{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:06:53Z","timestamp":1743113213486,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787913"},{"type":"electronic","value":"9789819787920"}],"license":[{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"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\/978-981-97-8792-0_26","type":"book-chapter","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T06:54:45Z","timestamp":1731048885000},"page":"372-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SCAMS: Semantic Category-Aware Multi-scale Network for\u00a0Video Quality Assessment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1996-692X","authenticated-orcid":false,"given":"Longgang","family":"Ren","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6983-9854","authenticated-orcid":false,"given":"Kaibing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5677-4713","authenticated-orcid":false,"given":"Dandan","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8878-0731","authenticated-orcid":false,"given":"Guang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,9]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Li, Y., Meng, S., Zhang, X., Wang, M., Wang, S., Wang, Y., Ma, S.: User-generated video quality assessment: a subjective and objective study. IEEE Trans. Multimed. 154\u2013166 (2021)","key":"26_CR1","DOI":"10.1109\/TMM.2021.3122347"},{"doi-asserted-by":"crossref","unstructured":"Siahaan, E., Hanjalic, A., Redi, J.A.: Semantic-aware blind image quality assessment. Signal Process.: Image Commun. 237\u2013252 (2018)","key":"26_CR2","DOI":"10.1016\/j.image.2017.10.009"},{"doi-asserted-by":"crossref","unstructured":"Li, D., Jiang, T., Jiang, M.: Quality assessment of in-the-wild videos. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 2351\u20132359 (2019)","key":"26_CR3","DOI":"10.1145\/3343031.3351028"},{"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 (CVPR), pp. 770\u2013778 (2016)","key":"26_CR4","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014). arXiv:1406.1078","key":"26_CR5","DOI":"10.3115\/v1\/D14-1179"},{"doi-asserted-by":"crossref","unstructured":"Wu, W., Li, Q., Chen, Z., Liu, S.: Semantic information oriented no-reference video quality assessment. Signal Process. Lett. 204\u2013208 (2021)","key":"26_CR6","DOI":"10.1109\/LSP.2020.3048607"},{"doi-asserted-by":"crossref","unstructured":"Jenni, S., Meishvili, G., Favaro, P.: Video representation learning by recognizing temporal transformations. In: European Conference on Computer Vision (ECCV), pp. 425\u2013442 (2020)","key":"26_CR7","DOI":"10.1007\/978-3-030-58604-1_26"},{"unstructured":"Bai, Y., Fan, H., Misra, I., Venkatesh, G., Lu, Y., Zhou, Y., Yuille, A.: Can temporal information help with contrastive self-supervised learning? (2020). arXiv:2011.13046","key":"26_CR8"},{"doi-asserted-by":"crossref","unstructured":"Saad, M.A., Bovik, A.C., Charrier, C.: Blind prediction of natural video quality. Trans. Image Process. (TIP) 1352\u20131365 (2014)","key":"26_CR9","DOI":"10.1109\/TIP.2014.2299154"},{"doi-asserted-by":"crossref","unstructured":"Xu, J., Ye, P., Liu, Y., Doermann, D.: No-reference video quality assessment via feature learning. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 491\u2013495 (2014)","key":"26_CR10","DOI":"10.1109\/ICIP.2014.7025098"},{"doi-asserted-by":"crossref","unstructured":"Mittal, A., Saad, M.A., Bovik, A.C.: A completely blind video integrity oracle. Trans. Image Process. (TIP) 289\u2013300 (2015)","key":"26_CR11","DOI":"10.1109\/TIP.2015.2502725"},{"doi-asserted-by":"crossref","unstructured":"Ebenezer, J.P., Shang, Z., Wu, Y., Wei, H., Sethuraman, S., Bovik, A.C.: ChipQA: no-reference video quality prediction via space-time chips. Trans. Image Process. (TIP) 8059\u20138074 (2021)","key":"26_CR12","DOI":"10.1109\/TIP.2021.3112055"},{"doi-asserted-by":"crossref","unstructured":"Hosu, V., Hahn, F., Jenadeleh, M., Lin, H., Men, H., Szir\u00e1nyi, T., Saupe, D.: The Konstanz natural video database (KoNViD-1k). In: 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX), pp. 1\u20136 (2017)","key":"26_CR13","DOI":"10.1109\/QoMEX.2017.7965673"},{"doi-asserted-by":"crossref","unstructured":"Seshadrinathan, K., Soundararajan, R., Bovik, A.C., Cormack, L.K.: Study of subjective and objective quality assessment of video. Trans. Image Process. (TIP) 1427\u20131441 (2010)","key":"26_CR14","DOI":"10.1109\/TIP.2010.2042111"},{"doi-asserted-by":"crossref","unstructured":"Mahmoudpour, S., Schelkens, P.: Synthesized view quality assessment using feature matching and superpixel difference. Signal Process. Lett. 1650\u20131654 (2020)","key":"26_CR15","DOI":"10.1109\/LSP.2020.3024109"},{"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 Conference on Computer Vision and Pattern Recognition (CVPR), 1733\u20131740 (2014)","key":"26_CR16","DOI":"10.1109\/CVPR.2014.224"},{"doi-asserted-by":"crossref","unstructured":"Li, D., Jiang, T., Jiang, M.: Unified quality assessment of in-the-wild videos with mixed datasets training. Int. J. Comput. Vis. 1238\u20131257 (2021)","key":"26_CR17","DOI":"10.1007\/s11263-020-01408-w"},{"doi-asserted-by":"crossref","unstructured":"Yi, F., Chen, M., Sun, W., Min, X., Tian, Y., Zhai, G.: Attention based network for no-reference UGC video quality assessment. