{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:48:22Z","timestamp":1786981702626,"version":"build-2736575974"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2021,8,13]],"date-time":"2021-08-13T00:00:00Z","timestamp":1628812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,13]],"date-time":"2021-08-13T00:00:00Z","timestamp":1628812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1007\/s11263-021-01505-4","type":"journal-article","created":{"date-parts":[[2021,8,13]],"date-time":"2021-08-13T04:03:03Z","timestamp":1628827383000},"page":"2889-2906","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Just Recognizable Distortion for Machine Vision Oriented Image and Video Coding"],"prefix":"10.1007","volume":"129","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1189-8755","authenticated-orcid":false,"given":"Qi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinfeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siwei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,8,13]]},"reference":[{"key":"1505_CR1","doi-asserted-by":"crossref","unstructured":"Aqqa, M., Mantini, P., & Shah, S. K. (2019). Understanding how video quality affects object detection algorithms. In VISIGRAPP (5: VISAPP) (pp. 96\u2013104).","DOI":"10.5220\/0007401600960104"},{"key":"1505_CR2","unstructured":"Bross, B., Chen, J., & Liu, S. (2018). Versatile video coding (draft 5). JVET-K1001."},{"key":"1505_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Murherjee, D., Han, J., Grange, A., Xu, Y., Liu, Z., Parker, S., Chen, C., Su, H., Joshi, U., & Chiang, C. H. (2018). An overview of core coding tools in the av1 video codec. In 2018 picture coding symposium (PCS) (pp. 41\u201345). IEEE.","DOI":"10.1109\/PCS.2018.8456249"},{"key":"1505_CR4","doi-asserted-by":"publisher","first-page":"2230","DOI":"10.1109\/TIP.2019.2941660","volume":"29","author":"Z Chen","year":"2019","unstructured":"Chen, Z., Fan, K., Wang, S., Duan, L., Lin, W., & Kot, A. C. (2019). Toward intelligent sensing: Intermediate deep feature compression. IEEE Transactions on Image Processing, 29, 2230\u20132243.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"6","key":"1505_CR5","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1109\/76.475889","volume":"5","author":"CH Chou","year":"1995","unstructured":"Chou, C. H., & Li, Y. C. (1995). A perceptually tuned subband image coder based on the measure of just-noticeable-distortion profile. IEEE Transactions on Circuits and Systems for Video Technology, 5(6), 467\u2013476.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1505_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (pp. 248\u2013255). IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1505_CR7","doi-asserted-by":"crossref","unstructured":"Dodge, S., & Karam, L. (2016). Understanding how image quality affects deep neural networks. In 2016 eighth international conference on quality of multimedia experience (QoMEX) (pp. 1\u20136), IEEE.","DOI":"10.1109\/QoMEX.2016.7498955"},{"key":"1505_CR8","doi-asserted-by":"crossref","unstructured":"Dodge, S., & Karam, L. (2017). A study and comparison of human and deep learning recognition performance under visual distortions. In 2017 26th international conference on computer communication and networks (ICCCN) (pp 1\u20137). IEEE.","DOI":"10.1109\/ICCCN.2017.8038465"},{"issue":"1","key":"1505_CR9","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1109\/TIP.2015.2500034","volume":"25","author":"LY Duan","year":"2015","unstructured":"Duan, L. Y., Chandrasekhar, V., Chen, J., Lin, J., Wang, Z., Huang, T., et al. (2015). Overview of the mpeg-cdvs standard. IEEE Transactions on Image Processing, 25(1), 179\u2013194.