{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T06:00:52Z","timestamp":1770357652781,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620609","type":"print"},{"value":"9789819620616","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"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\/978-981-96-2061-6_21","type":"book-chapter","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T05:46:12Z","timestamp":1735537572000},"page":"282-295","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["LLMs-Based Augmentation for\u00a0Domain Adaptation in\u00a0Long-Tailed Food Datasets"],"prefix":"10.1007","author":[{"given":"Qing","family":"Wang","sequence":"first","affiliation":[]},{"given":"Chong-Wah","family":"Ngo","sequence":"additional","affiliation":[]},{"given":"Ee-Peng","family":"Lim","sequence":"additional","affiliation":[]},{"given":"Qianru","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"21_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"21_CR2","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"key":"21_CR3","doi-asserted-by":"publisher","first-page":"5890","DOI":"10.1109\/TPAMI.2024.3369102","volume":"46","author":"C Du","year":"2024","unstructured":"Du, C., Wang, Y., Song, S., Huang, G.: Probabilistic contrastive learning for long-tailed visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 46, 5890\u20135904 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"21_CR4","first-page":"2030","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030\u20132096 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR5","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/978-3-031-20050-2_42","volume-title":"ECCV 2022, Part XXIII","author":"X Gu","year":"2022","unstructured":"Gu, X., et al.: Tackling long-tailed category distribution under domain shifts. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXIII. LNCS, vol. 13683, pp. 727\u2013743. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20050-2_42"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR7","unstructured":"Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. In: International Conference on Learning Representations (2019)"},{"key":"21_CR8","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: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"21_CR9","doi-asserted-by":"publisher","first-page":"7048","DOI":"10.1109\/TNNLS.2022.3213563","volume":"35","author":"Y Liang","year":"2022","unstructured":"Liang, Y., Zhu, L., Wang, X., Yang, Y.: Penalizing the hard example but not too much: a strong baseline for fine-grained visual classification. IEEE Trans. Neural Netw. Learn. Syst. 35, 7048\u20137059 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"21_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109550","volume":"140","author":"D Liu","year":"2023","unstructured":"Liu, D., Zhao, L., Wang, Y., Kato, J.: Learn from each other to classify better: cross-layer mutual attention learning for fine-grained visual classification. Pattern Recogn. 140, 109550 (2023)","journal-title":"Pattern Recogn."},{"key":"21_CR11","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2537\u20132546 (2019)","DOI":"10.1109\/CVPR.2019.00264"},{"issue":"11","key":"21_CR13","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"21_CR14","doi-asserted-by":"publisher","first-page":"9932","DOI":"10.1109\/TPAMI.2023.3237871","volume":"45","author":"W Min","year":"2023","unstructured":"Min, W., et al.: Large scale visual food recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9932\u20139949 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Park, S., Hong, Y., Heo, B., Yun, S., Choi, J.Y.: The majority can help the minority: context-rich minority oversampling for long-tailed classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6887\u20136896 (2022)","DOI":"10.1109\/CVPR52688.2022.00676"},{"key":"21_CR16","unstructured":"Qiu, J., Lo, F.P.W., Sun, Y., Wang, S., Lo, B.: Mining discriminative food regions for accurate food recognition. arXiv preprint arXiv:2207.03692 (2022)"},{"key":"21_CR17","unstructured":"Rangwani, H., Aithal, S.K., Mishra, M., Jain, A., Radhakrishnan, V.B.: A closer look at smoothness in domain adversarial training. In: International Conference on Machine Learning, pp. 18378\u201318399. PMLR (2022)"},{"key":"21_CR18","first-page":"4175","volume":"33","author":"J Ren","year":"2020","unstructured":"Ren, J., Yu, C., Ma, X., Zhao, H., Yi, S., et al.: Balanced meta-softmax for long-tailed visual recognition. Adv. Neural. Inf. Process. Syst. 33, 4175\u20134186 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"R\u00f3denas, J., Nagarajan, B., Bola\u00f1os, M., Radeva, P.: Learning multi-subset of classes for fine-grained food recognition. In: Proceedings of the 7th International Workshop on Multimedia Assisted Dietary Management, pp. 17\u201326 (2022)","DOI":"10.1145\/3552484.3555754"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Sahoo, D., et al.: FoodAI: food image recognition via deep learning for smart food logging. