{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T07:10:05Z","timestamp":1748589005593,"version":"3.41.0"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Science and Technology Foundation of Guizhou Province","award":["No. QKHJC-ZK[2024]063"],"award-info":[{"award-number":["No. QKHJC-ZK[2024]063"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62266011"],"award-info":[{"award-number":["No. 62266011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s11760-025-04151-2","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T06:09:50Z","timestamp":1747030190000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DC-HCVQA: a dark channel enhanced human cognitive system based video quality assessment"],"prefix":"10.1007","volume":"19","author":[{"given":"Minjie","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangqian","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyun","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"unstructured":"Series, B.: Methodology for the subjective assessment of the quality of television pictures. Recommendation ITU-R BT 500(13) (2012)","key":"4151_CR1"},{"issue":"4","key":"4151_CR2","doi-asserted-by":"publisher","first-page":"152","DOI":"10.5594\/J11535","volume":"114","author":"F Kozamernik","year":"2005","unstructured":"Kozamernik, F., Steinmann, V., Sunna, P., et al.: SAMVIQ-A new EBU methodology for video quality evaluations in multimedia. SMPTE Motion Imaging J. 114(4), 152\u2013160 (2005)","journal-title":"SMPTE Motion Imaging J."},{"doi-asserted-by":"crossref","unstructured":"Xing, F., Wang, Y.G., Wang, H., et\u00a0al.: StarVQA: Space-time attention for video quality assessment. In: 2022 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 2326\u20132330 (2022)","key":"4151_CR3","DOI":"10.1109\/ICIP46576.2022.9897881"},{"issue":"2","key":"4151_CR4","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1007\/s11063-022-10939-x","volume":"55","author":"Y Tan","year":"2023","unstructured":"Tan, Y., Kong, G., Duan, X., et al.: No-reference video quality assessment based on spatio-temporal perception feature fusion. Neural Process. Lett. 55(2), 1317\u20131335 (2023)","journal-title":"Neural Process. Lett."},{"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":"4151_CR5","DOI":"10.1145\/3343031.3351028"},{"unstructured":"Zhang, A.X., Wang, Y.G., Tang, W., et\u00a0al.: HVS revisited: a comprehensive video quality assessment framework. arXiv preprint arXiv:2210.04158 (2022)","key":"4151_CR6"},{"issue":"4","key":"4151_CR7","doi-asserted-by":"publisher","first-page":"043029","DOI":"10.1117\/1.JEI.33.4.043029","volume":"33","author":"Z Zhou","year":"2024","unstructured":"Zhou, Z., Kong, G., Duan, X., et al.: No-reference video quality assessment based on human visual perception. J. Electron. Imaging 33(4), 043029\u2013043029 (2024)","journal-title":"J. Electron. Imaging"},{"unstructured":"Wang, X., Katsenou, A., Bull, D.: Relax-VQA: Residual fragment and layer stack extraction for enhancing video quality assessment. arXiv preprint arXiv:2407.11496 (2024)","key":"4151_CR8"},{"key":"4151_CR9","doi-asserted-by":"publisher","first-page":"1137006","DOI":"10.3389\/frsip.2023.1137006","volume":"3","author":"J Ke","year":"2023","unstructured":"Ke, J., Zhang, T., Wang, Y., et al.: MRET: multi-resolution transformer for video quality assessment. Front. Signal Process. 3, 1137006 (2023)","journal-title":"Front. Signal Process."},{"doi-asserted-by":"crossref","unstructured":"Mi, Y., Shu, Y., Li, Y., et\u00a0al.: CLiF-VQA: Enhancing video quality assessment by incorporating high-level semantic information related to human feelings. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 9989\u20139998 (2024)","key":"4151_CR10","DOI":"10.1145\/3664647.3680930"},{"issue":"4","key":"4151_CR11","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/JSTSP.2022.3174338","volume":"16","author":"W Zhou","year":"2022","unstructured":"Zhou, W., Yang, E., Lei, J., et al.: FRNet: feature reconstruction network for RGB-D indoor scene parsing. IEEE J. Sel. Top. Signal Process. 16(4), 677\u2013687 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"1","key":"4151_CR12","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s00371-023-02773-6","volume":"40","author":"Y Cai","year":"2024","unstructured":"Cai, Y., Zhou, W., Zhang, L., et al.: DHFNet: dual-decoding hierarchical fusion network for RGB-thermal semantic segmentation. Vis. Comput. 