{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:33:49Z","timestamp":1743104029315,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723438"},{"type":"electronic","value":"9783031723445"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72344-5_21","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T14:03:01Z","timestamp":1726495381000},"page":"308-323","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FashionGPT: A Large Vision-Language Model for\u00a0Enhancing Fashion Understanding"],"prefix":"10.1007","author":[{"given":"Duanxiao","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dehong","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongshen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)","key":"21_CR1"},{"key":"21_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12 m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: CVPR (2021)","key":"21_CR3","DOI":"10.1109\/CVPR46437.2021.00356"},{"doi-asserted-by":"crossref","unstructured":"Chen, J., Guo, H., Yi, K., Li, B., Elhoseiny, M.: VisualGPT: data-efficient adaptation of pretrained language models for image captioning. In: CVPR, pp. 18030\u201318040 (2022)","key":"21_CR4","DOI":"10.1109\/CVPR52688.2022.01750"},{"unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal llm\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)","key":"21_CR5"},{"unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)","key":"21_CR6"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)","key":"21_CR7"},{"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: CVPR, pp. 5337\u20135345 (2019)","key":"21_CR8","DOI":"10.1109\/CVPR.2019.00548"},{"issue":"5","key":"21_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102276","volume":"57","author":"X Gu","year":"2020","unstructured":"Gu, X., Gao, F., Tan, M., Peng, P.: Fashion analysis and understanding with artificial intelligence. Inform. Process. Manage. 57(5), 102276 (2020)","journal-title":"Inform. Process. Manage."},{"doi-asserted-by":"crossref","unstructured":"Hadi\u00a0Kiapour, M., Han, X., Lazebnik, S., Berg, A.C., Berg, T.L.: Where to buy it: matching street clothing photos in online shops. In: ICCV, pp. 3343\u20133351 (2015)","key":"21_CR10","DOI":"10.1109\/ICCV.2015.382"},{"doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPscore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","key":"21_CR11","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"unstructured":"Hoffmann, J., et\u00a0al.: Training compute-optimal large language models. arXiv preprint arXiv:2203.15556 (2022)","key":"21_CR12"},{"doi-asserted-by":"crossref","unstructured":"Huang, J., Feris, R.S., Chen, Q., Yan, S.: Cross-domain image retrieval with a dual attribute-aware ranking network. In: ICCV, pp. 1062\u20131070 (2015)","key":"21_CR13","DOI":"10.1109\/ICCV.2015.127"},{"doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","key":"21_CR14","DOI":"10.1109\/ICCV51070.2023.00371"},{"unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)","key":"21_CR15"},{"doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","key":"21_CR16","DOI":"10.1109\/CVPR52733.2024.02484"},{"unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)","key":"21_CR17"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation (2020)","key":"21_CR18","DOI":"10.1162\/tacl_a_00343"},{"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, pp. 1096\u20131104 (2016)","key":"21_CR19","DOI":"10.1109\/CVPR.2016.124"},{"doi-asserted-by":"crossref","unstructured":"Ma, Y., Jia, J., Zhou, S., Fu, J., Liu, Y., Tong, Z.: Towards better understanding the clothing fashion styles: a multimodal deep learning approach. In: AAAI (2017)","key":"21_CR20","DOI":"10.1609\/aaai.v31i1.10509"},{"unstructured":"OpenAI: Introducing ChatGPT (2022). https:\/\/openai.com\/blog\/chatgpt","key":"21_CR21"},{"unstructured":"OpenAI: Gpt-4 technical report (2023)","key":"21_CR22"},{"unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2Text: describing images using 1 million captioned photographs. In: NeurIPS (2011)","key":"21_CR23"},{"unstructured":"Peng, Z., et al.: Kosmos-2: Grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)","key":"21_CR24"},{"unstructured":"Rostamzadeh, N., et al.: Fashion-Gen: the generative fashion dataset and challenge. arXiv preprint arXiv:1806.08317 (2018)","key":"21_CR25"},{"unstructured":"Schuhmann, C., K\u00f6pf, A., Vencu, R., Coombes, T., Beaumont, R.: LAION Coco: 600 m synthetic captions from laion2B-en. https:\/\/laion.ai\/blog\/laion-coco\/ (2022)","key":"21_CR26"},{"doi-asserted-by":"crossref","unstructured":"Shankar, S., Garg, V.K., Cipolla, R.: Deep-carving: Discovering visual attributes by carving deep neural nets. In: CVPR, pp. 3403\u20133412 (2015)","key":"21_CR27","DOI":"10.1109\/CVPR.2015.7298962"},{"unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: EVA-CLIP: improved training techniques for clip at scale (2023)","key":"21_CR28"},{"issue":"4","key":"21_CR29","doi-asserted-by":"publisher","DOI":"10.4108\/eetinis.v10i4.4315","volume":"10","author":"D Swain","year":"2023","unstructured":"Swain, D., Pandya, K., Sanghvi, J., Manchala, Y.: An intelligent fashion object classification using CNN. EAI Endorsed Trans. Ind. Netw. Intell. Syst. 10(4), e2 (2023)","journal-title":"EAI Endorsed Trans. Ind. Netw. Intell. Syst."},{"unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)","key":"21_CR30"},{"unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)","key":"21_CR31"},{"doi-asserted-by":"crossref","unstructured":"Zhao, B., Feng, J., Wu, X., Yan, S.: Memory-augmented attribute manipulation networks for interactive fashion search. In: CVPR, pp. 1520\u20131528 (2017)","key":"21_CR32","DOI":"10.1109\/CVPR.2017.652"},{"unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)","key":"21_CR33"},{"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: CVPR Workshops (2019)","key":"21_CR34","DOI":"10.1109\/CVPRW.2019.00039"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72344-5_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T06:23:13Z","timestamp":1732774993000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72344-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723438","9783031723445"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72344-5_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}