{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:16:30Z","timestamp":1785420990155,"version":"3.56.0"},"publisher-location":"Cham","reference-count":83,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729690","type":"print"},{"value":"9783031729706","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-72970-6_15","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:52:23Z","timestamp":1732272743000},"page":"259-276","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":48,"title":["Depicting Beyond Scores: Advancing Image Quality Assessment Through Multi-modal Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8546-3478","authenticated-orcid":false,"given":"Zhiyuan","family":"You","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9078-843X","authenticated-orcid":false,"given":"Zheyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4389-6236","authenticated-orcid":false,"given":"Jinjin","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8666-1103","authenticated-orcid":false,"given":"Zhenfei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5031-6618","authenticated-orcid":false,"given":"Tianfan","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2260-8079","authenticated-orcid":false,"given":"Chao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, H., et al.: Nocaps: novel object captioning at scale. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00904"},{"key":"15_CR2","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Bell, S., Upchurch, P., Snavely, N., Bala, K.: Material recognition in the wild with the materials in context database. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298970"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Bosse, S., Maniry, D., M\u00fcller, K.R., Wiegand, T., Samek, W.: Deep neural networks for no-reference and full-reference image quality assessment. IEEE TIP (2017)","DOI":"10.1109\/PCS.2016.7906376"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Bosse, S., Maniry, D., M\u00fcller, K.R., Wiegand, T., Samek, W.: Deep neural networks for no-reference and full-reference image quality assessment. IEEE TIP (2018)","DOI":"10.1109\/TIP.2017.2760518"},{"key":"15_CR6","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Cao, Y., Wan, Z., Ren, D., Yan, Z., Zuo, W.: Incorporating semi-supervised and positive-unlabeled learning for boosting full reference image quality assessment. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00576"},{"key":"15_CR8","unstructured":"Chen, X., et al.: A comparative study of image restoration networks for general backbone network design. arXiv preprint arXiv:2310.11881 (2023)"},{"key":"15_CR9","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Deep linear array pushbroom image restoration: a degradation pipeline and jitter-aware restoration network. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i2.27892"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., He, Z., Lu, Z., Lu, Z.M.: Prompt-based test-time real image dehazing: a novel pipeline. arXiv preprint arXiv:2309.17389 (2023)","DOI":"10.1007\/978-3-031-73116-7_25"},{"key":"15_CR12","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/vicuna.lmsys.org"},{"key":"15_CR13","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: NeurIPS (2023)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Ding, K., Liu, Y., Zou, X., Wang, S., Ma, K.: Locally adaptive structure and texture similarity for image quality assessment. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475419"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Ding, K., Ma, K., Wang, S., Simoncelli, E.P.: Image quality assessment: unifying structure and texture similarity. IEEE TPAMI (2020)","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Ghildyal, A., Liu, F.: Shift-tolerant perceptual similarity metric. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19797-0_6"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"15_CR18","unstructured":"Gu, J., Cai, H., Chen, H., Ye, X., Ren, J., Dong, C.: Image quality assessment for perceptual image restoration: a new dataset, benchmark and metric. arXiv preprint arXiv:2011.15002 (2020)"},{"key":"15_CR19","unstructured":"Gu, J., Cai, H., Chen, H., Ye, X., Ren, J., Dong, C.: Pipal: a large-scale image quality assessment dataset for perceptual image restoration. arXiv preprint arXiv:2007.12142 (2020)"},{"key":"15_CR20","unstructured":"Hu, E.J., et\u00a0al.: Lora: low-rank adaptation of large language models. In: ICLR (2021)"},{"key":"15_CR21","unstructured":"Huang, S., et\u00a0al.: Language is not all you need: aligning perception with language models. arXiv preprint arXiv:2302.14045 (2023)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., Mittal, A., Moorthy, A.K., Bovik, A.C.: Objective quality assessment of multiply distorted images. In: Asilomar Conference on Signals, Systems and Computers (ASILOMAR) (2012)","DOI":"10.1109\/ACSSC.2012.6489321"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Kang, L., Ye, P., Li, Y., Doermann, D.: Convolutional neural networks for no-reference image quality assessment. