{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T07:06:27Z","timestamp":1790233587541,"version":"4.1.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374608","type":"print"},{"value":"9783032374615","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37461-5_17","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:42:48Z","timestamp":1790232168000},"page":"310-326","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AMCI: Unlock the\u00a0Potential of\u00a0Large Multimodal Models for\u00a0Fine-Grained Open-World Classification via\u00a0Adaptive Memory Context Injection"],"prefix":"10.1007","author":[{"given":"Xiao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhun","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"17_CR1","unstructured":"Abdin, M., et al.: Phi-3 technical report: a highly capable language model locally on your phone (2024). https:\/\/arxiv.org\/abs\/2404.14219"},{"key":"17_CR2","unstructured":"Angheben, S., Berasi, D., Conti, A., Ricci, E., Wang, Y.: Specificity-aware reinforcement learning for fine-grained open-world classification. In: CVPR, pp. 41467\u201341477 (2026)"},{"key":"17_CR3","unstructured":"Bai, J., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond (2023). https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Bendale, A., Boult, T.: Towards open world recognition. In: CVPR, pp. 1893\u20131902 (2015)","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van\u00a0Gool, L.: Food-101\u2013mining discriminative components with random forests. In: ECCV, pp. 446\u2013461. Springer (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"17_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607. PmLR (2020)"},{"issue":"12","key":"17_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5","volume":"67","author":"Z Chen","year":"2024","unstructured":"Chen, Z., et al.: How far are we to GPT-4v? closing the gap to commercial multimodal models with open-source suites. Sci. China Inf. Sci. 67(12), 220101 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"17_CR9","first-page":"30662","volume":"36","author":"A Conti","year":"2023","unstructured":"Conti, A., et al.: Vocabulary-free image classification. NeurIPS 36, 30662\u201330680 (2023)","journal-title":"NeurIPS"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Conti, A., et al.: Vocabulary-free image classification and semantic segmentation. IEEE TPAMI (2026)","DOI":"10.1109\/TPAMI.2026.3657989"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Conti, A., et al.: On large multimodal models as open-world image classifiers. In: ICCV, pp. 16388\u201316398 (2025)","DOI":"10.1109\/ICCV51701.2025.01521"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Dai, Q., Yang, S.: Free on the fly: enhancing flexibility in test-time adaptation with online em. In: CVPR, pp. 9538\u20139548 (2025)","DOI":"10.1109\/CVPR52734.2025.00891"},{"key":"17_CR13","first-page":"49250","volume":"36","author":"W Dai","year":"2023","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning. NeurIPS 36, 49250\u201349267 (2023)","journal-title":"NeurIPS"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Dall\u2019Asen, N., Wang, Y., Fini, E., Ricci, E.: Retrieval-enriched zero-shot image classification in low-resource domains. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 21287\u201321302 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1186"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Fan, X., et al.: Test-time retrieval-augmented adaptation for vision-language models. In: ICCV, pp. 8810\u20138819 (2025)","DOI":"10.1109\/ICCV51701.2025.00824"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Feng, C.M., Yu, K., Liu, Y., Khan, S., Zuo, W.: Diverse data augmentation with diffusions for effective test-time prompt tuning. In: ICCV, pp. 2704\u20132714 (2023)","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"17_CR18","unstructured":"Gao, Y., et al.: Visual prompt tuning for test-time domain adaptation (2022). arXiv preprint arXiv:2210.04831"},{"key":"17_CR19","unstructured":"Garosi, M., Farina, M., Conti, A., Mancini, M., Ricci, E.: Large multimodal models as general in-context classifiers (2026). arXiv preprint arXiv:2602.23229"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR21","first-page":"31096","volume":"36","author":"CY Hsieh","year":"2023","unstructured":"Hsieh, C.Y., Zhang, J., Ma, Z., Kembhavi, A., Krishna, R.: Sugarcrepe: fixing hackable benchmarks for vision-language compositionality. NeurIPS 36, 31096\u201331116 (2023)","journal-title":"NeurIPS"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Karmanov, A., Guan, D., Lu, S., El Saddik, A., Xing, E.: Efficient test-time adaptation of vision-language models. In: CVPR, pp. 14162\u201314171 (2024)","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"17_CR24","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)"},{"key":"17_CR25","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. NeurIPS 25 (2012)"},{"key":"17_CR26","first-page":"87874","volume":"37","author":"H Lauren\u00e7on","year":"2024","unstructured":"Lauren\u00e7on, H., Tronchon, L., Cord, M., Sanh, V.: What matters when building vision-language models? NeurIPS 37, 87874\u201387907 (2024)","journal-title":"NeurIPS"},{"key":"17_CR27","unstructured":"Lee, Y., et al.: RA-TTA: Retrieval-augmented test-time adaptation for vision-language models. In: ICLR (2025)"},{"key":"17_CR28","unstructured":"Li, B., et\u00a0al.: LLaVA-OneVision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Li, B., et al.: Seed-Bench: benchmarking multimodal large language models. In: CVPR, pp. 13299\u201313308 (2024)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"17_CR30","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, pp. 19730\u201319742. PMLR (2023)"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Li, K., et\u00a0al.: MVBench: a comprehensive multi-modal video understanding benchmark. In: CVPR, pp. 22195\u201322206 (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"17_CR32","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":"17_CR33","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. NeurIPS 36, 34892\u201334916 (2023)","journal-title":"NeurIPS"},{"key":"17_CR34","unstructured":"Liu, H., et al.: Revisiting MLLMs: an in-depth analysis of image classification abilities. arXiv preprint arXiv:2412.16418 (2024)"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? In: ECCV, pp. 216\u2013233. Springer (2024)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"17_CR36","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft (2013). arXiv preprint arXiv:1306.5151"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian conference on computer vision, graphics & image processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR, pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"17_CR39","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PmLR (2021)"},{"key":"17_CR40","first-page":"14274","volume":"35","author":"M Shu","year":"2022","unstructured":"Shu, M., et al.: Test-time prompt tuning for zero-shot generalization in vision-language models. NeurIPS 35, 14274\u201314289 (2022)","journal-title":"NeurIPS"},{"issue":"1","key":"17_CR41","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.161","volume":"5","author":"P Tschandl","year":"2018","unstructured":"Tschandl, P., Rosendahl, C., Kittler, H.: The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5(1), 180161 (2018)","journal-title":"Sci. Data"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Van Horn, G., et al.: The inaturalist species classification and detection dataset. In: CVPR, pp. 8769\u20138778 (2018)","DOI":"10.1109\/CVPR.2018.00914"},{"key":"17_CR43","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: ICCV, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"17_CR45","first-page":"51727","volume":"37","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y.: Why are visually-grounded language models bad at image classification? NeurIPS 37, 51727\u201351753 (2024)","journal-title":"NeurIPS"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Doughty, H., Snoek, C.G.M.: Low-resource vision challenges for foundation models. In: CVPR, pp. 21956\u201321966 (2024)","DOI":"10.1109\/CVPR52733.2024.02073"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37461-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:42:59Z","timestamp":1790232179000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37461-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374608","9783032374615"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37461-5_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}