{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:41:47Z","timestamp":1782333707887,"version":"3.54.5"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031280726","type":"print"},{"value":"9783031280733","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-28073-3_33","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T06:04:47Z","timestamp":1677650687000},"page":"455-473","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Visual Mechanisms Inspired Efficient Transformers for Image and Video Quality Assessment"],"prefix":"10.1007","author":[{"given":"Junyong","family":"You","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"33_CR1","unstructured":"Wang, Z., Sheikh, H.R., Bovik, A.C.: Objective video quality assessment. In: The Handbook of Video Databases: Design and Applications, pp. 1041\u20131078. CRC Press,\u00a0 (2003)"},{"issue":"4","key":"33_CR2","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.image.2008.03.005","volume":"23","author":"PZM Sazaad","year":"2008","unstructured":"Sazaad, P.Z.M., Kawayoke, Y., Horita, Y.: No reference image quality assessment for JPEG2000 based on spatial features. Signal Process. Image Commun. 23(4), 257\u2013268 (2008)","journal-title":"Signal Process. Image Commun."},{"issue":"1","key":"33_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-5281-2014-40","volume":"2014","author":"M Shahid","year":"2014","unstructured":"Shahid, M., Rossholm, A., L\u00f6vstr\u00f6m, B., Zepernick, H.-J.: No-reference image and video quality assessment: a classification and review of recent approaches. EURASIP Journal on Image and Video Processing 2014(1), 1\u201332 (2014). https:\/\/doi.org\/10.1186\/1687-5281-2014-40","journal-title":"EURASIP Journal on Image and Video Processing"},{"issue":"12","key":"33_CR4","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":"33_CR5","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1109\/TIP.2014.2299154","volume":"23","author":"MA Saad","year":"2014","unstructured":"Saad, M.A., Bovik, A.C., Charrier, C.: Blind prediction of natural video quality. IEEE Trans. Image Process. 23(3), 1352\u20131365 (2014)","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"33_CR6","doi-asserted-by":"publisher","first-page":"5923","DOI":"10.1109\/TIP.2019.2923051","volume":"28","author":"J Korhonen","year":"2019","unstructured":"Korhonen, J.: Two-level approach for no-reference consumer video quality assessment. IEEE Trans. Image Process. 28(12), 5923\u20135938 (2019)","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"33_CR7","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/s11760-017-1166-8","volume":"12","author":"S Bianco","year":"2017","unstructured":"Bianco, S., Celona, L., Napoletano, P., Schettini, R.: On the use of deep learning for blind image quality assessment. SIViP 12(2), 355\u2013362 (2017). https:\/\/doi.org\/10.1007\/s11760-017-1166-8","journal-title":"SIViP"},{"key":"33_CR8","doi-asserted-by":"publisher","first-page":"4041","DOI":"10.1109\/TIP.2020.2967829","volume":"29","author":"V Hosu","year":"2020","unstructured":"Hosu, V., Lin, H., Sziranyi, T., Saupe, D.: KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment. IEEE Trans. Image Process. 29, 4041\u20134056 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR9","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/35058500","volume":"2","author":"L Itti","year":"2001","unstructured":"Itti, L., Koch, C.: Computational modelling of visual attention. Nat. Rev. Neurosci. 2, 194\u2013203 (2001)","journal-title":"Nat. Rev. Neurosci."},{"issue":"6","key":"33_CR10","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MSP.2011.942473","volume":"28","author":"U Engelke","year":"2011","unstructured":"Engelke, U., Kaprykowsky, H., Zepernick, H.-J., Ndjiki-Nya, P.: Visual attention in quality assessment. IEEE Signal Process. Mag. 28(6), 50\u201359 (2011)","journal-title":"IEEE Signal Process. Mag."},{"issue":"2","key":"33_CR11","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1080\/713819495","volume":"24","author":"H Kelly","year":"1977","unstructured":"Kelly, H.: Visual contrast sensitivity. Optica Acta: Int. J. Opt. 24(2), 107\u2013112 (1977)","journal-title":"Optica Acta: Int. J. Opt."},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Geisler, W.S.,\u00a0 Perry, J.S.: A real-time foveated multi-resolution system for low-bandwidth video communication. In: SPIE Human Vision Electron. Imaging,\u00a0San Jose, CA, USA, vol. 3299, pp. 294\u2013305\u00a0 (1998)","DOI":"10.1117\/12.320120"},{"issue":"1","key":"33_CR13","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.jvcir.2007.06.001","volume":"19","author":"X Zhang","year":"2007","unstructured":"Zhang, X., Lin, W., Xue, P.: Just-noticeable difference estimation with pixels in images. J. Vis. Commun. 19(1), 30\u201341 (2007)","journal-title":"J. Vis. Commun."