{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:12:54Z","timestamp":1780585974164,"version":"3.54.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Digital Signal Processing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.dsp.2026.106241","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T09:27:10Z","timestamp":1778578030000},"page":"106241","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Synergizing Mamba semantic alignment and knowledge distillation for human and machine vision in the compression domain"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0599-7085","authenticated-orcid":false,"given":"Shipei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiao","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunqiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinpeng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4995-728X","authenticated-orcid":false,"given":"Ping","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"10","key":"10.1016\/j.dsp.2026.106241_bib0001","doi-asserted-by":"crossref","first-page":"3736","DOI":"10.1109\/TCSVT.2021.3101953","article-title":"Overview of the versatile video coding (VVC) standard and its applications","volume":"31","author":"Bross","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"10.1016\/j.dsp.2026.106241_bib0002","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","article-title":"Overview of the high efficiency video coding (HEVC) standard","volume":"22","author":"Sullivan","year":"2012","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.dsp.2026.106241_bib0003","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.cities.2019.04.014","article-title":"Smart city and information technology: a review","volume":"93","author":"Camero","year":"2019","journal-title":"Cities"},{"key":"10.1016\/j.dsp.2026.106241_bib0004","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7939","article-title":"Learned image compression with discretized gaussian mixture likelihoods and attention modules","author":"Cheng","year":"2020"},{"key":"10.1016\/j.dsp.2026.106241_bib0005","series-title":"2022 Data Compression Conference","first-page":"469","article-title":"Transformer-based image compression","author":"Lu","year":"2022"},{"key":"10.1016\/j.dsp.2026.106241_bib0006","unstructured":"H. Li, S. Li, W. Dai, M. Cao, N. Kan, C. Li, J. Zou, H. Xiong, On disentangled training for nonlinear transform in learned image compression, arXiv preprint arXiv: 2501.13751(2025)."},{"key":"10.1016\/j.dsp.2026.106241_bib0007","series-title":"The Twelfth International Conference on Learning Representations","article-title":"Frequency-aware transformer for learned image compression","author":"Li","year":"2024"},{"key":"10.1016\/j.dsp.2026.106241_bib0008","series-title":"European Conference on Computer Vision","first-page":"382","article-title":"Image compression for machine and human vision with spatial-frequency adaptation","author":"Li","year":"2024"},{"key":"10.1016\/j.dsp.2026.106241_bib0009","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"23297","article-title":"Transtic: transferring transformer-based image compression from human perception to machine perception","author":"Chen","year":"2023"},{"issue":"1","key":"10.1016\/j.dsp.2026.106241_bib0010","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1109\/MMUL.2023.3245919","article-title":"The JPEG AI standard: providing efficient human and machine visual data consumption","volume":"30","author":"Ascenso","year":"2023","journal-title":"IEEE Multimed."},{"key":"10.1016\/j.dsp.2026.106241_bib0011","series-title":"2022 26th International Conference on Pattern Recognition","first-page":"331","article-title":"Improving multiple machine vision tasks in the compressed domain","author":"Liu","year":"2022"},{"key":"10.1016\/j.dsp.2026.106241_bib0012","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"8047","article-title":"ICMH-Net: neural image compression towards both machine vision and human vision","author":"Liu","year":"2023"},{"issue":"8","key":"10.1016\/j.dsp.2026.106241_bib0013","doi-asserted-by":"crossref","first-page":"4108","DOI":"10.1109\/TCSVT.2023.3240391","article-title":"Unified architecture adaptation for compressed domain semantic inference","volume":"33","author":"Duan","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.dsp.2026.106241_bib0014","series-title":"Advances in Neural Information Processing Systems","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017"},{"issue":"1","key":"10.1016\/j.dsp.2026.106241_bib0015","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106241_bib0016","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"25261","article-title":"MambaVision: a hybrid mamba-transformer vision backbone","author":"Hatamizadeh","year":"2025"},{"key":"10.1016\/j.dsp.2026.106241_bib0017","unstructured":"A. Gu, K. Goel, C. R\u00e9, Efficiently modeling long sequences with structured state spaces, arXiv preprint arXiv: 2111.00396(2021)."},{"key":"10.1016\/j.dsp.2026.106241_bib0018","unstructured":"G. Hinton, O. Vinyals, J. Dean, Distilling the knowledge in a neural network, arXiv preprint arXiv: 1503.02531(2015)."},{"issue":"6","key":"10.1016\/j.dsp.2026.106241_bib0019","doi-asserted-by":"crossref","first-page":"4190","DOI":"10.1109\/TCSVT.2023.3327113","article-title":"Boosting knowledge distillation via intra-class logit distribution smoothing","volume":"34","author":"Li","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.dsp.2026.106241_bib0020","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.isprsjprs.2025.02.006","article-title":"Adaptive discrepancy masked distillation for remote sensing object detection","volume":"222","author":"Li","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.dsp.2026.106241_bib0021","unstructured":"S. Zagoruyko, N. Komodakis, Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer, arXiv preprint arXiv: 1612.03928(2016)."