{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:14:28Z","timestamp":1763644468820,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730092"},{"type":"electronic","value":"9783031730108"}],"license":[{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73010-8_4","type":"book-chapter","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T13:11:09Z","timestamp":1731157869000},"page":"53-70","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Integration of\u00a0Global and\u00a0Local Representations for\u00a0Fine-Grained Cross-Modal Alignment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0542-2793","authenticated-orcid":false,"given":"Seungwan","family":"Jin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5714-2531","authenticated-orcid":false,"given":"Hoyoung","family":"Choi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1449-510X","authenticated-orcid":false,"given":"Taehyung","family":"Noh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5535-0081","authenticated-orcid":false,"given":"Kyungsik","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,10]]},"reference":[{"key":"4_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/978-3-031-19800-7_23","volume-title":"Computer Vision \u2013 ECCV 2022","author":"J Byun","year":"2022","unstructured":"Byun, J., Hwang, T., Fu, J., Moon, T.: GRIT-VLP: grouped mini-batch sampling for efficient vision and language pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13679, pp. 395\u2013412. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19800-7_23"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Q., Huang, J., Feris, R., Brown, L.M., Dong, J., Yan, S.: Deep domain adaptation for describing people based on fine-grained clothing attributes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5315\u20135324 (2015)","DOI":"10.1109\/CVPR.2015.7299169"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Gong, S., Bazzani, L.: Image search with text feedback by visiolinguistic attention learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3001\u20133011 (2020)","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Revisiting multimodal representation in contrastive learning: from patch and token embeddings to finite discrete tokens. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15095\u201315104 (2023)","DOI":"10.1109\/CVPR52729.2023.01449"},{"key":"4_CR5","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":"4_CR6","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Gao, D., et al.: FashionBERT: text and image matching with adaptive loss for cross-modal retrieval. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2251\u20132260 (2020)","DOI":"10.1145\/3397271.3401430"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Goenka, S., et al.: FashionVLP: vision language transformer for fashion retrieval with feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14105\u201314115 (2022)","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"4_CR9","unstructured":"Gunel, B., Du, J., Conneau, A., Stoyanov, V.: Supervised contrastive learning for pre-trained language model fine-tuning. In: International Conference on Learning Representations (2021)"},{"key":"4_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1007\/978-3-031-19833-5_37","volume-title":"Computer Vision \u2013 ECCV 2022","author":"X Han","year":"2022","unstructured":"Han, X., Yu, L., Zhu, X., Zhang, L., Song, Y.Z., Xiang, T.: FashionViL: fashion-focused vision-and-language representation learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13695, pp. 634\u2013651. Springer, Cham (2022)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Han, Y., et al.: FashionSAP: symbols and attributes prompt for fine-grained fashion vision-language pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15028\u201315038 (2023)","DOI":"10.1109\/CVPR52729.2023.01443"},{"key":"4_CR12","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Jang, J., Kong, C., Jeon, D., Kim, S., Kwak, N.: Unifying vision-language representation space with single-tower transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 980\u2013988 (2023)","DOI":"10.1609\/aaai.v37i1.25178"},{"key":"4_CR14","unstructured":"Jia, C., et al Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Kim, J., Yu, Y., Kim, H., Kim, G.: Dual compositional learning in interactive image retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1771\u20131779 (2021)","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"4_CR16","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. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, D., Han, B.: CoSMo: content-style modulation for image retrieval with text feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 802\u2013812 (2021)","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"4_CR18","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"4_CR19","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"4_CR20","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XXX. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"4_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Rodriguez-Opazo, C., Teney, D., Gould, S.: Image retrieval on real-life images with pre-trained vision-and-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2125\u20132134 (2021)","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"4_CR24","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Ma, H., et al.: EI-CLIP: entity-aware interventional contrastive learning for e-commerce cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18051\u201318061 (2022)","DOI":"10.1109\/CVPR52688.2022.01752"},{"key":"4_CR26","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"4_CR27","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: IM2Text: describing images using 1 million captioned photographs. Adv. Neural Inf. Process. Syst. 24 (2011)"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De\u00a0Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"4_CR30","unstructured":"Qi, D., Su, L., Song, J., Cui, E., Bharti, T., Sacheti, A.: ImageBERT: cross-modal pre-training with large-scale weak-supervised image-text data. arXiv preprint arXiv:2001.07966 (2020)"},{"key":"4_CR31","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"4_CR32","unstructured":"Robinson, J., Chuang, C.Y., Sra, S., Jegelka, S.: Contrastive learning with hard negative samples. In: International Conference on Learning Representations (2021)"},{"key":"4_CR33","unstructured":"Rostamzadeh, N., et al.: Fashion-gen: the generative fashion dataset and challenge. arXiv preprint arXiv:1806.08317 (2018)"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"4_CR37","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Vo, N., et al.: Composing text and image for image retrieval-an empirical odyssey. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6439\u20136448 (2019)","DOI":"10.1109\/CVPR.2019.00660"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhou, P., Shou, M.Z., Yan, S.: Position-guided text prompt for vision-language pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23242\u201323251 (2023)","DOI":"10.1109\/CVPR52729.2023.02226"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: FashionKLIP: enhancing E-commerce image-text retrieval with fashion multi-modal conceptual knowledge graph. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pp. 149\u2013158 (2023)","DOI":"10.18653\/v1\/2023.acl-industry.16"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Fashion IQ: a new dataset towards retrieving images by natural language feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11307\u201311317 (2021)","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"4_CR42","unstructured":"Wu, M., Mosse, M., Zhuang, C., Yamins, D., Goodman, N.: Conditional negative sampling for contrastive learning of visual representations. In: International Conference on Learning Representations (2020)"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Vision-language pre-training with triple contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15671\u201315680 (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: CommerceMM: large-scale commerce multimodal representation learning with omni retrieval. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4433\u20134442 (2022)","DOI":"10.1145\/3534678.3539151"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Zhuge, M., et al.: Kaleido-BERT: vision-language pre-training on fashion domain. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12647\u201312657 (2021)","DOI":"10.1109\/CVPR46437.2021.01246"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73010-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T14:02:47Z","timestamp":1731160967000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73010-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,10]]},"ISBN":["9783031730092","9783031730108"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73010-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,10]]},"assertion":[{"value":"10 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}