{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T11:12:45Z","timestamp":1767611565135,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031783463"},{"type":"electronic","value":"9783031783470"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-78347-0_18","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T14:54:10Z","timestamp":1733064850000},"page":"266-282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine Vision-Aware Quality Metrics for\u00a0Compressed Image and\u00a0Video Assessment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3572-6258","authenticated-orcid":false,"given":"Mikhail","family":"Dremin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0605-2214","authenticated-orcid":false,"given":"Konstantin","family":"Kozhemyakov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8294-0770","authenticated-orcid":false,"given":"Ivan","family":"Molodetskikh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Malakhov","family":"Kirill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sagitov","family":"Artur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8893-9340","authenticated-orcid":false,"given":"Dmitriy","family":"Vatolin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"18_CR1","unstructured":"Standards - MPEG-AI. https:\/\/www.mpeg.org\/standards\/MPEG-AI\/"},{"key":"18_CR2","unstructured":"Toward a practical perceptual video quality metric. https:\/\/netflixtechblog.com\/toward-a-practical-perceptual-video-quality-metric-653f208b9652"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"An, X., et\u00a0al.: Partial FC: training 10 million identities on a single machine. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1445\u20131449 (2021)","DOI":"10.1109\/ICCVW54120.2021.00166"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"18_CR5","first-page":"13814","volume":"35","author":"A Antsiferova","year":"2022","unstructured":"Antsiferova, A., Lavrushkin, S., Smirnov, M., Gushchin, A., Vatolin, D., Kulikov, D.: Video compression dataset and benchmark of learning-based video-quality metrics. Adv. Neural. Inf. Process. Syst. 35, 13814\u201313825 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Aqqa, M., Mantini, P., Shah, S.K.: Understanding how video quality affects object detection algorithms. In: VISIGRAPP (5: VISAPP), pp. 96\u2013104 (2019)","DOI":"10.5220\/0007401600002108"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Beniwal, P., Mantini, P., Shah, S.K.: Image quality assessment using deep features for object detection. In: VISIGRAPP (4: VISAPP), pp. 706\u2013714 (2022)","DOI":"10.5220\/0010917000003124"},{"issue":"12","key":"18_CR8","doi-asserted-by":"publisher","first-page":"3064","DOI":"10.1109\/TIFS.2018.2799585","volume":"13","author":"L Best-Rowden","year":"2018","unstructured":"Best-Rowden, L., Jain, A.K.: Learning face image quality from human assessments. IEEE Trans. Inf. Forensics Secur. 13(12), 3064\u20133077 (2018)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol.\u00a01, pp. 886\u2013893. IEEE (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Hernandez-Ortega, J., Galbally, J., Fierrez, J., Haraksim, R., Beslay, L.: FaceQnet: quality assessment for face recognition based on deep learning. In: 2019 International Conference on Biometrics (ICB), pp.\u00a01\u20138. IEEE (2019)","DOI":"10.1109\/ICB45273.2019.8987255"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Kong, L., Ikusan, A., Dai, R., Zhu, J.: Blind image quality prediction for object detection. In: 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pp. 216\u2013221. IEEE (2019)","DOI":"10.1109\/MIPR.2019.00046"},{"issue":"4","key":"18_CR13","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. Vision 129(4), 1238\u20131257 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730\u20133738 (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Min, X., Duan, H., Sun, W., Zhu, Y., Zhai, G.: Perceptual video quality assessment: a survey. arXiv preprint arXiv:2402.03413 (2024)","DOI":"10.1007\/s11432-024-4133-3"},{"issue":"3","key":"18_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":"18_CR18","doi-asserted-by":"crossref","unstructured":"Ou, F.Z., et al.: SDD-FIQA: unsupervised face image quality assessment with similarity distribution distance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7670\u20137679 (2021)","DOI":"10.1109\/CVPR46437.2021.00758"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"O\u2019Byrne, M., Sugrue, M., Kokaram, A., et\u00a0al.: Impact of video compression on the performance of object detection systems for surveillance applications. In: 2022 18th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.\u00a01\u20138. IEEE (2022)","DOI":"10.1109\/AVSS56176.2022.9959476"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Rahman, Q.M., Sunderhauf, N., Dayoub, F.: Per-frame map prediction for continuous performance monitoring of object detection during deployment. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 152\u2013160 (2021)","DOI":"10.1109\/WACVW52041.2021.00021"},{"key":"18_CR21","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Schubert, M., Kahl, K., Rottmann, M.: MetaDetect: uncertainty quantification and prediction quality estimates for object detection. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1\u201310. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9534289"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Terhorst, P., Kolf, J.N., Damer, N., Kirchbuchner, F., Kuijper, A.: SER-FIQ: unsupervised estimation of face image quality based on stochastic embedding robustness. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5651\u20135660 (2020)","DOI":"10.1109\/CVPR42600.2020.00569"},{"issue":"4","key":"18_CR24","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":"18_CR25","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Exploring video quality assessment on user generated contents from aesthetic and technical perspectives. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20144\u201320154 (2023)","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Xu, Z., Yang, W., Meng, A., Lu, N., Huang, H.: Towards end-to-end license plate detection and recognition: a large dataset and baseline. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 255\u2013271 (2018)","DOI":"10.1007\/978-3-030-01261-8_16"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C.C., Tang, X.: Wider face: a face detection benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5525\u20135533 (2016)","DOI":"10.1109\/CVPR.2016.596"},{"issue":"12","key":"18_CR28","doi-asserted-by":"publisher","first-page":"5947","DOI":"10.1109\/tnnls.2018.2817340","volume":"29","author":"Z Yu","year":"2018","unstructured":"Yu, Z., Yu, J., Xiang, C., Fan, J., Tao, D.: Beyond bilinear: generalized multimodal factorized high-order pooling for visual question answering. IEEE Trans. Neural Netw. Learn. Syst. 29(12), 5947\u20135959 (2018). https:\/\/doi.org\/10.1109\/tnnls.2018.2817340","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"18_CR29","first-page":"35549","volume":"35","author":"M Zhao","year":"2022","unstructured":"Zhao, M., et al.: Towards video text visual question answering: benchmark and baseline. Adv. Neural. Inf. Process. Syst. 35, 35549\u201335562 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Zvezdakov, S., Solovyov, A., Vatolin, D.: Iterative machine-learning-based method of selecting encoder parameters for speed-bitrate tradeoff. In: 2022 Data Compression Conference (DCC), p. 01. IEEE (2022)","DOI":"10.1109\/DCC52660.2022.00110"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78347-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T15:03:19Z","timestamp":1733065399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78347-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031783463","9783031783470"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78347-0_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 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"}}]}}