{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T11:15:55Z","timestamp":1750072555301,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"29","license":[{"start":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T00:00:00Z","timestamp":1627084800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T00:00:00Z","timestamp":1627084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2018YFE0203900"],"award-info":[{"award-number":["2018YFE0203900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901083","62001092"],"award-info":[{"award-number":["61901083","62001092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s11042-021-11214-2","type":"journal-article","created":{"date-parts":[[2021,7,24]],"date-time":"2021-07-24T14:02:30Z","timestamp":1627135350000},"page":"42497-42511","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["An explicit self-attention-based multimodality CNN in-loop filter for versatile video coding"],"prefix":"10.1007","volume":"81","author":[{"given":"Menghu","family":"Jia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbo","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9938-0917","authenticated-orcid":false,"given":"Shuai","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mao","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,24]]},"reference":[{"key":"11214_CR1","doi-asserted-by":"publisher","first-page":"11699","DOI":"10.1007\/s11042-019-08572-3","volume":"79","author":"R Birman","year":"2020","unstructured":"Birman R, Segal Y, Hadar O (2020) Overview of research in the field of video compression using deep neural networks. Multimed Tools Appl 79:11699\u201311722","journal-title":"Multimed Tools Appl"},{"unstructured":"Bossen F, Boyce J, Li X, and Seregin V, S\u00fchring K (2018) JVET common test conditions and software reference configurations for SDR video, document JVET-L1010, 12th JVET meeting: Macao, CN, pages 3\u201312","key":"11214_CR2"},{"unstructured":"Bross B, Chen J, Liu S (2018) Versatile Video Coding (Draft 3), document JVET-L1001, Macao, CN, pages 3\u201312","key":"11214_CR3"},{"doi-asserted-by":"crossref","unstructured":"Cavigelli L, Hager P, Benini L (2017) CAS-CNN: A deep convolutional neural network for image compression artifact suppression. 2017 International Joint Conference on Neural Networks (IJCNN), pages 752\u2013759","key":"11214_CR4","DOI":"10.1109\/IJCNN.2017.7965927"},{"doi-asserted-by":"crossref","unstructured":"Dai Y, Liu D, Wu F (2017) A convolutional neural network approach for post-processing in HEVC intra coding. MMM","key":"11214_CR5","DOI":"10.1007\/978-3-319-51811-4_3"},{"doi-asserted-by":"crossref","unstructured":"Ding D, Kong L, Chen G, Liu Z, Fang Y (2020) A switchable deep learning approach for in-loop filtering in video coding. In IEEE Transactions on Circuits and Systems for Video Technology, pages 1871-1887","key":"11214_CR6","DOI":"10.1109\/TCSVT.2019.2935508"},{"doi-asserted-by":"crossref","unstructured":"Dong C, Deng Y, Loy CC, Tang X (2015) Compression Artifacts Reduction by a Deep Convolutional Network. In 2015 IEEE International Conference on Computer Vision (ICCV), pages 576\u2013584","key":"11214_CR7","DOI":"10.1109\/ICCV.2015.73"},{"key":"11214_CR8","doi-asserted-by":"publisher","first-page":"2007","DOI":"10.1007\/s11063-019-10163-0","volume":"51","author":"O ElHarrouss","year":"2019","unstructured":"ElHarrouss O, Almaadeed N, Al-M\u00e1adeed S, Akbari Y (2019) Image Inpainting: a review. Neural Process Lett 51:2007\u20132028","journal-title":"Neural Process Lett"},{"doi-asserted-by":"crossref","unstructured":"Fu C, Alshina E, Alshin A, Huang Y, Chen C, Tsai C, Hsu C, Lei S, Park J, Han W (2012) Sample adaptive offset in the HEVC standard. In IEEE Transactions on Circuits and Systems for Video Technology, pages 1755-1764","key":"11214_CR9","DOI":"10.1109\/TCSVT.2012.2221529"},{"doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770\u2013778","key":"11214_CR10","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity Mappings in Deep Residual Networks. In European Conference on Computer Vision (ECCV), pages 630\u2013645","key":"11214_CR11","DOI":"10.1007\/978-3-319-46493-0_38"},{"doi-asserted-by":"crossref","unstructured":"He X, Hu Q, Han X, Zhang X, Zhang C, Lin W (2018) Enhancing HEVC Compressed Videos with a Partition-Masked Convolutional