},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"You, J.,\u00a0 Korhonen, J.: Transformer for image quality assessment. In: IEEE International Conference on Image Processing\u00a0(ICIP), Anchorage, Alaska, USA (2021)","DOI":"10.1109\/ICIP42928.2021.9506075"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, O., Wang, Y., Milanfar, P., Yang, F.: MUSIQ: Multi-scale image quality transformer. In: IEEE\/CVF\u00a0\u00a0International Conference on Computer Vision\u00a0(ICCV), Virtual (2021)","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"You, J.,\u00a0 Korhonen, J.: Attention integrated hierarchical networks for no-reference image quality assessment. J. Vis. Commun., 82 (2022)","DOI":"10.1016\/j.jvcir.2021.103399"},{"key":"33_CR17","doi-asserted-by":"publisher","first-page":"7414","DOI":"10.1109\/TIP.2020.3002478","volume":"29","author":"J Wu","year":"2020","unstructured":"Wu, J., Ma, J., Liang, F., Dong, W., Shi, G., Lin, W.: End-to-end blind image quality prediction with cascaded deep neural network. IEEE Trans. Image Process. 29, 7414\u20137426 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Su, S., Yan, Q., Zhu, Y., Zhang, C., Ge, X., Sun, J., Zhang, Y.: Blindly assess image quality in the wild guided by a self-adaptive hyper network.\u00a0 In: IEEE Computer Society Conference on Computer Vision and\u00a0Pattern Recogniton\u00a0(CVPR), Virtual (2020)","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R.,\u00a0 Li, F.-F.: Large-scale video classification with convolutional neural networks. In: IEEE Computer Society Conference on Computer Vision and\u00a0Pattern Recogniton\u00a0(CVPR), Columbus, OH, USA (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Varga, D., Szir\u00e1nyi, T.: No-reference video quality assessment via pretrained CNN and LSTM networks. Signal Image Video Proc. 13, 1569\u20131576 (2019)","DOI":"10.1007\/s11760-019-01510-8"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Korhonen, J., Su, Y.,\u00a0 You, J.: Blind natural video quality prediction via statistical temporal features and deep spatial features. In:\u00a0ACM\u00a0 International Conference Multimedia (MM), Seattle, United States (2020)","DOI":"10.1145\/3394171.3413845"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Li, D., Jiang, T., Jiang, M.: Quality assessment of in-the-wild videos. In:\u00a0ACM\u00a0 International Conference Multimedia\u00a0(MM), Nice France (2019)","DOI":"10.1145\/3343031.3351028"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"You, J., Korhonen, J.: Deep neural networks for no-reference video quality assessment. In: IEEE International Conference on Image Processing\u00a0(ICIP), Taipei, Taiwan (2019)","DOI":"10.1109\/ICIP.2019.8803395"},{"key":"33_CR24","doi-asserted-by":"publisher","first-page":"4449","DOI":"10.1109\/TIP.2021.3072221","volume":"30","author":"Z Tu","year":"2021","unstructured":"Tu, Z., Wang, Y., Birkbeck, N., Adsumilli, B., Bovik, A.C.: UGC-VQA: Benchmarking blind video quality assessment for user generated content. IEEE Trans. Image Process. 30, 4449\u20134464 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"You, J.: Long short-term convolutional transformer for no-reference video quality assessment. In:\u00a0ACM\u00a0 International Conference Multimedia (MM),\u00a0Chengdu, China (2021)","DOI":"10.1145\/3474085.3475368"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"G\u00f6ring, S., Skowronek, J., Raake, A.: DeViQ - A deep no reference video quality model. In:\u00a0Proceedings of Human Vision and Electronic Imaging (HVEI), Burlingame, California USA (2018)","DOI":"10.2352\/ISSN.2470-1173.2018.14.HVEI-518"},{"issue":"7","key":"33_CR27","doi-asserted-by":"publisher","first-page":"3329","DOI":"10.1109\/TIP.2016.2568752","volume":"25","author":"X Li","year":"2018","unstructured":"Li, X., Guo, Q., Lu, X.: Spatiotemporal statistics for video quality assessment. IEEE Trans. Image Process. 25(7), 3329\u20133342 (2018)","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"33_CR28","doi-asserted-by":"publisher","first-page":"3500","DOI":"10.1109\/TCSVT.2021.3114509","volume":"32","author":"Y Lu","year":"2021","unstructured":"Lu, Y., Wu, J., Li, L., Dong, W., Zhang, J., Shi, G.: Spatiotemporal representation learning for blind video quality assessment. IEEE Trans. Circuits Syst. Video Technol. 32(6), 3500\u20133513 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"33_CR29","unstructured":"Vaswani, A., et al.: Attention is all your need. In:\u00a0Advance in Neural Information Processing System (NIPS), Long Beach, CA, USA (2017)"},{"key":"33_CR30","unstructured":"Devlin, J., Chang, M.