{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:09:44Z","timestamp":1772172584277,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031781247","type":"print"},{"value":"9783031781254","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-78125-4_4","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T06:08:28Z","timestamp":1733292508000},"page":"48-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["CLIP-AGIQA: Boosting the\u00a0Performance of\u00a0AI-Generated Image Quality Assessment with\u00a0CLIP"],"prefix":"10.1007","author":[{"given":"Zhenchen","family":"Tang","sequence":"first","affiliation":[]},{"given":"Zichuan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Dong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"4_CR1","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"4_CR2","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.neunet.2021.07.019","volume":"144","author":"S Frolov","year":"2021","unstructured":"Frolov, S., Hinz, T., Raue, F., Hees, J., Dengel, A.: Adversarial text-to-image synthesis: a review. Neural Netw. 144, 187\u2013209 (2021)","journal-title":"Neural Netw."},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Gu, S., Bao, J., Chen, D., Wen, F.: Giqa: generated image quality assessment. arXiv preprint arXiv:2003.08932 (2020)","DOI":"10.1007\/978-3-030-58621-8_22"},{"key":"4_CR4","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"4_CR5","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":"4_CR6","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. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"4_CR7","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. Advances in neural information processing systems 30 (2017)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Hou, J., et al.: Towards transparent deep image aesthetics assessment with tag-based content descriptors. IEEE Trans. Image Process. (2023)","DOI":"10.1109\/TIP.2023.3308852"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Kang, L., Ye, P., Li, Y., Doermann, D.: Convolutional neural networks for no-reference image quality assessment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1733\u20131740 (2014)","DOI":"10.1109\/CVPR.2014.224"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Ke, J., Ye, K., Yu, J., Wu, Y., Milanfar, P., Yang, F.: Vila: learning image aesthetics from user comments with vision-language pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10041\u201310051 (2023)","DOI":"10.1109\/CVPR52729.2023.00968"},{"issue":"3","key":"4_CR11","doi-asserted-by":"publisher","first-page":"3713","DOI":"10.1007\/s11042-022-13428-4","volume":"82","author":"D Khurana","year":"2023","unstructured":"Khurana, D., Koli, A., Khatter, K., Singh, S.: Natural language processing: state of the art, current trends and challenges. Multimed. Tools Appl. 82(3), 3713\u20133744 (2023)","journal-title":"Multimed. Tools Appl."},{"key":"4_CR12","first-page":"36652","volume":"36","author":"Y Kirstain","year":"2023","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation. Adv. Neural. Inf. Process. Syst. 36, 36652\u201336663 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR13","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. arXiv preprint arXiv:2201.03546 (2022)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Agiqa-3k: an open database for ai-generated image quality assessment. IEEE Trans. Circuits Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Liu, X., Van De\u00a0Weijer, J., Bagdanov, A.D.: Rankiqa: learning from rankings for no-reference image quality assessment. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1040\u20131049 (2017)","DOI":"10.1109\/ICCV.2017.118"},{"issue":"12","key":"4_CR16","doi-asserted-by":"publisher","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","volume":"21","author":"A Mittal","year":"2012","unstructured":"Mittal, A., Moorthy, A.K., Bovik, A.C.: No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. 21(12), 4695\u20134708 (2012)","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"4_CR17","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","volume":"20","author":"A Mittal","year":"2012","unstructured":"Mittal, A., Soundararajan, R., Bovik, A.C.: Making a \u201ccompletely blind\u2019\u2019 image quality analyzer. IEEE Signal Process. Lett. 20(3), 209\u2013212 (2012)","journal-title":"IEEE Signal Process. Lett."