40(1), 169\u2013179 (2024)","journal-title":"Vis. Comput."},{"key":"4151_CR13","doi-asserted-by":"publisher","first-page":"3483","DOI":"10.1109\/TMM.2022.3161852","volume":"25","author":"W Zhou","year":"2022","unstructured":"Zhou, W., Yang, E., Lei, J., et al.: PGDENet: progressive guided fusion and depth enhancement network for RGB-D indoor scene parsing. IEEE Trans. Multimed. 25, 3483\u20133494 (2022)","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"4151_CR14","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/TIV.2022.3164899","volume":"8","author":"W Zhou","year":"2022","unstructured":"Zhou, W., Dong, S., Lei, J., et al.: MTANet: multitask-aware network with hierarchical multimodal fusion for RGB-T urban scene understanding. IEEE Trans. Intell. Veh. 8(1), 48\u201358 (2022)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"4151_CR15","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1109\/TMM.2021.3086618","volume":"24","author":"W Zhou","year":"2021","unstructured":"Zhou, W., Lin, X., Lei, J., et al.: Mffenet: multiscale feature fusion and enhancement network for RGB-thermal urban road scene parsing. IEEE Trans. Multimed. 24, 2526\u20132538 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"4151_CR16","doi-asserted-by":"publisher","first-page":"107766","DOI":"10.1016\/j.sigpro.2020.107766","volume":"178","author":"J Wu","year":"2021","unstructured":"Wu, J., Zhou, W., Luo, T., et al.: Multiscale multilevel context and multimodal fusion for RGB-D salient object detection. Signal Process. 178, 107766 (2021)","journal-title":"Signal Process."},{"issue":"4","key":"4151_CR17","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1109\/JSTSP.2022.3159032","volume":"16","author":"W Zhou","year":"2022","unstructured":"Zhou, W., Jin, J., Lei, J., et al.: CIMFNet: cross-layer interaction and multiscale fusion network for semantic segmentation of high-resolution remote sensing images. IEEE J. Sel. Top. Signal Process. 16(4), 666\u2013676 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"4","key":"4151_CR18","doi-asserted-by":"publisher","first-page":"3222","DOI":"10.1109\/TCSVT.2024.3508058","volume":"35","author":"W Zhou","year":"2024","unstructured":"Zhou, W., Wu, H., Jiang, Q.: MDNet: mamba-effective diffusion-distillation network for RGB-thermal urban dense prediction. IEEE Trans. Circuits Syst. Video Technol. 35(4), 3222\u20133233 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4151_CR19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3537281","author":"W Zhou","year":"2025","unstructured":"Zhou, W., Jian, B., Liu, Y.: Feature contrast difference and enhanced network for RGB-D indoor scene classification in internet of things. IEEE Internet Things J. (2025). https:\/\/doi.org\/10.1109\/JIOT.2025.3537281","journal-title":"IEEE Internet Things J."},{"issue":"6","key":"4151_CR20","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1109\/TPAMI.2012.213","volume":"35","author":"K He","year":"2012","unstructured":"He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35(6), 1397\u20131409 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Dong, Y., Liu, X., Gao, Y., et\u00a0al.: Light-VQA: a multi-dimensional quality assessment model for low-light video enhancement. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1088\u20131097, (2023)","key":"4151_CR21","DOI":"10.1145\/3581783.3611923"},{"doi-asserted-by":"crossref","unstructured":"Pan, J., Sun, D., Pfister, H., et\u00a0al.: Blind image deblurring using dark channel prior. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1628\u20131636, (2016)","key":"4151_CR22","DOI":"10.1109\/CVPR.2016.180"},{"doi-asserted-by":"crossref","unstructured":"Jiang, X., Yao, H., Zhang, S., et\u00a0al.: Night video enhancement using improved dark channel prior. In: 2013 IEEE International Conference on Image Processing, IEEE, pp. 553\u2013557, (2013)","key":"4151_CR23","DOI":"10.1109\/ICIP.2013.6738114"},{"issue":"6","key":"4151_CR24","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1109\/TIP.2018.2813092","volume":"27","author":"YT Peng","year":"2018","unstructured":"Peng, Y.T., Cao, K., Cosman, P.C.: Generalization of the dark channel prior for single image restoration. IEEE Trans. Image Process. 27(6), 2856\u20132868 (2018)","journal-title":"IEEE Trans. Image Process."