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"2","key":"1505_CR10","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/MMUL.2018.2873844","volume":"26","author":"LY Duan","year":"2018","unstructured":"Duan, L. Y., Lou, Y., Bai, Y., Huang, T., Gao, W., Chandrasekhar, V., et al. (2018). Compact descriptors for video analysis: The emerging mpeg standard. IEEE MultiMedia, 26(2), 44\u201354.","journal-title":"IEEE MultiMedia"},{"issue":"2","key":"1505_CR11","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"1505_CR12","doi-asserted-by":"crossref","unstructured":"Fan, C., Lin, H., Hosu, V., Zhang, Y., Jiang, Q., Hamzaoui, R., & Saupe, D. (2019). Sur-net: Predicting the satisfied user ratio curve for image compression with deep learning. In 2019 eleventh international conference on quality of multimedia experience (QoMEX) (pp. 1\u20136), IEEE.","DOI":"10.1109\/QoMEX.2019.8743204"},{"key":"1505_CR13","first-page":"7538","volume":"31","author":"R Geirhos","year":"2018","unstructured":"Geirhos, R., Temme, C. R., Rauber, J., Sch\u00fctt, H. H., Bethge, M., & Wichmann, F. A. (2018). Generalisation in humans and deep neural networks. Advances in Neural Information Processing Systems, 31, 7538\u20137550.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1505_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1505_CR15","unstructured":"Hu, T., Qi, H., Huang, Q., & Lu, Y. (2019). See better before looking closer: Weakly supervised data augmentation network for fine-grained visual classification. arXiv preprint arXiv:1901.09891."},{"key":"1505_CR16","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017a). Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700\u20134708).","DOI":"10.1109\/CVPR.2017.243"},{"key":"1505_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Q., Wang, H., Lim, S. C., Kim, H. Y., Jeong, S. Y., & Kuo, C. C. J. (2017b). Measure and prediction of hevc perceptually lossy\/lossless boundary qp values. In: 2017 data compression conference (DCC) (pp. 42\u201351). IEEE.","DOI":"10.1109\/DCC.2017.17"},{"issue":"10","key":"1505_CR18","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1109\/5.241504","volume":"81","author":"N Jayant","year":"1993","unstructured":"Jayant, N., Johnston, J., & Safranek, R. (1993). Signal compression based on models of human perception. Proceedings of the IEEE, 81(10), 1385\u20131422.","journal-title":"Proceedings of the IEEE"},{"issue":"13","key":"1505_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2352\/ISSN.2470-1173.2016.13.IQSP-222","volume":"2016","author":"L Jin","year":"2016","unstructured":"Jin, L., Lin, J. Y., Hu, S., Wang, H., Wang, P., Katsavounidis, I., et al. (2016). Statistical study on perceived jpeg image quality via mcl-jci dataset construction and analysis. Electronic Imaging, 2016(13), 1\u20139.","journal-title":"Electronic Imaging"},{"key":"1505_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Jia, C., Wang, S., Zhang, X., Wang, S., Ma, S., & Gao, W. (2018). Joint rate-distortion optimization for simultaneous texture and deep feature compression of facial images. In 2018 IEEE fourth international conference on multimedia big data (BigMM) (pp 1\u20135). IEEE.","DOI":"10.1109\/BigMM.2018.8499170"},{"key":"1505_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41233-020-00034-1","volume":"5","author":"H Lin","year":"2020","unstructured":"Lin, H., Hosu, V., Fan, C., Zhang, Y., Mu, Y., Hamzaoui, R., et al. (2020). Sur-featnet: Predicting the satisfied user ratio curve for image compression with deep feature learning. Quality and User Experience, 5, 1\u201323.","journal-title":"Quality and User Experience"},{"key":"1505_CR22","doi-asserted-by":"crossref","unstructured":"Lin, J. Y., Jin, L., Hu, S., Katsavounidis, I., Li, Z., Aaron, A., & Kuo, C. C. J. (2015). Experimental design and analysis of jnd test on coded image\/video. In Applications of digital image processing XXXVIII, International Society for optics and photonics (Vol. 9599, p. 95990Z).","DOI":"10.1117\/12.2188389"},{"key":"1505_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"1","key":"1505_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11220-016-0152-5","volume":"18","author":"D Liu","year":"2017","unstructured":"Liu, D., Wang, D., & Li, H. (2017). Recognizable or not: Towards image semantic quality assessment for compression. Sensing and Imaging, 18(1), 1.","journal-title":"Sensing and Imaging"},{"key":"1505_CR25","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1109\/TIP.2019.2933743","volume":"29","author":"H Liu","year":"2019","unstructured":"Liu, H., Zhang, Y., Zhang, H., Fan, C., Kwong, S., Kuo, C. C. J., et al. (2019). Deep learning-based picture-wise just noticeable distortion prediction model for image compression. IEEE Transactions on Image Processing, 29, 641\u2013656.