{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:41:47Z","timestamp":1778694107311,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T00:00:00Z","timestamp":1726790400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T00:00:00Z","timestamp":1726790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Institute of Information & communications Technology Planning & Evaluation","award":["2020-0-00011"],"award-info":[{"award-number":["2020-0-00011"]}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","award":["4120240214871"],"award-info":[{"award-number":["4120240214871"]}],"id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Image Video Proc."],"DOI":"10.1186\/s13640-024-00649-w","type":"journal-article","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T05:24:21Z","timestamp":1727155461000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep learning-guided video compression for machine vision tasks"],"prefix":"10.1186","volume":"2024","author":[{"given":"Aro","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung-taek","family":"Woo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minho","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong-hwi","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanshin","family":"Lim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soon-heung","family":"Jung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangwoon","family":"Kwak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7282-7686","authenticated-orcid":false,"given":"Sang-hyo","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,20]]},"reference":[{"issue":"10","key":"649_CR1","doi-asserted-by":"publisher","first-page":"3736","DOI":"10.1109\/TCSVT.2021.3101953","volume":"31","author":"B Bross","year":"2021","unstructured":"B. Bross, Y.-K. Wang, Y. Ye, S. Liu, J. Chen, G.J. Sullivan, J.-R. Ohm, Overview of the versatile video coding (VVC) standard and its applications. IEEE Trans. Circuits Syst. Video Technol. 31(10), 3736\u20133764 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"649_CR2","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","volume":"22","author":"GJ Sullivan","year":"2012","unstructured":"G.J. Sullivan, J.R. Ohm, W.J. Han, T. Wiegand, Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circuits Syst. Video Technol. 22(12), 1649\u20131668 (2012)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"649_CR3","unstructured":"S. Liu, C. Rosewarne, Working draft 2 of video coding for machines, document ISO\/IEC JTC1\/SC29\/WG 04, N00465, (2024)"},{"key":"649_CR4","unstructured":"SFU-HW-Object-v1, ftp:\/\/hevc@mpeg.tnt.uni-hannover.de\/testsequences\/. Accessed July 2024"},{"key":"649_CR5","unstructured":"Tencent video dataset, https:\/\/multimedia.tencent.com\/resources\/tvd. Accessed July 2024"},{"key":"649_CR6","doi-asserted-by":"crossref","unstructured":"S. R\u00f3\u017cek, O. Stankiewicz, S. Ma\u0107kowiak, M. Doma\u0144ski, Video coding for machines using object analysis and standard video codecs, in Proceedings 2023 IEEE International Conference on Visual Communications and Image Processing (VCIP), (Jeju, Korea, 2023), pp. 1\u20135","DOI":"10.1109\/VCIP59821.2023.10402642"},{"key":"649_CR7","doi-asserted-by":"crossref","unstructured":"Z. Huang, C. Jia, S. Wang, S. Ma, Visual analysis motivated rate-distortion model for image coding, in Proceedings 2021 IEEE International Conference on Multimedia and Expo (ICME), (2021), pp. 1\u20136","DOI":"10.1109\/ICME51207.2021.9428417"},{"key":"649_CR8","doi-asserted-by":"crossref","unstructured":"Y. Lee, S. Kim, K. Yoon, H. Lim, S. Kwak, H.