},{"doi-asserted-by":"crossref","unstructured":"Hosu, V., Hahn, F., Jenadeleh, M., et\u00a0al.: The Konstanz natural video database (KoNViD-1k). In: 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX), IEEE, pp. 1\u20136, (2017)","key":"4151_CR25","DOI":"10.1109\/QoMEX.2017.7965673"},{"issue":"2","key":"4151_CR26","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1109\/TIP.2018.2869673","volume":"28","author":"Z Sinno","year":"2018","unstructured":"Sinno, Z., Bovik, A.C.: Large-scale study of perceptual video quality. IEEE Trans. Image Process. 28(2), 612\u2013627 (2018)","journal-title":"IEEE Trans. Image Process."},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Inguva, S., Adsumilli, B.: Youtube UGC dataset for video compression research. In: 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP), IEEE, pp. 1\u20135, (2019)","key":"4151_CR27","DOI":"10.1109\/MMSP.2019.8901772"},{"doi-asserted-by":"crossref","unstructured":"Ying, Z., Mandal, M., Ghadiyaram, D., et\u00a0al.: Patch-VQ:\u2019patching up\u2019the video quality problem. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14019\u201314029, (2021)","key":"4151_CR28","DOI":"10.1109\/CVPR46437.2021.01380"},{"doi-asserted-by":"crossref","unstructured":"Wu, H., Zhang, E., Liao, L., et\u00a0al.: 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)","key":"4151_CR29","DOI":"10.1109\/ICCV51070.2023.01843"},{"issue":"3","key":"4151_CR30","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 completely blind image quality analyzer. IEEE Signal Process. Lett. 20(3), 209\u2013212 (2012)","journal-title":"IEEE Signal Process. Lett."},{"issue":"12","key":"4151_CR31","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."},{"doi-asserted-by":"crossref","unstructured":"Ye, P., Kumar, J., Kang, L., et\u00a0al.: Unsupervised feature learning framework for no-reference image quality assessment. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 1098\u20131105, (2012)","key":"4151_CR32","DOI":"10.1109\/CVPR.2012.6247789"},{"issue":"12","key":"4151_CR33","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."},{"doi-asserted-by":"crossref","unstructured":"You, J., Korhonen, J.: Deep neural networks for no-reference video quality assessment. In: 2019 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 2349\u20132353, (2019)","key":"4151_CR34","DOI":"10.1109\/ICIP.2019.8803395"},{"issue":"4","key":"4151_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3632178","volume":"20","author":"A Telili","year":"2023","unstructured":"Telili, A., Fezza, S.A., Hamidouche, W., et al.: 2bivqa: double bi-LSTM-based video quality assessment of UGC videos. ACM Trans. Multimed. Comput. Commun. Appl. 20(4), 1\u201322 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"doi-asserted-by":"crossref","unstructured":"Sun, W., Min, X., Lu, W., et\u00a0al.: A deep learning based no-reference quality assessment model for UGC videos. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 856\u2013865, (2022)","key":"4151_CR36","DOI":"10.1145\/3503161.3548329"},{"unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. Advances in neural information processing systems 30, (2017)","key":"4151_CR37"},{"doi-asserted-by":"crossref","unstructured":"You, J.: Long short-term convolutional transformer for no-reference video quality assessment. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2112\u20132120, (2021)","key":"4151_CR38","DOI":"10.1145\/3474085.3475368"},{"doi-asserted-by":"crossref","unstructured":"Wu, H., Chen, C., Hou, J., et\u00a0al.: Fast-VQA: efficient end-to-end video quality assessment with fragment sampling. In: European Conference on Computer Vision, Springer, pp. 538\u2013554, (2022)","key":"4151_CR39","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"4151_CR40","first-page":"56979","volume":"36","author":"T Toosi","year":"2023","unstructured":"Toosi, T., Issa, E.: Brain-like flexible visual inference by harnessing feedback feedforward alignment. Adv. Neural. Inf. Process. Syst. 36, 56979\u201356997 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4151_CR41","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.neunet.2022.04.003","volume":"152","author":"E Ben-Iwhiwhu","year":"2022","unstructured":"Ben-Iwhiwhu, E., Dick, J., Ketz, N.A., et al.: Context meta-reinforcement learning via neuromodulation. Neural Netw. 152, 70\u201379 (2022)","journal-title":"Neural Netw."