{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T14:47:39Z","timestamp":1781102859942,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819500086","type":"print"},{"value":"9789819500093","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\/978-981-95-0009-3_25","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T13:25:21Z","timestamp":1753363521000},"page":"291-302","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Agro-LLaVA-Next: A Large Multimodal Model for Plant Diseases Recognization"],"prefix":"10.1007","author":[{"given":"Guowei","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiting","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhui","family":"Bie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingliang","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zekun","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaojun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"25_CR1","unstructured":"Radford, A., Narasimhan, K., Salimans, T.: Improving language understanding by generative pre-training. https:\/\/openai.com\/index\/language-unsupervised\/. Accessed 7 May 2025"},{"key":"25_CR2","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1016\/j.neucom.2017.06.023","volume":"267","author":"Y Lu","year":"2017","unstructured":"Lu, Y., Yi, S., Zeng, N.: Identification of rice diseases using deep convolutional neural networks. Neurocomputing 267, 378\u2013384 (2017)","journal-title":"Neurocomputing"},{"key":"25_CR3","doi-asserted-by":"publisher","first-page":"28773","DOI":"10.1007\/s11042-020-09461-w","volume":"79","author":"M Prabhakar","year":"2020","unstructured":"Prabhakar, M., Purushothaman, R., Awasthi, D.: Deep learning based assessment of disease severity for early blight in tomato crop. Multimedia Tools Appl. 79, 28773\u201328784 (2020)","journal-title":"Multimedia Tools Appl."},{"key":"25_CR4","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1016\/j.compag.2019.01.034","volume":"157","author":"Q Liang","year":"2019","unstructured":"Liang, Q., Xiang, S., Hu, Y.: PD2SE-Net: computer-assisted plant disease diagnosis and severity estimation network. Comput. Electron. Agric. 157, 518\u2013529 (2019)","journal-title":"Comput. Electron. Agric."},{"key":"25_CR5","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/s41348-020-00423-w","volume":"128","author":"S Xiang","year":"2021","unstructured":"Xiang, S., Liang, Q., Sun, W.: L-CSMS: novel lightweight network for plant disease severity recognition. J. Plant Dis. Prot. 128, 557\u2013569 (2021)","journal-title":"J. Plant Dis. Prot."},{"key":"25_CR6","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.927424","volume":"13","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Wang, Y., Zhao, J.: MGA-YOLO: a lightweight one-stage network for apple leaf disease detection. Front. Plant Sci. 13, 927424 (2022)","journal-title":"Front. Plant Sci."},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Y., Zhao, J.: Eca-convnext: a rice leaf disease identification model based on convnext. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6234\u20136242 (2023)","DOI":"10.1109\/CVPRW59228.2023.00663"},{"key":"25_CR8","unstructured":"Vaswani, A., Shazeer, N., Parmar, N.: Attention is all you need. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 5998\u20136008. Curran Associates, Inc., Long Beach, CA (2017)"},{"key":"25_CR9","unstructured":"Devlin, J., Chang, M.-W., Lee, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, MN (2019)"},{"key":"25_CR10","unstructured":"Brown, T.B., Mann, B., Ryder, N.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 1877\u20131901. Curran Associates, Inc., Virtual Event (2020)"},{"key":"25_CR11","unstructured":"Chowdhery, A., Narang, S., Devlin, J.: PaLM: scaling language modeling with pathways. https:\/\/arxiv.org\/abs\/2204.02311. Accessed 7 May 2025"},{"key":"25_CR12","unstructured":"Radford, A., Kim, J.W., Hallacy, C.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML), pp. 8748\u20138763. PMLR, Virtual Event (2021)"},{"key":"25_CR13","unstructured":"Ramesh, A., Pavlov, M., Goh, G.: DALL\u00b7E: creating images from text. https:\/\/arxiv.org\/abs\/2102.12092. Accessed 7 May 2025"},{"key":"25_CR14","unstructured":"Li, J., Li, D., Xiong, C.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning (ICML), pp. 12888\u201312900. PMLR (2022)"},{"key":"25_CR15","unstructured":"Li, J., Li, D., Savarese, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning (ICML), pp. 19730\u201319742. PMLR (2023)"},{"key":"25_CR16","unstructured":"Liu, H., Li, C., Wu, Q.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"25_CR17","unstructured":"Bai, J., Bai, S., Yang, S.: Qwen-vl: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"25_CR18","unstructured":"Wang, P., Bai, S., Tan, S.: Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Dai, D., Zhang, Y., Xu, L.: Pa-llava: A large language-vision assistant for human pathology image understanding. arXiv preprint arXiv:2408.09530 (2024)","DOI":"10.1109\/BIBM62325.2024.10821785"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Shi, W., Hu, Z., Bin, Y.: Math-LLaVA: bootstrapping mathematical reasoning for multimodal large language models. In: Findings of the Association for Computational Linguistics, pp. 4663\u20134680 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.268"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Bin, Y., Shi, W., Ding, Y.: Gallerygpt: analyzing paintings with large multimodal models. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 7734\u20137743 (2024)","DOI":"10.1145\/3664647.3681656"},{"key":"25_CR22","unstructured":"Li, C., Wong, C., Zhang, S.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Singh, A., Natarajan, V., Shah, M.: 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":"25_CR25","doi-asserted-by":"crossref","unstructured":"Hudson, D., Manning, C.: 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":"25_CR26","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (ICLR 2022). OpenReview.net (2022)"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: LlamaFactory: unified efficient fine-tuning of 100+ language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, vol. 3, pp 400\u2013410. Association for Computational Linguistics, Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Duan, H., et al.: VLMEvalKit: an open-source toolkit for evaluating large multi-modality models. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 11198\u201311201 (2024)","DOI":"10.1145\/3664647.3685520"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0009-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T02:24:12Z","timestamp":1779416652000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0009-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500086","9789819500093"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0009-3_25","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":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}