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"7","key":"1505_CR26","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/JSAC.2019.2916488","volume":"37","author":"Y Lou","year":"2019","unstructured":"Lou, Y., Duan, L. Y., Wang, S., Chen, Z., Bai, Y., Chen, C., et al. (2019). Front-end smart visual sensing and back-end intelligent analysis: A unified infrastructure for economizing the visual system of city brain. IEEE Journal on Selected Areas in Communications, 37(7), 1489\u20131503.","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"10","key":"1505_CR27","doi-asserted-by":"publisher","first-page":"3095","DOI":"10.1109\/TCSVT.2018.2873102","volume":"29","author":"S Ma","year":"2018","unstructured":"Ma, S., Zhang, X., Wang, S., Zhang, X., Jia, C., & Wang, S. (2018). Joint feature and texture coding: Toward smart video representation via front-end intelligence. IEEE Transactions on Circuits and Systems for Video Technology, 29(10), 3095\u20133105.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"12","key":"1505_CR28","doi-asserted-by":"publisher","first-page":"3000","DOI":"10.1109\/TMC.2016.2519340","volume":"15","author":"A Redondi","year":"2016","unstructured":"Redondi, A., Baroffio, L., Bianchi, L., Cesana, M., & Tagliasacchi, M. (2016). Compress-then-analyze versus analyze-then-compress: What is best in visual sensor networks? IEEE Transactions on Mobile Computing, 15(12), 3000\u20133013.","journal-title":"IEEE Transactions on Mobile Computing"},{"issue":"6","key":"1505_CR29","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2016). Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137\u20131149.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1505_CR30","doi-asserted-by":"crossref","unstructured":"Schrimpf, M., Kubilius, J., Hong, H., Majaj, N. J., Rajalingham, R., Issa, E. B., Kar, K., Bashivan, P., Prescott-Roy, J., Schmidt, K., et al. (2018). Brain-score: Which artificial neural network for object recognition is most brain-like? BioRxiv p. 407007.","DOI":"10.1101\/407007"},{"key":"1505_CR31","doi-asserted-by":"crossref","unstructured":"Shi, J., & Chen, Z. (2020). Reinforced bit allocation under task-driven semantic distortion metrics. In 2020 IEEE international symposium on circuits and systems (ISCAS) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ISCAS45731.2020.9180454"},{"key":"1505_CR32","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"issue":"5","key":"1505_CR33","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/79.952804","volume":"18","author":"A Skodras","year":"2001","unstructured":"Skodras, A., Christopoulos, C., & Ebrahimi, T. (2001). The jpeg 2000 still image compression standard. IEEE Signal Processing Magazine, 18(5), 36\u201358.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"5","key":"1505_CR34","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1109\/TEVC.2019.2890858","volume":"23","author":"J Su","year":"2019","unstructured":"Su, J., Vargas, D. V., & Sakurai, K. (2019). One pixel attack for fooling deep neural networks. IEEE Transactions on Evolutionary Computation, 23(5), 828\u2013841.","journal-title":"IEEE Transactions on Evolutionary Computation"},{"issue":"12","key":"1505_CR35","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","volume":"22","author":"GJ Sullivan","year":"2012","unstructured":"Sullivan, G. J., Ohm, J. R., Han, W. J., & Wiegand, T. (2012). Overview of the high efficiency video coding (hevc) standard. IEEE Transactions on Circuits and Systems for Video Technology, 22(12), 1649\u20131668.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1505_CR36","unstructured":"Tan, M., & Le, Q. V. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946."},{"key":"1505_CR37","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., & Belongie, S. (2011). The caltech-ucsd birds-200-2011 dataset."