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2260\u20132268 (2019)","DOI":"10.1145\/3292500.3330734"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Salvador, A., Gundogdu, E., Bazzani, L., Donoser, M.: Revamping cross-modal recipe retrieval with hierarchical transformers and self-supervised learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15475\u201315484 (2021)","DOI":"10.1109\/CVPR46437.2021.01522"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Salvador, A., et al.: Learning cross-modal embeddings for cooking recipes and food images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3020\u20133028 (2017)","DOI":"10.1109\/CVPR.2017.327"},{"issue":"2","key":"21_CR23","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0378-3758(00)00115-4","volume":"90","author":"H Shimodaira","year":"2000","unstructured":"Shimodaira, H.: Improving predictive inference under covariate shift by weighting the log-likelihood function. J. Stat. Plan. Inference 90(2), 227\u2013244 (2000)","journal-title":"J. Stat. Plan. Inference"},{"key":"21_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-031-19806-9_26","volume-title":"ECCV 2022","author":"Y Shu","year":"2022","unstructured":"Shu, Y., Yu, B., Xu, H., Liu, L.: Improving fine-grained visual recognition in low data regimes via self-boosting attention mechanism. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13685, pp. 449\u2013465. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19806-9_26"},{"issue":"5","key":"21_CR25","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1109\/72.788640","volume":"10","author":"VN Vapnik","year":"1999","unstructured":"Vapnik, V.N.: An overview of statistical learning theory. IEEE Trans. Neural Networks 10(5), 988\u2013999 (1999)","journal-title":"IEEE Trans. Neural Networks"},{"key":"21_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"21_CR27","unstructured":"Wang, X., Kumar, D., Thome, N., Cord, M., Precioso, F.: Recipe recognition with large multimodal food dataset. In: 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp.\u00a01\u20136. IEEE (2015)"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Y., Song, R., Wei, X.S., Zhang, L.: An adversarial domain adaptation network for cross-domain fine-grained recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1228\u20131236 (2020)","DOI":"10.1109\/WACV45572.2020.9093306"},{"key":"21_CR29","unstructured":"Wang, Z., Xu, Q., Yang, Z., He, Y., Cao, X., Huang, Q.: A unified generalization analysis of re-weighting and logit-adjustment for imbalanced learning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"21_CR30","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/978-3-031-20044-1_4","volume-title":"ECCV 2022","author":"Y Yang","year":"2022","unstructured":"Yang, Y., Wang, H., Katabi, D.: On multi-domain long-tailed recognition, imbalanced domain generalization and beyond. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13680, pp. 57\u201375. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20044-1_4"},{"key":"21_CR31","unstructured":"Yin, Y., Qi, H., Zhu, B., Chen, J., Jiang, Y.G., Ngo, C.W.: FoodLMM: a versatile food assistant using large multi-modal model. arXiv preprint arXiv:2312.14991 (2023)"},{"key":"21_CR32","unstructured":"Zhang, Y., et al.: Free lunch for domain adversarial training: environment label smoothing. arXiv preprint arXiv:2302.00194 (2023)"},{"key":"21_CR33","doi-asserted-by":"publisher","first-page":"8201","DOI":"10.1109\/TCSVT.2024.3391304","volume":"34","author":"W Zhou","year":"2024","unstructured":"Zhou, W., Zhou, Z.: Unsupervised domain adaption harnessing vision-language pre-training. IEEE Trans. Circuits Syst. Video Technol. 34, 8201\u20138214 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2061-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T06:05:52Z","timestamp":1735538752000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2061-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"ISBN":["9789819620609","9789819620616"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2061-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,31]]},"assertion":[{"value":"31 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}