-W., Lee, K.,\u00a0 Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT,\u00a0vol. 1, pp. 4171\u20134186, Minneapolis, Minnesota, USA (2019)"},{"key":"33_CR31","doi-asserted-by":"publisher","unstructured":"Xing, F., Wang, Y-G., Wang, H., Li, L., and Zhu, G.: StarVQA: Space-time attention for video quality assessment. https:\/\/doi.org\/10.48550\/arXiv.2108.09635 (2021)","DOI":"10.48550\/arXiv.2108.09635"},{"key":"33_CR32","unstructured":"Kitaev, N., Kaiser, L.,\u00a0 Levskaya, A.: Reformer: The efficient Transformer. In: International Conference on Learning Representations (ICLR), Virtual (2020)"},{"key":"33_CR33","unstructured":"Zhu, C., et al.: Long-short Transformer: Efficient Transformers for language and vision. In: Advance in Neural Information Processing System (NeurIPS), Virtual (2021)"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer: Hierarchical vision Transformer using shifted windows. In:\u00a0IEEE\/CVF\u00a0\u00a0International Conference on Computer Vision\u00a0(ICCV),\u00a0Virtual (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"33_CR35","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In:\u00a0International Conference on Learning Representations\u00a0(ICLR), Virtual (2021)"},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Fang, Y., Zhu, H., Zeng, Y., Ma, K.,\u00a0 Wang, Z.: Perceptual quality assessment of smartphone photography.\u00a0 In: IEEE Computer Society Conference on Computer Vision and\u00a0Pattern Recogniton\u00a0(CVPR), Virtual (2020)","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Hosu, V., et al.: The Konstanz natural video database (KoNViD-1k). In: International Conference on Quality of Multimedia Experience\u00a0(QoMEX), Erfurt, Germany (2017)","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Inguva, S.,\u00a0 Adsumilli, B.: YouTube UGC dataset for video compression research. In:\u00a0International Workshop on Multimedia Signal Processing\u00a0(MMSP), Kuala Lumpur, Malaysia (2019)","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Ying, Z., Niu, H., Gupta, P., Mahajan, D., Ghadiyaram, D., Bovik A.C.: From patches to pictures (PaQ-2-PiQ): Mapping the perceptual space of picture quality. In: IEEE Computer Society Conference on Computer Vision and\u00a0Pattern Recogniton\u00a0(CVPR), Virtual\u00a0(2020)","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"33_CR40","doi-asserted-by":"publisher","first-page":"3474","DOI":"10.1109\/TIP.2021.3061932","volume":"30","author":"W Zhang","year":"2021","unstructured":"Zhang, W., Ma, K., Zhai, G., Yang, X.: Uncertainty-aware blind image quality assessment in the laboratory and wild. IEEE Trans. Image Process 30, 3474\u20133486 (2021)","journal-title":"IEEE Trans. Image Process"},{"key":"33_CR41","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1007\/s11263-020-01408-w","volume":"129","author":"D Li","year":"2021","unstructured":"Li, D., Jiang, T., Jiang, M.: Unified quality assessment of in-the-wild videos with mixed datasets training. Int. J. Comput. Vis. 129, 1238\u20131257 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"33_CR42","unstructured":"ITU-T Recommendation P.910. Subjective video quality assessment methods for multimedia applications,\u201d ITU (2008)"},{"issue":"1","key":"33_CR43","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1109\/TIP.2014.2378061","volume":"24","author":"T Virtanen","year":"2015","unstructured":"Virtanen, T., Nuutinen, M., Vaahteranoksa, M., Oittinen, P., H\u00e4kkinen, J.: CID2013: A database for evaluating no-reference image quality assessment algorithms. IEEE Trans. Image Process 24(1), 390\u2013402 (2015)","journal-title":"IEEE Trans. Image Process"},{"issue":"1","key":"33_CR44","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1109\/TIP.2015.2500021","volume":"25","author":"D Ghadiyaram","year":"2016","unstructured":"Ghadiyaram, D., Bovik, A.C.: Massive online crowdsourced study of subjective and objective picture quality. IEEE Trans. Image Process 25(1), 372\u2013387 (2016)","journal-title":"IEEE Trans. Image Process"},{"issue":"2","key":"33_CR45","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1109\/TIP.2018.2869673","volume":"28","author":"Z Sinno","year":"2019","unstructured":"Sinno, Z., Bovik, A.C.: Large-scale study of perceptual video quality. IEEE Trans. Image Process. 28(2), 612\u2013627 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR46","unstructured":"\u00a0Jung, A.B., Wada,\u00a0K., Crall,  J., et al.: Imgaug, https:\/\/github.com\/aleju\/imgaug"}],"container-title":["Lecture Notes in Networks and Systems","Advances in Information and Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-28073-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T06:10:51Z","timestamp":1677651051000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-28073-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031280726","9783031280733"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-28073-3_33","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"value":"2367-3370","type":"print"},{"value":"2367-3389","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FICC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Future of Information and Communication Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Francisco, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 March 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 March 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ficc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}