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.224"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., Yang, F.: Musiq: multi-scale image quality transformer. In: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Kudo, T., Richardson, J.: Sentencepiece: a simple and language independent subword tokenizer and detokenizer for neural text processing. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-2012"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Larson, E.C., Chandler, D.M.: Most apparent distortion: full-reference image quality assessment and the role of strategy. J. Electron. Imaging (2010)","DOI":"10.1117\/1.3267105"},{"key":"15_CR27","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Lin, H., Hosu, V., Saupe, D.: Kadid-10k: a large-scale artificially distorted IQA database. In: International Conference on Quality of Multimedia Experience (QoMEX) (2019)","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"15_CR30","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Liu, X., van\u00a0de Weijer, J., Bagdanov, A.D.: RankIQA: learning from rankings for no-reference image quality assessment. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.118"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"15_CR33","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: NeurIPS (2022)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Ma, C., Yang, C.Y., Yang, X., Yang, M.H.: Learning a no-reference quality metric for single-image super-resolution. In: Computer Vision and Image Understanding (2017)","DOI":"10.1016\/j.cviu.2016.12.009"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Masry, A., Do, X.L., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. In: ACL Findings (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: A dataset for VQA on document images. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Mittal, A., Moorthy, A.K., Bovik, A.C.: No-reference image quality assessment in the spatial domain. IEEE TIP (2012)","DOI":"10.1109\/ACSSC.2012.6489326"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Mittal, A., Soundararajan, R., Bovik, A.C.: Making a \u201ccompletely blind\u201d image quality analyzer. IEEE Sign. Process. Lett. (2013)","DOI":"10.1109\/LSP.2012.2227726"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Moorthy, A.K., Bovik, A.C.: A two-step framework for constructing blind image quality indices. IEEE Sign. Process. Lett. (2010)","DOI":"10.1109\/LSP.2010.2043888"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Moorthy, A.K., Bovik, A.C.: Blind image quality assessment: from natural scene statistics to perceptual quality. IEEE TIP (2011)","DOI":"10.1109\/TIP.2011.2147325"},{"key":"15_CR41","unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"15_CR42","unstructured":"OpenAI: GPT-4V(ision) system card (2023). https:\/\/openai.com\/research\/gpt-4v-system-card"},{"key":"15_CR43","unstructured":"Ouyang, L., et\u00a0al.: Training language models to follow instructions with human feedback. In: NeurIPS (2022)"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Pan, D., Shi, P., Hou, M., Ying, Z., Fu, S., Zhang, Y.: Blind predicting similar quality map for image quality assessment. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00667"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Ponomarenko, N., et\u00a0al.: Image database TID2013: peculiarities, results and perspectives. Signal Processing: Image Communication (2015)","DOI":"10.1016\/j.image.2014.10.009"},{"key":"15_CR46","unstructured":"Ponomarenko, N., Lukin, V., Zelensky, A., Egiazarian, K., Carli, M., Battisti, F.: TID2008-a database for evaluation of full-reference visual quality assessment metrics. In: Advances of Modern Radioelectronics (2009)"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Prashnani, E., Cai, H., Mostofi, Y., Sen, P.: Pieapp: perceptual image-error assessment through pairwise preference. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00194"},{"key":"15_CR48","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Saad, M.A., Bovik, A.C., Charrier, C.: Blind image quality assessment: a natural scene statistics approach in the DCT domain. IEEE TIP (2012)","DOI":"10.1109\/TIP.2012.2191563"},{"key":"15_CR51","unstructured":"Sheikh, H.: Live image quality assessment database release 2 (2005). http:\/\/live.ece.utexas.edu\/research\/quality"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Sheikh, H.R., Bovik, A.C.: Image information and visual quality. IEEE TIP (2006)","DOI":"10.1109\/TIP.2005.859378"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"15_CR54","doi-asserted-by":"crossref","unstructured":"Su, S., et al.: Blindly assess image quality in the wild guided by a self-adaptive hyper network. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"15_CR55","doi-asserted-by":"crossref","unstructured":"Sun, S., Yu, T., Xu, J., Zhou, W., Chen, Z.: GraphIQA: learning distortion graph representations for blind image quality assessment. IEEE TMM (2022)","DOI":"10.1109\/TMM.2022.3152942"},{"key":"15_CR56","doi-asserted-by":"crossref","unstructured":"Sun, W., Zhou, F., Liao, Q.: MDID: a multiply distorted image database for image quality assessment. PR (2017)","DOI":"10.1016\/j.patcog.2016.07.033"},{"key":"15_CR57","doi-asserted-by":"crossref","unstructured":"Tang, H., Joshi, N., Kapoor, A.: Learning a blind measure of perceptual image quality. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995446"},{"key":"15_CR58","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"15_CR59","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"15_CR60","doi-asserted-by":"crossref","unstructured":"Wang, J., Chan, K.C., Loy, C.C.: Exploring clip for assessing the look and feel of images. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"15_CR61","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE TIP (2004)","DOI":"10.1109\/TIP.2003.819861"},{"key":"15_CR62","unstructured":"Wu, H., et\u00a0al.: Q-bench: a benchmark for general-purpose foundation models on low-level vision. arXiv preprint arXiv:2309.14181 (2023)"},{"key":"15_CR63","doi-asserted-by":"crossref","unstructured":"Wu, H., et\u00a0al.: Q-instruct: improving low-level visual abilities for multi-modality foundation models. arXiv preprint arXiv:2311.06783 (2023)","DOI":"10.1109\/CVPR52733.2024.02408"},{"key":"15_CR64","unstructured":"Wu, H., et\u00a0al.: Q-align: teaching LMMs for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090 (2023)"},{"key":"15_CR65","unstructured":"Wu, H., et\u00a0al.: Towards open-ended visual quality comparison. arXiv preprint arXiv:2402.16641 (2024)"},{"key":"15_CR66","doi-asserted-by":"crossref","unstructured":"Wu, T., Ma, K., Liang, J., Yang, Y., Zhang, L.: A comprehensive study of multimodal large language models for image quality assessment. arXiv preprint arXiv:2403.10854 (2024)","DOI":"10.1007\/978-3-031-72904-1_9"},{"key":"15_CR67","unstructured":"Ye, Q., et\u00a0al.: mPLUG-Owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"15_CR68","doi-asserted-by":"crossref","unstructured":"Yin, G., et al.: Content-variant reference image quality assessment via knowledge distillation. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20221"},{"key":"15_CR69","unstructured":"Yin, Z., et\u00a0al.: LAMM: language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. In: NeurIPS (2023)"},{"key":"15_CR70","unstructured":"You, Z., et al.: Descriptive image quality assessment in the wild. arXiv preprint arXiv:2405.18842 (2024)"},{"key":"15_CR71","doi-asserted-by":"crossref","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. (2014)","DOI":"10.1162\/tacl_a_00166"},{"key":"15_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, L., Mou, X., Zhang, D.: FSIM: a feature similarity index for image quality assessment. IEEE TIP (2011)","DOI":"10.1109\/TIP.2011.2109730"},{"key":"15_CR73","unstructured":"Zhang, P., et al.: Internlm-xcomposer: a vision-language large model for advanced text-image comprehension and composition. arXiv preprint arXiv:2309.15112 (2023)"},{"key":"15_CR74","unstructured":"Zhang, R., et al.: Llama-adapter: efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"},{"key":"15_CR75","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"},{"key":"15_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, W., Li, D., Ma, C., Zhai, G., Yang, X., Ma, K.: Continual learning for blind image quality assessment. IEEE TPAMI (2022)","DOI":"10.1109\/TPAMI.2022.3178874"},{"key":"15_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhai, G., Wei, Y., Yang, X., Ma, K.: Blind image quality assessment via vision-language correspondence: a multitask learning perspective. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"15_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wu, H., Zhang, E., Zhai, G., Lin, W.: A benchmark for multi-modal foundation models on low-level vision: from single images to pairs. arXiv preprint arXiv:2402.07116 (2024)","DOI":"10.1109\/TPAMI.2024.3445770"},{"key":"15_CR79","unstructured":"Zhao, H., et al.: MMICL: empowering vision-language model with multi-modal in-context learning. arXiv preprint arXiv:2309.07915 (2023)"},{"key":"15_CR80","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Zeng, Y., Zha, Z.J., Luo, J.: Learning conditional knowledge distillation for degraded-reference image quality assessment. ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01008"},{"key":"15_CR81","doi-asserted-by":"crossref","unstructured":"Zhou, W., Wang, Z.: Quality assessment of image super-resolution: balancing deterministic and statistical fidelity. In: ACM MM (2022)","DOI":"10.1145\/3503161.3547899"},{"key":"15_CR82","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"15_CR83","doi-asserted-by":"crossref","unstructured":"Zhu, H., Li, L., Wu, J., Dong, W., Shi, G.: MetaIQA: deep meta-learning for no-reference image quality assessment. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01415"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72970-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T11:13:43Z","timestamp":1732274023000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72970-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031729690","9783031729706"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72970-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 November 2024","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":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}