-G. Choo, Machine-Attention-based Video Coding for Machines, in Proceedings 2023 IEEE International Conference on Image Processing (ICIP), (Kuala Lumpur, Malalysia, 2023), pp. 2700\u20132704","DOI":"10.1109\/ICIP49359.2023.10222037"},{"issue":"27","key":"649_CR9","doi-asserted-by":"publisher","first-page":"42803","DOI":"10.1007\/s11042-023-15409-7","volume":"82","author":"JY Lee","year":"2023","unstructured":"J.Y. Lee, Y. Choi, T. Van Le, K. Choi, Efficient feature coding based on performance analysis of Versatile Video Coding (VVC) in Video Coding for Machines (VCM). Multimed. Tools Appl. 82(27), 42803\u201342816 (2023)","journal-title":"Multimed. Tools Appl."},{"key":"649_CR10","unstructured":"D. Ding, Z. Xin, L. Zizheng, L. Shan, [VCM] Bitwise efficiency: truncating bit depth for machine video coding, document ISO\/IEC JTC1\/SC29\/WG 04, m65525 (Hannover, Germany, 2023)"},{"key":"649_CR11","doi-asserted-by":"crossref","unstructured":"K. Fischer, F. Fleckenstein, C. Herglotz, A. Kaup, Saliency-driven versatile video coding for neural object detection, in Proceedings 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), (Toronto, Canada, 2021), pp. 1505\u20131509","DOI":"10.1109\/ICASSP39728.2021.9415048"},{"key":"649_CR12","unstructured":"Z. Lui, Y. Zhang, R. Chernyak, H. Zhu, X. Xu, S. Liu, J. Jia, Z. Chen, M. W. Park, [VCM] Response to VCM call for proposals\u2014an EVC based solution, document ISO\/IEC JTC1\/SC29\/WG 04, m61452 (Mainz, Germany, 2022)"},{"key":"649_CR13","unstructured":"L. Yu, VCM-CE 4: temporal resampling, document ISO\/IEC JTC1\/SC29\/WG 04, N00383 (Switzerland, Geneva, 2023)"},{"key":"649_CR14","unstructured":"S. Kim, M. Jeong, J. Lee, H. Lee, S. Jung, [VCM] Proposed text of RoI based coding, document ISO\/IEC JTC1\/SC29\/WG 04, m64627 (Switzerland, Geneva, 2023)"},{"key":"649_CR15","unstructured":"J. Lee, S. Cho, S.-K. Beack, Context-adaptive entropy model for end-to-end optimized image compression, in Proceedings 2019 International Conference on Learning Representations (ICLR), (New Orleans, USA, 2019), pp. 1\u201320"},{"key":"649_CR16","doi-asserted-by":"crossref","unstructured":"D. Minnen, S. Singh, Channel-wise autoregressive entropy models for learned image compression\u201d, in Proceedings 2020 IEEE International Conference on Image Processing (ICIP) (Abu Dhabi, United Arab Emirates, 2020), pp. 3339\u20133343","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"649_CR17","doi-asserted-by":"crossref","unstructured":"J. Lin, D. Liu, H. Li, F. Wu, M-LVC: multiple frames prediction for learned video compression, in Proceedings 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (Seattle, USA, 2020), pp. 3546\u20133554","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"649_CR18","doi-asserted-by":"crossref","unstructured":"Z. Cheng, H. Sun, M. Takeuchi, J. Katto, Learned image compression with discretized gaussian mixture likelihoods and attention modules, in Proceedings 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), (Seattle, USA, 2020), pp. 7939\u20137948","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"649_CR19","doi-asserted-by":"crossref","unstructured":"D. He, Y. Zheng, B. Sun, Y. Wang, H. Qin, Checkerboard context model for efficient learned image compression, in Proceedings 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (Nashville, USA, 2021), pp. 14771\u201314780","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"649_CR20","unstructured":"Y. Qian, M. Lin, X. Sun, Z. Tan, R. Jin, Entroformer: a transformer-based entropy model for learned image compression, in Proceedings 2022 International Conference on Learning Representations (ICLR), (Virtual, 2022), pp. 1\u201315"},{"key":"649_CR21","doi-asserted-by":"crossref","unstructured":"J. Li, B. Li, Y. Lu, Neural video compression with diverse contexts, in Proceedings 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), (Vancouver, Canada, 2023), pp. 