},{"key":"4_CR18","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"4_CR19","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. Advances in neural information processing systems 29 (2016)"},{"key":"4_CR20","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"2","key":"4_CR21","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1109\/TIP.2011.2166082","volume":"21","author":"R Soundararajan","year":"2011","unstructured":"Soundararajan, R., Bovik, A.C.: Rred indices: reduced reference entropic differencing for image quality assessment. IEEE Trans. Image Process. 21(2), 517\u2013526 (2011)","journal-title":"IEEE Trans. Image Process."},{"key":"4_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"issue":"4","key":"4_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530068","volume":"41","author":"Y Vinker","year":"2022","unstructured":"Vinker, Y., Pajouheshgar, E., Bo, J.Y., Bachmann, R.C., Bermano, A.H., Cohen-Or, D., Zamir, A., Shamir, A.: Clipasso: semantically-aware object sketching. ACM Trans. Graph. (TOG) 41(4), 1\u201311 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Wang, J., Chan, K.C., Loy, C.C.: Exploring clip for assessing the look and feel of images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2555\u20132563 (2023)","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Wang, J., Duan, H., Liu, J., Chen, S., Min, X., Zhai, G.: Aigciqa2023: A large-scale image quality assessment database for ai generated images: from the perspectives of quality, authenticity and correspondence. In: CAAI International Conference on Artificial Intelligence, pp. 46\u201357. Springer (2023)","DOI":"10.1007\/978-981-99-9119-8_5"},{"issue":"4","key":"4_CR26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"4_CR27","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.ins.2016.02.043","volume":"351","author":"J Wu","year":"2016","unstructured":"Wu, J., Lin, W., Shi, G., Li, L., Fang, Y.: Orientation selectivity based visual pattern for reduced-reference image quality assessment. Inf. Sci. 351, 18\u201329 (2016)","journal-title":"Inf. Sci."},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Wu, X., Sun, K., Zhu, F., Zhao, R., Li, H.: Human preference score: Better aligning text-to-image models with human preference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2096\u20132105 (2023)","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"4_CR29","unstructured":"Xu, J., e al.: Imagereward: learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems 36 (2024)"},{"issue":"9","key":"4_CR30","doi-asserted-by":"publisher","first-page":"4444","DOI":"10.1109\/TIP.2016.2585880","volume":"25","author":"J Xu","year":"2016","unstructured":"Xu, J., Ye, P., Li, Q., Du, H., Liu, Y., Doermann, D.: Blind image quality assessment based on high order statistics aggregation. IEEE Trans. Image Process. 25(9), 4444\u20134457 (2016)","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"4_CR31","doi-asserted-by":"publisher","first-page":"4850","DOI":"10.1109\/TIP.2014.2355716","volume":"23","author":"W Xue","year":"2014","unstructured":"Xue, W., Mou, X., Zhang, L., Bovik, A.C., Feng, X.: Blind image quality assessment using joint statistics of gradient magnitude and laplacian features. IEEE Trans. Image Process. 23(11), 4850\u20134862 (2014)","journal-title":"IEEE Trans. Image Process."},{"key":"4_CR32","unstructured":"Yan, J., Li, J., Fu, X.: No-reference quality assessment of contrast-distorted images using contrast enhancement. arXiv preprint arXiv:1904.08879 (2019)"},{"key":"4_CR33","unstructured":"Yuan, J., Cao, X., Li, C., Yang, F., Lin, J., Cao, X.: Pku-i2iqa: an image-to-image quality assessment database for ai generated images. arXiv preprint arXiv:2311.15556 (2023)"},{"key":"4_CR34","unstructured":"Zhang, C., Zhang, C., Zhang, M., Kweon, I.S.: Text-to-image diffusion models in generative ai: a survey. arXiv preprint arXiv:2303.07909 (2023)"},{"issue":"1","key":"4_CR35","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/TCSVT.2018.2886771","volume":"30","author":"W Zhang","year":"2018","unstructured":"Zhang, W., Ma, K., Yan, J., Deng, D., Wang, Z.: Blind image quality assessment using a deep bilinear convolutional neural network. IEEE Trans. Circuits Syst. Video Technol. 30(1), 36\u201347 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4_CR36","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14071\u201314081 (2023)","DOI":"10.1109\/CVPR52729.2023.01352"},{"issue":"9","key":"4_CR37","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78125-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T07:03:55Z","timestamp":1733295835000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78125-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031781247","9783031781254"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78125-4_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}