{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T01:30:03Z","timestamp":1784165403640,"version":"3.55.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586003","type":"print"},{"value":"9783030586010","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58601-0_1","type":"book-chapter","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T19:02:52Z","timestamp":1606503772000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards"],"prefix":"10.1007","author":[{"given":"Xuewen","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingru","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Hao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianchao","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongliang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,28]]},"reference":[{"key":"1_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Aneja, J., Deshpande, A., Schwing, A.G.: Convolutional image captioning. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00583"},{"key":"1_CR4","unstructured":"Chen, X., et al.: Microsoft COCO captions: Data collection and evaluation server (2015)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Cucurull, G., Taslakian, P., Vazquez, D.: Context-aware visual compatibility prediction. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2019)","DOI":"10.1109\/CVPR.2019.01290"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: Language specific translation evaluation for any target language. In: Proceedings of the 9th Workshop on Statistical Machine Translation (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"1_CR7","unstructured":"Gabale, V., Prabhu Subramanian, A.: How to Extract Fashion Trends from Social Media? A Robust Object Detector With Support For Unsupervised Learning. arXiv e-prints (2018)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Gao, J., Wang, S., Wang, S., Ma, S., Gao, W.: Self-critical n-step training for image captioning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00646"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zhang, R., Wu, L., Wang, X., Tang, X., Luo, P.: A versatile benchmark for detection, pose estimation, segmentation and re-identification of clothing images. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00548"},{"key":"1_CR10","unstructured":"Guo, X., Wu, H., Gao, Y., Rennie, S., Feris, R.: The fashion IQ dataset: Retrieving images by combining side information and relative natural language feedback. arXiv preprint arXiv:1905.12794 (2019)"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Jiang, Y.G., Davis, L.S.: Learning fashion compatibility with bidirectional LSTMs. In: ACM Multimedia (2017)","DOI":"10.1145\/3123266.3123394"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR14","unstructured":"He, Y., Yang, L., Chen, L.: Real-time fashion-guided clothing semantic parsing: a lightweight multi-scale inception neural network and benchmark. In: AAAI Workshops (2017)"},{"key":"1_CR15","unstructured":"Herdade, S., Kappeler, A., Boakye, K., Soares, J.: Image captioning: transforming objects into words. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"issue":"8","key":"1_CR16","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_CR17","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: DenseCap: fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"1_CR18","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2017","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 39, 664\u2013676 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014)","DOI":"10.3115\/v1\/D14-1181"},{"key":"1_CR20","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization (2015)"},{"key":"1_CR21","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123, 32\u201373 (2017). https:\/\/doi.org\/10.1007\/s11263-016-0981-7","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR22","unstructured":"Lin, C.Y.: ROUGE: A package for automatic evaluation of summaries. In: Text Summarization Branches Out (2004)"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Hi, magic closet, tell me what to wear! In: Proceedings of the 20th ACM International Conference on Multimedia (2012)","DOI":"10.1145\/2393347.2396470"},{"key":"1_CR24","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 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Lu, Z., Hu, Y., Jiang, Y., Chen, Y., Zeng, B.: Learning binary code for personalized fashion recommendation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2019)","DOI":"10.1109\/CVPR.2019.01081"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Ma, C.Y., Kadav, A., Melvin, I., Kira, Z., Alregib, G., Graf, H.: Attend and interact: Higher-order object interactions for video understanding (2017)","DOI":"10.1109\/CVPR.2018.00710"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Qin, Y., Du, J., Zhang, Y., Lu, H.: Look back and predict forward in image captioning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00856"},{"key":"1_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Ren, Z., Wang, X., Zhang, N., Lv, X., Li, L.J.: Deep reinforcement learning-based image captioning with embedding reward (2017)","DOI":"10.1109\/CVPR.2017.128"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"1_CR32","unstructured":"Socher, R., Bauer, J., Manning, C.D., Ng, A.Y.: Parsing with compositional vector grammars. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2013)"},{"key":"1_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-01270-0_24","volume-title":"Computer Vision \u2013 ECCV 2018","author":"MI Vasileva","year":"2018","unstructured":"Vasileva, M.I., Plummer, B.A., Dusad, K., Rajpal, S., Kumar, R., Forsyth, D.: Learning type-aware embeddings for fashion compatibility. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 405\u2013421. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_24"},{"key":"1_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Wang, W., Xu, Y., Shen, J., Zhu, S.C.: Attentive fashion grammar network for fashion landmark detection and clothing category classification. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00449"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Z., Gu, Y., Zhang, Y., Zhou, J., Gu, X.: Clothing retrieval with visual attention model. In: 2017 IEEE Visual Communications and Image Processing (VCIP), pp. 1\u20134 (2017)","DOI":"10.1109\/VCIP.2017.8305144"},{"key":"1_CR38","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992). https:\/\/doi.org\/10.1007\/BF00992696","journal-title":"Mach. Learn."},{"key":"1_CR39","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: Proceedings of the 32nd International Conference on Machine Learning (2015)"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Yu, W., Zhang, H., He, X., Chen, X., Xiong, L., Qin, Z.: Aesthetic-based clothing recommendation. In: Proceedings of the 2018 World Wide Web Conference (2018)","DOI":"10.1145\/3178876.3186146"},{"key":"1_CR41","unstructured":"Zhang, L., et al.: Actor-critic sequence training for image captioning. In: NIPS workshop (2017)"},{"key":"1_CR42","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: ACM Multimedia (2018)","DOI":"10.1145\/3240508.3240652"},{"key":"1_CR43","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: CVPRW (2019)","DOI":"10.1109\/CVPRW.2019.00039"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58601-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:02:55Z","timestamp":1732665775000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58601-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586003","9783030586010"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58601-0_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"28 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 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)"}}]}}