{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:46:54Z","timestamp":1742914014267,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726729"},{"type":"electronic","value":"9783031726736"}],"license":[{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"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\/978-3-031-72673-6_4","type":"book-chapter","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T16:03:50Z","timestamp":1729526630000},"page":"58-75","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dataset Growth"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8571-1228","authenticated-orcid":false,"given":"Ziheng","family":"Qin","sequence":"first","affiliation":[]},{"given":"Zhaopan","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Yukun","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Zangwei","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Zebang","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Shang","sequence":"additional","affiliation":[]},{"given":"Baigui","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Xiaojiang","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Radu","family":"Timofte","sequence":"additional","affiliation":[]},{"given":"Hongxun","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yang","family":"You","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,22]]},"reference":[{"key":"4_CR1","unstructured":"Common crawl. https:\/\/commoncrawl.org\/"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"4_CR3","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. CoRR abs\/2102.08981 (2021). https:\/\/arxiv.org\/abs\/2102.08981","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"4_CR4","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4_CR5","unstructured":"Douze, M., et al.: The Faiss library (2024)"},{"key":"4_CR6","unstructured":"Duarte, F.: Amount of data created daily (2024). https:\/\/explodingtopics.com\/blog\/data-generated-per-day"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the v in VQA matter: elevating the role of image understanding in visual question answering (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"4_CR8","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs\/1512.03385 (2015). http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"4_CR9","unstructured":"Iyer, R., Khargoankar, N., Bilmes, J., Asanani, H.: Submodular combinatorial information measures with applications in machine learning. In: Algorithmic Learning Theory, pp. 722\u2013754. PMLR (2021)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything (2023). arXiv:2304.02643","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"4_CR11","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)","journal-title":"Int. J. Comput. Vis."},{"key":"4_CR12","unstructured":"Krizhevsky, A., Nair, V., Hinton, G.: CIFAR-10 (Canadian institute for advanced research). http:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"4_CR13","unstructured":"LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"4_CR14","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models (2023)"},{"key":"4_CR15","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 12888\u201312900. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"4_CR16","unstructured":"Li, J., Selvaraju, R.R., Gotmare, A.D., Joty, S.R., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. CoRR abs\/2107.07651 (2021). https:\/\/arxiv.org\/abs\/2107.07651"},{"key":"4_CR17","unstructured":"Li, J., Socher, R., Hoi, S.C.H.: DivideMix: learning with noisy labels as semi-supervised learning (2020)"},{"key":"4_CR18","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., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"4_CR19","unstructured":"Malkov, Y.A., Yashunin, D.A.: Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. CoRR abs\/1603.09320 (2016). http:\/\/arxiv.org\/abs\/1603.09320"},{"key":"4_CR20","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":"4_CR21","unstructured":"Peng, B., Li, C., He, P., Galley, M., Gao, J.: Instruction tuning with GPT-4 (2023)"},{"key":"4_CR22","unstructured":"Qin, Z., et al.: InfoBatch: lossless training speed up by unbiased dynamic data pruning. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=C61sk5LsK6"},{"key":"4_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"4_CR24","doi-asserted-by":"publisher","unstructured":"Raju, R.S., Daruwalla, K., Lipasti, M.: Accelerating deep learning with dynamic data pruning (2021). https:\/\/doi.org\/10.48550\/ARXIV.2111.12621. https:\/\/arxiv.org\/abs\/2111.12621","DOI":"10.48550\/ARXIV.2111.12621"},{"key":"4_CR25","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models (2022)"},{"key":"4_CR26","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 (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1238. https:\/\/aclanthology.org\/P18-1238","DOI":"10.18653\/v1\/P18-1238"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs (2019)","DOI":"10.18653\/v1\/P19-1644"},{"key":"4_CR28","doi-asserted-by":"publisher","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 843\u2013852 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.97","DOI":"10.1109\/ICCV.2017.97"},{"issue":"2","key":"4_CR29","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016)","journal-title":"Commun. ACM"},{"key":"4_CR30","doi-asserted-by":"publisher","unstructured":"Toneva, M., Sordoni, A., des Combes, R.T., Trischler, A., Bengio, Y., Gordon, G.J.: An empirical study of example forgetting during deep neural network learning (2018). https:\/\/doi.org\/10.48550\/ARXIV.1812.05159. https:\/\/arxiv.org\/abs\/1812.05159","DOI":"10.48550\/ARXIV.1812.05159"},{"key":"4_CR31","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"4_CR32","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models (2023)"}],"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\/978-3-031-72673-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T16:04:48Z","timestamp":1729526688000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72673-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,22]]},"ISBN":["9783031726729","9783031726736"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72673-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,22]]},"assertion":[{"value":"22 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"}}]}}