{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T17:01:14Z","timestamp":1775667674717,"version":"3.50.1"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032101846","type":"print"},{"value":"9783032101853","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\/978-3-032-10185-3_15","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:48:32Z","timestamp":1767314912000},"page":"181-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SVGauge: Towards Human-Aligned Evaluation for\u00a0SVG Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9439-9867","authenticated-orcid":false,"given":"Leonardo","family":"Zini","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5310-5169","authenticated-orcid":false,"given":"Elia","family":"Frigieri","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3588-6848","authenticated-orcid":false,"given":"Sebastiano","family":"Aloscari","sequence":"additional","affiliation":[]},{"given":"Marcello","family":"Generali","sequence":"additional","affiliation":[]},{"given":"Lorenzo","family":"Dodi","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Dosen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5125-4957","authenticated-orcid":false,"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"15_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 Technical Report. arXiv preprint (2023)"},{"key":"15_CR2","unstructured":"Grattafiori, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint (2024)"},{"key":"15_CR3","unstructured":"Guo, D., et\u00a0al.: Deepseek-r1: incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint (2025)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"15_CR6","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Jain, A., Xie, A., Abbeel, P.: Vectorfusion: text-to-svg by abstracting pixel-based diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Chum, O.: Negative evidences and co-occurrences in image retrieval: the benefit of PCA and whitening. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33709-3_55"},{"key":"15_CR9","unstructured":"Lauren\u00e7on, H., Marafioti, A., Sanh, V., Tronchon, L.: Building and better understanding vision-language models: insights and future directions. arXiv preprint (2024)"},{"key":"15_CR10","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 (2023)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Li, T.M., Luk\u00e1\u010d, M., Gharbi, M., Ragan-Kelley, J.: Differentiable vector graphics rasterization for editing and learning. TOG (2020)","DOI":"10.1145\/3414685.3417871"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: Towards layer-wise image vectorization. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01583"},{"key":"15_CR13","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. TMLR (2024)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Radenovi\u0107, F., Tolias, G., Chum, O.: Fine-tuning cnn image retrieval with no human annotation. IEEE TPAMI (2019)","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"15_CR15","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. arXiv preprint (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Rodriguez, J.A., et al.: Starvector: generating scalable vector graphics code from images and text. In: AAAI (2024)","DOI":"10.1109\/CVPR52734.2025.01508"},{"key":"15_CR18","unstructured":"Team, G.: Gemma. Kaggle (2024)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Wu, R., Su, W., Liao, J.: Chat2SVG: vector graphics generation with large language models and image diffusion models. arXiv preprint (2024)","DOI":"10.1109\/CVPR52734.2025.02206"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Wu, R., Su, W., Ma, K., Liao, J.: IconShop: text-guided vector icon synthesis with autoregressive transformers. TOG (2023)","DOI":"10.1145\/3618364"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Xiao, B., et al.: Florence-2: advancing a unified representation for a variety of vision tasks. In: CVPR (2023)","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"15_CR22","unstructured":"Xing, X., Hu, J., Zhang, J., Xu, D., Yu, Q.: Svgfusion: scalable text-to-svg generation via vector space diffusion. arXiv preprint (2025)"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Xing, X., Hu, J., Zhang, L., Guotao, J., Xu, D., Yu, Q.: Empowering llms to understand and generate complex vector graphics. arXiv preprint (2024)","DOI":"10.1109\/CVPR52734.2025.01815"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Xing, X., Zhou, H., Wang, C., Zhang, J., Xu, D., Yu, Q.: Svgdreamer: text guided svg generation with diffusion model. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00435"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10185-3_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:48:35Z","timestamp":1767314915000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10185-3_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032101846","9783032101853"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10185-3_15","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":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}