},{"key":"1505_CR38","doi-asserted-by":"crossref","unstructured":"Wang, H., Gan, W., Hu, S., Lin, J. Y., Jin, L., Song, L., Wang, P., Katsavounidis, I., Aaron, A., & Kuo, C. C. J. (2016). Mcl-jcv: a jnd-based h. 264\/avc video quality assessment dataset. In 2016 IEEE international conference on image processing (ICIP) (pp. 1509\u20131513). IEEE.","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"1505_CR39","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.jvcir.2017.04.009","volume":"46","author":"H Wang","year":"2017","unstructured":"Wang, H., Katsavounidis, I., Zhou, J., Park, J., Lei, S., Zhou, X., et al. (2017). Videoset: A large-scale compressed video quality dataset based on jnd measurement. Journal of Visual Communication and Image Representation, 46, 292\u2013302.","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"1505_CR40","doi-asserted-by":"crossref","unstructured":"Wang, H., Katsavounidis, I., Huang, Q., Zhou, X., & Kuo, C. C. J. (2018a). Prediction of satisfied user ratio for compressed video. In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 6747\u20136751). IEEE.","DOI":"10.1109\/ICASSP.2018.8461571"},{"key":"1505_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, X., Yang, C., & Kuo, C. C. J. (2018b). Analysis and prediction of jnd-based video quality model. In 2018 picture coding symposium (PCS) (pp 278\u2013282). IEEE.","DOI":"10.1109\/PCS.2018.8456243"},{"key":"1505_CR42","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, S., Yang, W., Zhang, X., Wang, S., Ma, S., & Gao, W. (2020). Towards analysis-friendly face representation with scalable feature and texture compression. arXiv preprint arXiv:2004.10043.","DOI":"10.1109\/TMM.2021.3094300"},{"key":"1505_CR43","doi-asserted-by":"crossref","unstructured":"Wiegand, T., Sullivan, G. J., Bjontegaard, G., & Luthra, A. (2003). Overview of the h. 264\/avc video coding standard. IEEE Transactions on Circuits and Systems for Video Technology, 13(7), 560\u2013576.","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"1505_CR44","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1492\u20131500.","DOI":"10.1109\/CVPR.2017.634"},{"issue":"3","key":"1505_CR45","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1038\/nn.4244","volume":"19","author":"DL Yamins","year":"2016","unstructured":"Yamins, D. L., & DiCarlo, J. J. (2016). Using goal-driven deep learning models to understand sensory cortex. Nature Neuroscience, 19(3), 356\u2013365.","journal-title":"Nature Neuroscience"},{"issue":"7","key":"1505_CR46","first-page":"662","volume":"20","author":"X Yang","year":"2005","unstructured":"Yang, X., Ling, W., Lu, Z., Ong, E. P., & Yao, S. (2005). Just noticeable distortion model and its applications in video coding. Signal Processing: Image Communication, 20(7), 662\u2013680.","journal-title":"Signal Processing: Image Communication"},{"key":"1505_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, J., Jia, C., Lei, M., Wang, S., Ma, S., & Gao, W. (2019). Recent development of avs video coding standard: Avs3. In 2019 picture coding symposium (PCS) (pp. 1\u20135). IEEE.","DOI":"10.1109\/PCS48520.2019.8954503"},{"issue":"2","key":"1505_CR48","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1109\/TIP.2016.2629447","volume":"26","author":"X Zhang","year":"2016","unstructured":"Zhang, X., Ma, S., Wang, S., Zhang, X., Sun, H., & Gao, W. (2016). A joint compression scheme of video feature descriptors and visual content. IEEE Transactions on Image Processing, 26(2), 633\u2013647.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1505_CR49","doi-asserted-by":"publisher","first-page":"3777","DOI":"10.1109\/TIP.2020.2965994","volume":"29","author":"X Zhang","year":"2020","unstructured":"Zhang, X., Yang, C., Wang, H., Xu, W., & Kuo, C. C. J. (2020). Satisfied-user-ratio modeling for compressed video. IEEE Transactions on Image Processing, 29, 3777\u20133789.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1505_CR50","unstructured":"Zhou, X., Wang, D., & Kr\u00e4henb\u00fchl, P. (2019). Objects as points. arXiv preprint arXiv:1904.07850."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01505-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01505-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01505-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T04:02:50Z","timestamp":1634270570000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01505-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,13]]},"references-count":50,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["1505"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01505-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,13]]},"assertion":[{"value":"15 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}