{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:16:59Z","timestamp":1784765819088,"version":"3.55.0"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031916717","type":"print"},{"value":"9783031916724","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91672-4_3","type":"book-chapter","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T15:23:47Z","timestamp":1747754627000},"page":"32-45","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Aligning Vision Language Models with\u00a0Contrastive Learning"],"prefix":"10.1007","author":[{"given":"Kenan E.","family":"Ak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jay","family":"Mohta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitris","family":"Dimitriadis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saurav","family":"Manchanda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingwei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Ak, K.E., Lee, G.G., Xu, Y., Shen, M.: Leveraging efficient training and feature fusion in transformers for multimodal classification. In: 2023 IEEE International Conference on Image Processing (ICIP), pp. 1420\u20131424. IEEE (2023)","DOI":"10.1109\/ICIP49359.2023.10223098"},{"key":"3_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR3","unstructured":"Bai, J., et al.: Qwen-vl: a versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"3_CR4","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. arXiv:abs\/2005.14165 (2020). https:\/\/api.semanticscholar.org\/CorpusID:218971783"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Cha, J., Kang, W., Mun, J., Roh, B.: Honeybee: locality-enhanced projector for multimodal LLM. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13817\u201313827 (2024)","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Sharegpt4v: improving large multi-modal models with better captions. arXiv preprint arXiv:2311.12793 (2023)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"3_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"3_CR10","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"3_CR11","unstructured":"Chowdhery, A., et al.: Palm: scaling language modeling with pathways. arXiv:abs\/2204.02311 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247951931"},{"issue":"70","key":"3_CR12","first-page":"1","volume":"25","author":"HW Chung","year":"2024","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. J. Mach. Learn. Res. 25(70), 1\u201353 (2024)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR13","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"3_CR14","unstructured":"Fu, C., et al.: MME: a comprehensive evaluation benchmark for multimodal large language models (2024). https:\/\/arxiv.org\/abs\/2306.13394"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., Chen, D.: SIMCSE: simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Giorgi, J., Nitski, O., Wang, B., Bader, G.: DeCLUTR: deep contrastive learning for unsupervised textual representations. arXiv preprint arXiv:2006.03659 (2020)","DOI":"10.18653\/v1\/2021.acl-long.72"},{"key":"3_CR17","unstructured":"He, M., et al.: Efficient multimodal learning from data-centric perspective. arXiv preprint arXiv:2402.11530 (2024)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, C., et al.: Hallucination augmented contrastive learning for multimodal large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27036\u201327046 (2024)","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, T., et al.: PromptBert: improving Bert sentence embeddings with prompts. arXiv preprint arXiv:2201.04337 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.603"},{"key":"3_CR21","unstructured":"Kim, T., et\u00a0al.: Nice: CVPR 2023 challenge on zero-shot image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshop: New Frontiers for Zero-Shot Image Captioning Evaluation, pp. 7356\u20137365 (2024)"},{"key":"3_CR22","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":"3_CR23","doi-asserted-by":"crossref","unstructured":"Li, B., et al.: Seed-bench: benchmarking multimodal large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13299\u201313308 (2024)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"3_CR24","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":"3_CR25","doi-asserted-by":"crossref","unstructured":"Lin, J., Yin, H., Ping, W., Molchanov, P., Shoeybi, M., Han, S.: Vila: on pre-training for visual language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26689\u201326699 (2024)","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"3_CR26","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":"3_CR27","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"3_CR28","unstructured":"Liu, H., et al.: Llava-next: improved reasoning, OCR, and world knowledge (2024). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"3_CR29","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"3_CR31","unstructured":"van\u00a0der Maaten, L., Hinton, G.: Visualizing data using T-SNE. J. Mach. Learn. Res. 9(86), 2579\u20132605 (2008). http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html"},{"key":"3_CR32","unstructured":"McKinzie, B., et\u00a0al.: MM1: methods, analysis & insights from multimodal LLM pre-training. arXiv preprint arXiv:2403.09611 (2024)"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Mishra, A., Shekhar, S., Singh, A.K., Chakraborty, A.: OCR-VQA: visual question answering by reading text in images. In: 2019 International Conference on Document analysis and Recognition (ICDAR), pp. 947\u2013952. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"3_CR34","unstructured":"Mohta, J., Ak, K., Xu, Y., Shen, M.: Are large language models good annotators? In: Advances in Neural Information Processing Systems Workshop: I Can\u2019t Believe It\u2019s Not Better- Failure Modes in the Age of Foundation Models"},{"key":"3_CR35","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2text: describing images using 1 million captioned photographs. In: Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F., Weinberger, K. (eds.) Advances in Neural Information Processing Systems. vol.\u00a024. Curran Associates, Inc. (2011), https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2011\/file\/5dd9db5e033da9c6fb5ba83c7a7ebea9-Paper.pdf"},{"key":"3_CR36","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. arXiv:abs\/2203.02155 (2022). https:\/\/api.semanticscholar.org\/CorpusID:246426909"},{"key":"3_CR37","unstructured":"Penedo, G., et al.: The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116 (2023), https:\/\/arxiv.org\/abs\/2306.01116"},{"key":"3_CR38","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":"3_CR39","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":"3_CR40","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs (2021). https:\/\/arxiv.org\/abs\/2111.02114"},{"key":"3_CR41","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), Melbourne, Australia, pp. 2556\u20132565. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1238, https:\/\/aclanthology.org\/P18-1238","DOI":"10.18653\/v1\/P18-1238"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"3_CR43","unstructured":"Sukhbaatar, S., et\u00a0al.: Branch-train-mix: mixing expert LLMS into a mixture-of-experts LLM. arXiv preprint arXiv:2403.07816 (2024)"},{"key":"3_CR44","unstructured":"Tay, Y., et\u00a0al.: Ul2: Unifying language learning paradigms. arXiv preprint arXiv:2205.05131 (2022)"},{"key":"3_CR45","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv:abs\/2302.13971 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257219404"},{"key":"3_CR46","first-page":"200","volume":"34","author":"M Tsimpoukelli","year":"2021","unstructured":"Tsimpoukelli, M., Menick, J.L., Cabi, S., Eslami, S., Vinyals, O., Hill, F.: Multimodal few-shot learning with frozen language models. Adv. Neural. Inf. Process. Syst. 34, 200\u2013212 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: MPLUG-owl2: revolutionizing multi-modal large language model with modality collaboration (2023). https:\/\/arxiv.org\/abs\/2311.04257","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"3_CR48","unstructured":"Yu, W., et al.: MM-VET: evaluating large multimodal models for integrated capabilities (2023). https:\/\/arxiv.org\/abs\/2308.02490"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91672-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T15:24:17Z","timestamp":1747754657000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91672-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031916717","9783031916724"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91672-4_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}