, I.: E-commerce in the fashion business: the roles of the Covid-19 situational factors, hedonic and utilitarian motives on consumers\u2019 intention to purchase online. Int. J. Fashion Des. Technol. Educ. 15(2), 167\u2013177 (2022)","journal-title":"Int. J. Fashion Des. Technol. Educ."},{"key":"1_CR25","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS, pp. 3104\u20133112 (2014)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Wiegreffe, S., Pinter, Y.: Attention is not not explanation. In: EMNLP\/IJCNLP (1), pp. 11\u201320. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/D19-1002"},{"key":"1_CR29","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, vol. 37, pp. 2048\u20132057 (2015)"},{"key":"1_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58601-0_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Yang","year":"2020","unstructured":"Yang, X., et al.: Fashion captioning: towards generating accurate descriptions with semantic rewards. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 1\u201317. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_1"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Yin, R., Li, K., Lu, J., Zhang, G.: Enhancing fashion recommendation with visual compatibility relationship. In: WWW, pp. 3434\u20133440, New York, NY, USA (2019)","DOI":"10.1145\/3308558.3313739"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yao, L., Sun, A., Tay, Y.: Deep learning based recommender system: a survey and new perspectives. ACM Comput. Surv. 52(1), 5:1\u20135:38 (2019)","DOI":"10.1145\/3285029"},{"key":"1_CR33","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with BERT. In: ICLR (2020)"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, S., Fidler, S., Urtasun, R., Lin, D., Loy, C.C.: Be your own prada: Fashion synthesis with structural coherence. In: ICCV, pp. 1689\u20131697 (2017)","DOI":"10.1109\/ICCV.2017.186"}],"container-title":["Lecture Notes in Computer Science","Experimental IR Meets Multilinguality, Multimodality, and Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-42448-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:21:40Z","timestamp":1710260500000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-42448-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031424472","9783031424489"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-42448-9_1","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":"11 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CLEF","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Cross-Language Evaluation Forum for European Languages","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"clef2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/clef2023.clef-initiative.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"35","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":"10","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":"1","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":"29% - 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":"2","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","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":"7 Best of 2022 Labs + 13 Lab Overviews","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)"}}]}}