Neural Network. In 2018 25th IEEE International Conference on Image Processing (ICIP), pages 216\u2013220","key":"11214_CR12","DOI":"10.1109\/ICIP.2018.8451086"},{"doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. In IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 2011-2023","key":"11214_CR13","DOI":"10.1109\/TPAMI.2019.2913372"},{"doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z., Weinberger KQ (2017) Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2261\u20132269","key":"11214_CR14","DOI":"10.1109\/CVPR.2017.243"},{"doi-asserted-by":"crossref","unstructured":"Huang Z, Li Y, Sun J (2020) Multi-Gradient Convolutional Neural Network Based In-Loop Filter For Vvc. In 2020 IEEE International Conference on Multimedia and Expo (ICME), pages 1\u20136","key":"11214_CR15","DOI":"10.1109\/ICME46284.2020.9102826"},{"doi-asserted-by":"crossref","unstructured":"Jia, C., Wang, S., Zhang, X., Wang S, Liu J, Pu S, Ma S (2019) Content-aware convolutional neural network for in-loop filtering in high efficiency video coding. IEEE Transactions on Image Processing, pages 3343-3356","key":"11214_CR16","DOI":"10.1109\/TIP.2019.2896489"},{"doi-asserted-by":"crossref","unstructured":"Kang J, Kim S, Lee KM (2017) Multi-modal\/multi-scale convolutional neural network based in-loop filter design for next generation video codec. In 2017 IEEE International Conference on Image Processing (ICIP), pages 26\u201330","key":"11214_CR17","DOI":"10.1109\/ICIP.2017.8296236"},{"unstructured":"Kingma DP, Ba J (2015). Adam: a method for stochastic optimization. In 2015 international conference on learning representations (ICLR), 2015","key":"11214_CR18"},{"key":"11214_CR19","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Commun ACM 60:84\u201390","journal-title":"Commun ACM"},{"doi-asserted-by":"crossref","unstructured":"Lai P, Wang J (2020) Multi-stage Attention Convolutional Neural Networks for HEVC In-Loop Filtering. In 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), pages 173\u2013177","key":"11214_CR20","DOI":"10.1109\/AICAS48895.2020.9073980"},{"doi-asserted-by":"crossref","unstructured":"Li D, Yu L (2019) An In-Loop Filter Based on Low-Complexity CNN using Residuals in Intra Video Coding. 2019 IEEE International Symposium on Circuits and Systems (ISCAS), pages 1\u20135","key":"11214_CR21","DOI":"10.1109\/ISCAS.2019.8702443"},{"doi-asserted-by":"crossref","unstructured":"Li C, Song L, Xie R, Zhang W (2017) CNN based post-processing to improve HEVC. 2017 IEEE International Conference on Image Processing (ICIP), pages 4577\u20134580","key":"11214_CR22","DOI":"10.1109\/ICIP.2017.8297149"},{"doi-asserted-by":"crossref","unstructured":"Li S, Li W, Cook C, Zhu C, Gao Y. (2018). Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 5457-5466, 2018","key":"11214_CR23","DOI":"10.1109\/CVPR.2018.00572"},{"doi-asserted-by":"crossref","unstructured":"Li S, Li W, Cook C, Zhu C, Gao Y (2019) A fully trainable network with RNN-based pooling. CoRR","key":"11214_CR24","DOI":"10.1016\/j.neucom.2019.02.004"},{"doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X, Yang J (2019) Selective Kernel Networks. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 510\u2013519","key":"11214_CR25","DOI":"10.1109\/CVPR.2019.00060"},{"unstructured":"Ma D, Zhang F, Bull D (2020) BVI-DVC: A Training Database for Deep Video Compression. CoRR","key":"11214_CR26"},{"doi-asserted-by":"crossref","unstructured":"Minaee S, Boykov Y, Porikli F, Plaza A, Kehtarnavaz N, & Terzopoulos D. (2021) Image Segmentation Using Deep Learning: A Survey. IEEE transactions on pattern analysis and machine intelligence","key":"11214_CR27","DOI":"10.1109\/TPAMI.2021.3059968"},{"unstructured":"Mishkin D, Matas J (2016). All you need is a good init. In 2016 international conference on learning representations (ICLR), 2016.","key":"11214_CR28"},{"doi-asserted-by":"crossref","unstructured":"Norkin A, Bj\u00f8ntegaard G, Fuldseth A, Narroschke M, Ikeda M, Andersson K, Zhou M, Auwera G (2012) HEVC Deblocking Filter. In IEEE Transactions on Circuits and Systems for Video Technology, pages 1746-1754","key":"11214_CR29","DOI":"10.1109\/TCSVT.2012.2223053"},{"doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. CoRR","key":"11214_CR30","DOI":"10.1007\/978-3-319-24574-4_28"},{"doi-asserted-by":"crossref","unstructured":"Sullivan