{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:20:19Z","timestamp":1777569619600,"version":"3.51.4"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726637","type":"print"},{"value":"9783031726644","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72664-4_23","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"405-422","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Removing Distributional Discrepancies in\u00a0Captions Improves Image-Text Alignment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6082-6398","authenticated-orcid":false,"given":"Yuheng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haotian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7967-9752","authenticated-orcid":false,"given":"Mu","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7295-8750","authenticated-orcid":false,"given":"Yijun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6783-1795","authenticated-orcid":false,"given":"Eli","family":"Shechtman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1154-9907","authenticated-orcid":false,"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9863-1270","authenticated-orcid":false,"given":"Yong Jae","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8066-6835","authenticated-orcid":false,"given":"Krishna Kumar","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"23_CR1","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS, vol. 35, pp. 23716\u201323736 (2022)"},{"key":"23_CR2","unstructured":"Betker, J., et al.: Improving image generation with better captions (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"23_CR3","unstructured":"Bitton, Y.: WYSIWYR repository (2023). https:\/\/github.com\/yonatanbitton\/wysiwyr. Accessed 24 Feb 2024"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"23_CR5","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, June 2022","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"23_CR6","unstructured":"Chen, X., et al.: PaLI: a jointly-scaled multilingual language-image model (2022). ArXiv abs\/2209.06794. https:\/\/api.semanticscholar.org\/CorpusID:252222320"},{"key":"23_CR7","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":"23_CR8","unstructured":"Doveh, S., et\u00a0al.: Dense and aligned captions (DAC) promote compositional reasoning in VL models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Doveh, S., et al.: Teaching structured vision & language concepts to vision & language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2657\u20132668 (2023)","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"23_CR10","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=PUIqjT4rzq7"},{"key":"23_CR11","unstructured":"Gadre, S.Y., et\u00a0al.: DataComp: in search of the next generation of multimodal datasets. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Herzig, R., et al.: Incorporating structured representations into pretrained vision & language models using scene graphs. In: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.870"},{"key":"23_CR13","doi-asserted-by":"publisher","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Le\u00a0Bras, R., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.T. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7514\u20137528. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, November 2021. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.595. https:\/\/aclanthology.org\/2021.emnlp-main.595","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"23_CR14","unstructured":"Hsieh, C.Y., Zhang, J., Ma, Z., Kembhavi, A., Krishna, R.: SugarCrepe: fixing hackable benchmarks for vision-language compositionality. In: Thirty-Seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2023)"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: TIFA: accurate and interpretable text-to-image faithfulness evaluation with question answering. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"23_CR16","unstructured":"Karthik, S., Roth, K., Mancini, M., Akata, Z.: If at first you don\u2019t succeed, try, try again: faithful diffusion-based text-to-image generation by selection. arXiv preprint arXiv:2305.13308 (2023)"},{"key":"23_CR17","unstructured":"Le, T., Lal, V., Howard, P.: COCO-counterfactuals: automatically constructed counterfactual examples for image-text pairs. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"23_CR18","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.C.H.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning (2023). https:\/\/api.semanticscholar.org\/CorpusID:256390509"},{"key":"23_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":"23_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. In: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"23_CR21","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":"23_CR22","unstructured":"Lin, Z., Chen, X., Pathak, D., Zhang, P., Ramanan, D.: Revisiting the role of language priors in vision-language models. arXiv preprint arXiv:2306.01879 (2023)"},{"key":"23_CR23","unstructured":"Lin, Z., Chen, X., Pathak, D., Zhang, P., Ramanan, D.: VisualGPTScore: visio-linguistic reasoning with multimodal generative pre-training scores. arXiv preprint arXiv:2306.01879 (2023)"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"23_CR25","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv:2304.08485 (2023)"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Ma, Z., Hong, J., Gul, M.O., Gandhi, M., Gao, I., Krishna, R.: CREPE: can vision-language foundation models reason compositionally? arXiv preprint arXiv:2212.07796 (2022)","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"23_CR27","unstructured":"OpenAI: GPT-4V(ision) system card (2023). https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf"},{"key":"23_CR28","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":"23_CR29","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"23_CR30","unstructured":"Ray, A., Radenovic, F., Dubey, A., Plummer, B.A., Krishna, R., Saenko, K.: COLA: how to adapt vision-language models to compose objects localized with attributes? (2023)"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR32","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 25278\u201325294 (2022)"},{"key":"23_CR33","doi-asserted-by":"publisher","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565. Association for Computational Linguistics, Melbourne, Australia, July 2018. https:\/\/doi.org\/10.18653\/v1\/P18-1238. https:\/\/aclanthology.org\/P18-1238","DOI":"10.18653\/v1\/P18-1238"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: FLAVA: a foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15638\u201315650 (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"23_CR35","unstructured":"StabilityAI: IF repository. https:\/\/github.com\/deep-floyd\/IF"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Thrush, T., et al.: Winoground: probing vision and language models for visio-linguistic compositionality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5238\u20135248 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Z.J., Montoya, E., Munechika, D., Yang, H., Hoover, B., Chau, D.H.: Large-scale prompt gallery dataset for text-to-image generative models. arXiv:2210.14896 [cs] (2022). https:\/\/arxiv.org\/abs\/2210.14896","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"23_CR38","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"23_CR39","unstructured":"Yarom, M., et al.: What you see is what you read? Improving text-image alignment evaluation. arXiv preprint arXiv:2305.10400 (2023)"},{"key":"23_CR40","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? In: International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=KRLUvxh8uaX"},{"key":"23_CR41","unstructured":"Zhang, K., Mo, L., Chen, W., Sun, H., Su, Y.: MagicBrush: a manually annotated dataset for instruction-guided image editing. In: Advances in Neural Information Processing Systems (2023)"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, T., et al.: VL-CheckList: evaluating pre-trained vision-language models with objects, attributes and relations. arXiv preprint arXiv:2207.00221 (2022)","DOI":"10.18653\/v1\/2022.emnlp-demos.4"}],"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\/978-3-031-72664-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:09:13Z","timestamp":1729876153000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72664-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726637","9783031726644"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72664-4_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 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"}}]}}