{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T21:21:07Z","timestamp":1758057667561,"version":"3.44.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051783","type":"print"},{"value":"9783032051790","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"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\/978-3-032-05179-0_3","type":"book-chapter","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T21:43:12Z","timestamp":1757972592000},"page":"29-40","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Food Waste Detection in Canteen Plates with Visual Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3110-2834","authenticated-orcid":false,"given":"Raffaele","family":"Cal\u00ec","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2264-3418","authenticated-orcid":false,"given":"Jo\u00e3o","family":"Ferreira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2165-0666","authenticated-orcid":false,"given":"Paulino","family":"Cerqueira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1874-7340","authenticated-orcid":false,"given":"Jorge","family":"Ribeiro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"3_CR1","unstructured":"Commission, E.; for Environment, D.G. Preparatory study on food waste across EU 27 - Final report; Publications Office (2011)"},{"key":"3_CR2","doi-asserted-by":"publisher","unstructured":"Belot, M., James, J.: Healthy school meals and educational outcomes. J. Health Econ. 30, 489\u2013504 (2011). https:\/\/doi.org\/10.1016\/j.jhealeco.2011.02.003","DOI":"10.1016\/j.jhealeco.2011.02.003"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Redmon, J., et al.: You Only Look Once: Unified, Real-Time Object Detection (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3_CR4","doi-asserted-by":"publisher","unstructured":"Zhang, Y., et al.: Deep learning in food category recognition. Inf. Fusion 98, 101859 (2023). https:\/\/doi.org\/10.1016\/j.inffus.2023.101859","DOI":"10.1016\/j.inffus.2023.101859"},{"key":"3_CR5","doi-asserted-by":"publisher","unstructured":"Lan, X., et al.: FoodSAM: any food segmentation. IEEE Trans. Multimed. 2024, 1\u201314 (2024). https:\/\/doi.org\/10.1109\/tmm.2023.3330047","DOI":"10.1109\/tmm.2023.3330047"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Fan, J., Cui, L., Fei, S.: Waste detection system based on data augmentation and YOLO_EC. Sensors 23 (2023). https:\/\/doi.org\/10.3390\/s23073646","DOI":"10.3390\/s23073646"},{"key":"3_CR7","doi-asserted-by":"publisher","unstructured":"Dhelia, A., Chordia, S.: YOLO-based Food Damage Detection: An Automated Approach for Quality Control in Food Industry (2024). https:\/\/doi.org\/10.1109\/I-SMAC61858.2024.10714664","DOI":"10.1109\/I-SMAC61858.2024.10714664"},{"key":"3_CR8","doi-asserted-by":"publisher","unstructured":"Pouladzadeh, P., Shirmohammadi, S.: Mobile Multi-Food Recognition Using Deep Learning (2017). https:\/\/doi.org\/10.1109\/ICAC3N56670.2022.10074297","DOI":"10.1109\/ICAC3N56670.2022.10074297"},{"issue":"13","key":"3_CR9","doi-asserted-by":"publisher","first-page":"7137","DOI":"10.3390\/app15137137","volume":"15","author":"J Ferreira","year":"2025","unstructured":"Ferreira, J., Cerqueira, P., Ribeiro, J.: Food waste detection in canteen plates using YOLOv11. Appl. Sci. 15(13), 7137 (2025). https:\/\/doi.org\/10.3390\/app15137137","journal-title":"Appl. Sci."},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"Xiao, T., Zhu, J.: Foundations of Large Language Models (2025). arXiv:2501.09223, https:\/\/doi.org\/10.48550\/arXiv.2501.09223","DOI":"10.48550\/arXiv.2501.09223"},{"key":"3_CR11","doi-asserted-by":"publisher","unstructured":"Smith, B., et al.: A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.09056","DOI":"10.48550\/arXiv.2505.09056"},{"key":"3_CR12","doi-asserted-by":"publisher","unstructured":"Huang, D., et al.: From large language models to large multimodal models: a literature review. Appl. Sci. 14, 5068 (2024). https:\/\/doi.org\/10.3390\/app14125068","DOI":"10.3390\/app14125068"},{"key":"3_CR13","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges (2025). https:\/\/doi.org\/10.13140\/RG.2.2.14334.91209","DOI":"10.13140\/RG.2.2.14334.91209"},{"key":"3_CR14","doi-asserted-by":"publisher","unstructured":"Li, Y., et al.: Visual Large Language Models for Generalized and Specialized Applications (2025). https:\/\/doi.org\/10.48550\/arXiv.2501.02765","DOI":"10.48550\/arXiv.2501.02765"},{"key":"3_CR15","doi-asserted-by":"publisher","unstructured":"Xue, J., et al.: Enhanced Multimodal RAG-LLM for Accurate Visual Question Answering (2024). https:\/\/doi.org\/10.48550\/arXiv.2412.20927","DOI":"10.48550\/arXiv.2412.20927"},{"key":"3_CR16","doi-asserted-by":"publisher","unstructured":"Zang, Y., et al.: Contextual object detection with multimodal large language models. Int. J. Comput. Vis. 133(2), 825\u2013843 (2025). https:\/\/doi.org\/10.1007\/s11263-024-02214-4","DOI":"10.1007\/s11263-024-02214-4"},{"key":"3_CR17","unstructured":"Limberg, C., et al.: Leveraging YOLO-World and GPT-4V LMMs for Zero-Shot Person Detection and Action Recognition in Drone Imagery (2024). ArXiv, abs\/2404.01571"},{"key":"3_CR18","doi-asserted-by":"publisher","unstructured":"Lee, J., et al.: Exploring Multimodal Perception in Large Language Models through Perceptual Strength Ratings (2025). https:\/\/doi.org\/10.48550\/arXiv.2503.06980","DOI":"10.48550\/arXiv.2503.06980"},{"key":"3_CR19","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural Inf. Process. Syst. 35, 2482"},{"key":"3_CR20","unstructured":"Long, X., et al.: Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines (2025). 2502.16641v1"},{"key":"3_CR21","doi-asserted-by":"publisher","unstructured":"Jun-Hwa, K., et al.: Multimodal food image classification with large language models. Electronics (2024). https:\/\/doi.org\/10.3390\/electronics13224552","DOI":"10.3390\/electronics13224552"},{"key":"3_CR22","doi-asserted-by":"publisher","unstructured":"Ma, P., et al.: Large language models in food science: Innovations, applications, and future. Trends Food Sci. Technol. (2024). https:\/\/doi.org\/10.1016\/j.tifs.2024.104488","DOI":"10.1016\/j.tifs.2024.104488"},{"key":"3_CR23","doi-asserted-by":"publisher","unstructured":"Chen, G., et al.: LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.02506","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"3_CR24","doi-asserted-by":"publisher","unstructured":"Martinel, N., Foresti, G., Micheloni, C.: Wide-Slice Residual Networks for Food Recognition (2016). https:\/\/doi.org\/10.48550\/arXiv.1612.06543","DOI":"10.48550\/arXiv.1612.06543"},{"key":"3_CR25","unstructured":"Goswami, A.: Deep Dish: Deep Learning for Classifying Food Dishes (2017)"},{"key":"3_CR26","doi-asserted-by":"publisher","unstructured":"Ciocca, G., Micali, G., Napoletano, P.: State recognition of food images using deep features. IEEE Access 8, 32003\u201332017 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2973704","DOI":"10.1109\/ACCESS.2020.2973704"},{"key":"3_CR27","doi-asserted-by":"publisher","unstructured":"Sousa, J., Rebelo, A., Cardoso, J.: Automation of Waste Sorting with Deep Learning (2019). https:\/\/doi.org\/10.1109\/WVC.2019.8876924","DOI":"10.1109\/WVC.2019.8876924"},{"key":"3_CR28","doi-asserted-by":"publisher","unstructured":"Ciocca, G., Napoletano, P., Schettini, R.: Food Recognition and Leftover Estimation for Daily Diet Monitoring (2015). https:\/\/doi.org\/10.1007\/978-3-319-23222-5_41","DOI":"10.1007\/978-3-319-23222-5_41"},{"key":"3_CR29","doi-asserted-by":"publisher","unstructured":"Ciocca, G., Napoletano, P., Schettini, R.: Food Recognition: A New Dataset, Experiments, and Results (2016). https:\/\/doi.org\/10.1109\/JBHI.2016.2636441","DOI":"10.1109\/JBHI.2016.2636441"},{"key":"3_CR30","doi-asserted-by":"publisher","unstructured":"Ma, C., et al.: Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models (2025). https:\/\/doi.org\/10.1007\/978-3-031-72658-3_24","DOI":"10.1007\/978-3-031-72658-3_24"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05179-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T21:43:14Z","timestamp":1757972594000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05179-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032051783","9783032051790"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05179-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"EPIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EPIA Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Faro","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"1 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/epia2025.ualg.pt\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}