},{"issue":"1","key":"4151_CR42","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1146\/annurev-neuro-092021-125059","volume":"45","author":"CD Grossman","year":"2022","unstructured":"Grossman, C.D., Cohen, J.Y.: Neuromodulation and neurophysiology on the timescale of learning and decision-making. Annu. Rev. Neurosci. 45(1), 317\u2013337 (2022)","journal-title":"Annu. Rev. Neurosci."},{"unstructured":"Chen, Z., Qing, J., Zhou, J.H.: Cinematic mindscapes: high-quality video reconstruction from brain activity. Advances in Neural Information Processing Systems 36, (2024)","key":"4151_CR43"},{"unstructured":"Yang, H., Gee, J., Shi, J.: Memory encoding model. arXiv preprint arXiv:2308.01175, (2023)","key":"4151_CR44"},{"unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929,(2020)","key":"4151_CR45"},{"issue":"8","key":"4151_CR46","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1007\/s11760-019-01510-8","volume":"13","author":"D Varga","year":"2019","unstructured":"Varga, D., Szir\u00e1nyi, T.: No-reference video quality assessment via pretrained CNN and LSTM networks. SIViP 13(8), 1569\u20131576 (2019)","journal-title":"SIViP"},{"doi-asserted-by":"crossref","unstructured":"Graves, A., Graves, A.: Long short-term memory. Supervised sequence labelling with recurrent neural networks pp. 37\u201345 , (2012)","key":"4151_CR47","DOI":"10.1007\/978-3-642-24797-2_4"},{"doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Gulcehre, C., et\u00a0al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","key":"4151_CR48","DOI":"10.3115\/v1\/D14-1179"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Cao, Y., Zha, Z.J., et\u00a0al.: Deep degradation prior for low-quality image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11049\u201311058, (2020)","key":"4151_CR49","DOI":"10.1109\/CVPR42600.2020.01106"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Lin, Y., et\u00a0al.: Swin transformer v2: Scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009\u201312019, (2022)","key":"4151_CR50","DOI":"10.1109\/CVPR52688.2022.01170"},{"doi-asserted-by":"crossref","unstructured":"Li, B., Zhang, W., Tian, M., et al.: Blindly assess quality of in-the-wild videos via quality-aware pre-training and motion perception. IEEE Trans. Circuits Syst. Video Technol. 32(9), 5944\u20135958 (2022)","key":"4151_CR51","DOI":"10.1109\/TCSVT.2022.3164467"},{"doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., et\u00a0al.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211, (2019)","key":"4151_CR52","DOI":"10.1109\/ICCV.2019.00630"},{"doi-asserted-by":"crossref","unstructured":"Mi, Y., Shu, Y., Li, Y., et\u00a0al.: Clif-VQA: enhancing video quality assessment by incorporating high-level semantic information related to human feelings. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 9989\u20139998, (2024)","key":"4151_CR53","DOI":"10.1145\/3664647.3680930"},{"unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, PmLR, pp 8748\u20138763 (2021)","key":"4151_CR54"},{"unstructured":"Zhou, X., Liu, X., Dong, Y., et\u00a0al.: Light-VQA+: a video quality assessment model for exposure correction with vision-language guidance. arXiv preprint arXiv:2405.03333 (2024)","key":"4151_CR55"},{"doi-asserted-by":"crossref","unstructured":"Wen, W., Li, M., Zhang, Y., et\u00a0al.: Modular blind video quality assessment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2763\u20132772, (2024)","key":"4151_CR56","DOI":"10.1109\/CVPR52733.2024.00267"},{"issue":"5","key":"4151_CR57","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1037\/h0020071","volume":"80","author":"E Tulving","year":"1973","unstructured":"Tulving, E., Thomson, D.M.: Encoding specificity and retrieval processes in episodic memory. Psychol. Rev. 80(5), 352 (1973)","journal-title":"Psychol. Rev."},{"issue":"4","key":"4151_CR58","first-page":"281","volume":"7","author":"JL Kolodner","year":"1983","unstructured":"Kolodner, J.L.: Reconstructive memory: a computer model. Cogn. Sci. 7(4), 281\u2013328 (1983)","journal-title":"Cogn. Sci."},{"issue":"2","key":"4151_CR59","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.tics.2007.11.004","volume":"12","author":"CA Kurby","year":"2008","unstructured":"Kurby, C.A., Zacks, J.M.: Segmentation in the perception and memory of events. Trends Cogn. Sci. 12(2), 72\u201379 (2008)","journal-title":"Trends Cogn. Sci."