G, Ohm J, Han W, Wiegand T (2012) Overview of the high efficiency video coding (HEVC) standard. In IEEE Transactions on Circuits and Systems for Video Technology, pages 1649-1668","key":"11214_CR31","DOI":"10.1109\/TCSVT.2012.2221191"},{"doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1\u20139","key":"11214_CR32","DOI":"10.1109\/CVPR.2015.7298594"},{"doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2818\u20132826","key":"11214_CR33","DOI":"10.1109\/CVPR.2016.308"},{"key":"11214_CR34","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.neunet.2020.07.025","volume":"131","author":"C Tian","year":"2020","unstructured":"Tian C, Fei L, Zheng W, Xu Y, Zuo W, Lin C (2020) Deep learning on image Denoising: an overview. Neural networks: the official journal of the International Neural Network Society 131:251\u2013275","journal-title":"Neural networks: the official journal of the International Neural Network Society"},{"doi-asserted-by":"crossref","unstructured":"Tsai C, Chen C, Yamakage T, Chong I.S, Huang Y, Fu C, Itoh T, Watanabe T, Chujoh T, Karczewicz M, Lei S (2012) Adaptive loop filtering for video coding. In IEEE Journal of Selected Topics in Signal Processing, pages 934-945","key":"11214_CR35","DOI":"10.1109\/JSTSP.2013.2271974"},{"key":"11214_CR36","doi-asserted-by":"publisher","first-page":"2441","DOI":"10.1007\/s11042-020-09231-8","volume":"80","author":"Z Wang","year":"2021","unstructured":"Wang Z, Li F (2021) Convolutional neural network based low complexity HEVC intra encoder. Multimed Tools Appl 80:2441\u20132460","journal-title":"Multimed Tools Appl"},{"doi-asserted-by":"crossref","unstructured":"Wang X, Girshick RB, Gupta A, He K (2018) Non-local Neural Networks. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 7794-7803, 2018.","key":"11214_CR37","DOI":"10.1109\/CVPR.2018.00813"},{"doi-asserted-by":"crossref","unstructured":"Wang M, Wan S, Gong H, Ma M (2019) Attention-based dual-scale CNN in-loop filter for versatile video coding. In IEEE Access 7:145214\u2013145226","key":"11214_CR38","DOI":"10.1109\/ACCESS.2019.2944473"},{"doi-asserted-by":"crossref","unstructured":"Wang Z, Chen J, Hoi S (2020) Deep learning for image super-resolution: a survey. IEEE Trans Pattern Anal Mach Intell","key":"11214_CR39","DOI":"10.1109\/TPAMI.2020.2982166"},{"doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J, Kweon I (2018) CBAM: Convolutional Block Attention Module. ECCV, 2018.","key":"11214_CR40","DOI":"10.1007\/978-3-030-01234-2_1"},{"unstructured":"Yao J and Wang L (2019) CE13\u20132.1. Convolutional Neural Network Filter (CNNF) for Intra Frame, document JVET-N0169, 14th JVET Meeting, Geneva, Switzerland, pages 19\u201327","key":"11214_CR41"},{"doi-asserted-by":"crossref","unstructured":"Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2018) Residual Dense Network for Image Super-Resolution. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 2472-2481","key":"11214_CR42","DOI":"10.1109\/CVPR.2018.00262"},{"doi-asserted-by":"crossref","unstructured":"Zhang Y, Shen T, Ji X, Xiong R, Dai Q (2018) Residual highway convolutional neural networks for in-loop filtering in HEVC. In IEEE Transactions on Image Processing, pages 3827-3841","key":"11214_CR43","DOI":"10.1109\/TIP.2018.2815841"},{"doi-asserted-by":"crossref","unstructured":"Zhang S, Fan Z, Ling N, Jiang M (2020) Recursive residual convolutional neural network- based in-loop filtering for intra frames. In IEEE Transactions on Circuits and Systems for Video Technology, pages 1888-1900","key":"11214_CR44","DOI":"10.1109\/TCSVT.2019.2938192"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11214-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11214-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11214-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,26]],"date-time":"2022-11-26T22:39:42Z","timestamp":1669502382000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11214-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,24]]},"references-count":44,"journal-issue":{"issue":"29","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["11214"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11214-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2021,7,24]]},"assertion":[{"value":"7 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}