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 1414\u20131418 (2021)","key":"26_CR18","DOI":"10.1109\/ICIP42928.2021.9506420"},{"doi-asserted-by":"crossref","unstructured":"Yuan, K., Kong, Z., Zheng, C., Sun, M., Wen, X.: Capturing co-existing distortions in user-generated content for no-reference video quality assessment. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1098\u20131107 (2023)","key":"26_CR19","DOI":"10.1145\/3581783.3612023"},{"doi-asserted-by":"crossref","unstructured":"Ying, Z., Mandal, M., Ghadiyaram, D., Bovik, A.: Patch-VG: \u2018patching up\u2019 the video quality problem. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14019\u201314029 (2021)","key":"26_CR20","DOI":"10.1109\/CVPR46437.2021.01380"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Ke, J., Talebi, H., Yim, J. G., Birkbeck, N., Adsumilli, B., Yang, F.: Rich features for perceptual quality assessment of UGC videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13435\u201313444 (2021)","key":"26_CR21","DOI":"10.1109\/CVPR46437.2021.01323"},{"doi-asserted-by":"crossref","unstructured":"Xing, F., Wang, Y.G., Tang, W., Zhu, G., Kwong, S.: StarVQA+: co-training space-time attention for video quality assessment (2023). arXiv:2306.12298","key":"26_CR22","DOI":"10.1109\/ICIP46576.2022.9897881"},{"doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, C., Liao, L., Hou, J., Sun, W., Yan, Q., Lin, W.: DisCovQA: temporal distortion-content transformers for video quality assessment. In: IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) (2023)","key":"26_CR23","DOI":"10.1109\/TCSVT.2023.3249741"},{"doi-asserted-by":"crossref","unstructured":"Li, Z., Yang, L.: DCVQE: a hierarchical transformer for video quality assessment. In: Proceedings of the Asian Conference on Computer Vision (ACCV), pp. 2562\u20132579 (2022)","key":"26_CR24","DOI":"10.1007\/978-3-031-26316-3_24"},{"doi-asserted-by":"crossref","unstructured":"Zhao, K., Yuan, K., Sun, M., Wen, X.: Zoom-VQA: patches, frames and clips integration for video quality assessment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1302\u20131310 (2023)","key":"26_CR25","DOI":"10.1109\/CVPRW59228.2023.00137"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11976\u201311986 (2022)","key":"26_CR26","DOI":"10.1109\/CVPR52688.2022.01167"},{"doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255 (2009)","key":"26_CR27","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video Swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3202\u20133211 (2022)","key":"26_CR28","DOI":"10.1109\/CVPR52688.2022.00320"},{"doi-asserted-by":"crossref","unstructured":"Xiao, C., Liu, M.: Efficient mean-shift clustering using gaussian KD-tree. In: Computer Graphics Forum, vol. 29, no. 7, pp. 2065\u20132073. Blackwell Publishing Ltd., Oxford, UK (2010)","key":"26_CR29","DOI":"10.1111\/j.1467-8659.2010.01793.x"},{"unstructured":"Gunel, B., Du, J., Conneau, A., Stoyanov, V.: Supervised contrastive learning for pre-trained language model fine-tuning (2020). arXiv:2011.01403","key":"26_CR30"},{"doi-asserted-by":"crossref","unstructured":"Tu, Z., Chen, C.J., Wang, Y., Birkbeck, N., Adsumilli, B., Bovik, A.C.: Video quality assessment of user generated content: a benchmark study and a new model. In: 2021 International Conference on Image Processing (ICIP), pp. 1409\u20131413 (2021)","key":"26_CR31","DOI":"10.1109\/ICIP42928.2021.9506189"},{"doi-asserted-by":"crossref","unstructured":"Ye, P., Kumar, J., Kang, L., Doermann, D.: Unsupervised feature learning framework for no-reference image quality assessment. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1098\u20131105 (2012)","key":"26_CR32","DOI":"10.1109\/CVPR.2012.6247789"},{"doi-asserted-by":"crossref","unstructured":"Korhonen, J.: Two-level approach for no-reference consumer video quality assessment. In: IEEE Trans. Image Process. (TIP) 5923\u20135938 (2019)","key":"26_CR33","DOI":"10.1109\/TIP.2019.2923051"},{"doi-asserted-by":"crossref","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. (TIP) 4449\u20134464 (2021)","key":"26_CR34","DOI":"10.1109\/TIP.2021.3072221"},{"doi-asserted-by":"crossref","unstructured":"Chen, P., Li, L., Wu, J., Dong, W., Shi, G. Contrastive self-supervised pre-training for video quality assessment. IEEE Trans. Image Process. (TIP) 458\u2013471 (2021)","key":"26_CR35","DOI":"10.1109\/TIP.2021.3130536"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8792-0_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T07:10:48Z","timestamp":1731049848000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8792-0_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,9]]},"ISBN":["9789819787913","9789819787920"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8792-0_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,9]]},"assertion":[{"value":"9 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}