},{"issue":"1","key":"4151_CR60","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1146\/annurev-psych-122414-033400","volume":"68","author":"T Moore","year":"2017","unstructured":"Moore, T., Zirnsak, M.: Neural mechanisms of selective visual attention. Annu. Rev. Psychol. 68(1), 47\u201372 (2017)","journal-title":"Annu. Rev. Psychol."},{"key":"4151_CR61","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., et al.: 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":"4151_CR62","doi-asserted-by":"publisher","first-page":"4840","DOI":"10.1109\/TCSVT.2023.3249741","volume":"33","author":"H Wu","year":"2023","unstructured":"Wu, H., Chen, C., Liao, L., et al.: DisCoVQA: temporal distortion-content transformers for video quality assessment. IEEE Trans. Circuits Syst. Video Technol. 33, 4840\u20134854 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"doi-asserted-by":"crossref","unstructured":"Zhao, K., Yuan, K., Sun, M., et\u00a0al.: Zoom-VQA: Patches, frames and clips integration for video quality assessment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1302\u20131310, (2023)","key":"4151_CR63","DOI":"10.1109\/CVPRW59228.2023.00137"},{"doi-asserted-by":"crossref","unstructured":"Mitra, S., Soundararajan, R.: Knowledge guided semi-supervised learning for quality assessment of user generated videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4251\u20134260,(2024)","key":"4151_CR64","DOI":"10.1609\/aaai.v38i5.28221"},{"doi-asserted-by":"crossref","unstructured":"Yuan, K., Liu, H., Li, M., et\u00a0al.: PTM-VQA: efficient video quality assessment leveraging diverse pretrained models from the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2835\u20132845 (2024)","key":"4151_CR65","DOI":"10.1109\/CVPR52733.2024.00274"},{"issue":"11","key":"4151_CR66","doi-asserted-by":"publisher","first-page":"7056","DOI":"10.1109\/TPAMI.2024.3385364","volume":"46","author":"W Sun","year":"2024","unstructured":"Sun, W., Wen, W., Min, X., et al.: Analysis of video quality datasets via design of minimalistic video quality models. IEEE Trans. Pattern Anal. Mach. Intell. 46(11), 7056\u20137071 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., Quan, Y., Xiao, G., et\u00a0al.: Scaling and masking: A new paradigm of data sampling for image and video quality assessment. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3792\u20133801 (2024)","key":"4151_CR67","DOI":"10.1609\/aaai.v38i4.28170"},{"unstructured":"Wu, H., Zhang, Z., Zhang, W., et\u00a0al.: Q-align: Teaching LMMS for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090 (2023)","key":"4151_CR68"},{"key":"4151_CR69","doi-asserted-by":"publisher","first-page":"127633","DOI":"10.1016\/j.neucom.2024.127633","volume":"586","author":"R Li","year":"2024","unstructured":"Li, R., Wang, W., Hu, H., et al.: Ultrahigh-definition video quality assessment: a new dataset and benchmark. Neurocomputing 586, 127633 (2024)","journal-title":"Neurocomputing"},{"unstructured":"Kay, W., Carreira, J., Simonyan,K., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)","key":"4151_CR70"},{"doi-asserted-by":"crossref","unstructured":"Lu, Y., Li, X., Pei, Y., et\u00a0al.: KVQ: Kwai video quality assessment for short-form videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 25963\u201325973 (2024)","key":"4151_CR71","DOI":"10.1109\/CVPR52733.2024.02453"},{"doi-asserted-by":"crossref","unstructured":"Wu, H., Zhang, E., Liao, L., et\u00a0al.: Towards explainable in-the-wild video quality assessment: a database and a language-prompted approach. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1045\u20131054 (2023)","key":"4151_CR72","DOI":"10.1145\/3581783.3611737"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04151-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04151-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04151-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T06:40:13Z","timestamp":1748587213000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04151-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,12]]},"references-count":72,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["4151"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04151-2","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,5,12]]},"assertion":[{"value":"12 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain studies with human participants or animals. Statement of informed consent is not applicable since the manuscript does not contain any patient data.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"566"}}