},{"issue":"12","key":"10.1016\/j.dsp.2026.106241_bib0022","doi-asserted-by":"crossref","first-page":"15171","DOI":"10.1109\/TPAMI.2023.3319634","article-title":"Mutual-assistance learning for object detection","volume":"45","author":"Xie","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106241_bib0023","first-page":"1","article-title":"Instance-aware distillation for efficient object detection in remote sensing images","volume":"61","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"4","key":"10.1016\/j.dsp.2026.106241_bib0024","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1145\/103085.103089","article-title":"The JPEG still picture compression standard","volume":"34","author":"Wallace","year":"1991","journal-title":"Commun. ACM"},{"issue":"1","key":"10.1016\/j.dsp.2026.106241_bib0025","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/JPROC.2004.839613","article-title":"JPEG 2000: Retrospective and new developments","volume":"93","author":"Lee","year":"2005","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.dsp.2026.106241_bib0026","unstructured":"G. Toderici, S.M. O\u2019Malley, S.J. Hwang, D. Vincent, D. Minnen, S. Baluja, M. Covell, R. Sukthankar, Variable rate image compression with recurrent neural networks, arXiv preprint arXiv: 1511.06085(2015)."},{"key":"10.1016\/j.dsp.2026.106241_bib0027","unstructured":"J. Ball\u00e9, V. Laparra, E.P. Simoncelli, End-to-end optimized image compression, arXiv preprint arXiv: 1611.01704(2016)."},{"key":"10.1016\/j.dsp.2026.106241_bib0028","unstructured":"J. Ball\u00e9, D. Minnen, S. Singh, S.J. Hwang, N. Johnston, Variational image compression with a scale hyperprior, arXiv preprint arXiv: 1802.01436(2018)."},{"key":"10.1016\/j.dsp.2026.106241_bib0029","first-page":"10771","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume":"31","author":"Minnen","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.dsp.2026.106241_bib0030","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1109\/TPAMI.2020.3026003","article-title":"End-to-end optimized versatile image compression with wavelet-like transform","volume":"44","author":"Ma","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106241_bib0031","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"7618","article-title":"MLIC: multi-reference entropy model for learned image compression","author":"Jiang","year":"2023"},{"key":"10.1016\/j.dsp.2026.106241_bib0032","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"ALIC: Adaptive fusion entropy model for learned image compression","author":"Li","year":"2025"},{"key":"10.1016\/j.dsp.2026.106241_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2020.102804","article-title":"Deep dilated and densely connected parallel convolutional groups for compression artifacts reduction","volume":"106","author":"Amaranageswarao","year":"2020","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106241_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2023.104339","article-title":"A region-based hierarchical image compression method with simulated visual perception","volume":"145","author":"Wang","year":"2024","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106241_bib0035","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"ROI-based deep image compression with swin transformers","author":"Li","year":"2023"},{"issue":"7","key":"10.1016\/j.dsp.2026.106241_bib0036","doi-asserted-by":"crossref","first-page":"6416","DOI":"10.1109\/TCSVT.2023.3348995","article-title":"Task-switchable pre-processor for image compression for multiple machine vision tasks","volume":"34","author":"Yang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.dsp.2026.106241_bib0037","doi-asserted-by":"crossref","first-page":"2739","DOI":"10.1109\/TIP.2022.3160602","article-title":"Scalable image coding for humans and machines","volume":"31","author":"Choi","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.dsp.2026.106241_bib0038","series-title":"2024 IEEE 26th International Workshop on Multimedia Signal Processing","first-page":"1","article-title":"JPEG AI compressed domain face detection","author":"Alkhateeb","year":"2024"},{"key":"10.1016\/j.dsp.2026.106241_bib0039","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1874","article-title":"Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network","author":"Shi","year":"2016"},{"key":"10.1016\/j.dsp.2026.106241_bib0040","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"issue":"6","key":"10.1016\/j.dsp.2026.106241_bib0041","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","article-title":"Knowledge distillation and student-teacher learning for visual intelligence: a review and new outlooks","volume":"44","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106241_bib0042","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.dsp.2026.106241_bib0043","unstructured":"J. B\u00e9gaint, F. Racap\u00e9, S. Feltman, A. Pushparaja, CompressAI: a pytorch library and evaluation platform for end-to-end compression research, arXiv preprint arXiv: 2011.03029(2020)."},{"key":"10.1016\/j.dsp.2026.106241_bib0044","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"issue":"5","key":"10.1016\/j.dsp.2026.106241_bib0045","first-page":"2567","article-title":"Image quality assessment: unifying structure and texture similarity","volume":"44","author":"Ding","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106241_bib0046","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.dsp.2026.106241_bib0047","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.dsp.2026.106241_bib0048","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"}],"container-title":["Digital Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S105120042600360X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S105120042600360X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T14:54:52Z","timestamp":1780584892000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S105120042600360X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":48,"alternative-id":["S105120042600360X"],"URL":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106241","relation":{},"ISSN":["1051-2004"],"issn-type":[{"value":"1051-2004","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Synergizing Mamba semantic alignment and knowledge distillation for human and machine vision in the compression domain","name":"articletitle","label":"Article Title"},{"value":"Digital Signal Processing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106241","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106241"}}