22616\u201322626","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"649_CR22","doi-asserted-by":"crossref","unstructured":"N. Le, H. Zhang, F. Cricri, R. Ghaznavi-Youvalari, E. Rahtu, Image coding for machines: an end-to-end learned approach, in Proceedings 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), (Toronto, Canada, 2021), pp. 1590\u20131594","DOI":"10.1109\/ICASSP39728.2021.9414465"},{"key":"649_CR23","doi-asserted-by":"crossref","unstructured":"Y. Kim, H. Jeong, J. Yu, Y. Kim, J. Lee, S. Y. Jeong, H. Y. Kim, End-to-end learnable multi-scale feature compression for VCM. IEEE Trans. Circuits Syst. Video Technol. (2023), p. 1","DOI":"10.1109\/TCSVT.2023.3302858"},{"key":"649_CR24","doi-asserted-by":"crossref","unstructured":"S. Suzuki, M. Takagi, K. Hayase, T. Onishi, A. Shimizu, Image pre-transformation for recognition-aware image compression, in Proceedings 2019 IEEE International Conference on Image Processing (ICIP), (Taipei, Taiwan, 2019), pp. 2686\u20132690","DOI":"10.1109\/ICIP.2019.8803275"},{"key":"649_CR25","doi-asserted-by":"crossref","unstructured":"K. Fischer, C. Herglotz, A. Kaup, On intra video coding and in-loop filtering for neural object detection networks, in Proceedings 2020 IEEE International Conference on Image Processing (ICIP), (Abu Dhabi, United Arab Emirates, 2020), pp. 1147\u20131151","DOI":"10.1109\/ICIP40778.2020.9191023"},{"key":"649_CR26","unstructured":"H. Yu, A. Liu, K. Jia, L, Yu, [VCM] CE2-related: single layer framework with NNIC and VVC for video coding for machines, document ISO\/IEC JTC1\/SC29\/WG 04, m64253, (Geneva, Switzerland, 2023)"},{"key":"649_CR27","unstructured":"Y. Lee, K. Yoon, H. Lim, S. Kwak, S. Jung, W, Cheong, H. -G. Choo, [VCM] comments on VCM anchor, document ISO\/IEC JTC1\/SC29\/WG 04, m64809, (Hannover, Germany, 2023)"},{"key":"649_CR28","unstructured":"S. Liu, H. Zhang, [VCM] Common test conditions for video coding for machines, document ISO\/IEC JTC1\/SC29\/WG 04, m62002, (2023)"},{"key":"649_CR29","unstructured":"D. Ding, H. Wang, X. Zhao, X. Pan, Z. Lui, X. Xu, S. Lui, [VCM] A curve fitting approach to transform nonmonotonic test data for BD-rate calculation, document ISO\/IEC JTC1\/SC29\/WG 04, m65531 (Hannover, Germany, 2023)"},{"issue":"10","key":"649_CR30","doi-asserted-by":"publisher","first-page":"3907","DOI":"10.1109\/TCSVT.2021.3072297","volume":"31","author":"M Karczewicz","year":"2021","unstructured":"M. Karczewicz et al., VVC in-loop filters. IEEE Trans. Circuits Syst. Video Technol. 31(10), 3907\u20133925 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"10","key":"649_CR31","doi-asserted-by":"publisher","first-page":"3818","DOI":"10.1109\/TCSVT.2021.3088134","volume":"31","author":"Y-W Huang","year":"2021","unstructured":"Y.-W. Huang, J. An, H. Huang, X. Li, S.-T. Hsiang, K. Zhang, H. Gao, J. Ma, O. Chubach, Block partitioning structure in the VVC standard. IEEE Trans. Circuits Syst. Video Technol. 31(10), 3818\u20133833 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"649_CR32","doi-asserted-by":"crossref","unstructured":"W. Zhu, J. Xu, L. Zhang, Y. Wang, Adaptive dual tree structure for screen content coding, in Proceedings 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), (Toronto, Canada, 2021), pp. 1550\u20131554","DOI":"10.1109\/ICASSP39728.2021.9414002"},{"issue":"4","key":"649_CR33","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1109\/JETCAS.2016.2597645","volume":"6","author":"X Xu","year":"2016","unstructured":"X. Xu et al., Intra block copy in HEVC screen content coding extensions. IEEE J. Emerg. Sel. Top. Circuits Syst. 6(4), 409\u2013419 (2016)","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"649_CR34","doi-asserted-by":"crossref","unstructured":"J. Kim, J. Yang, K. Won, B. Jeon, Early determination of mode decision for HEVC, in Proceedings 2012 Picture Coding Symposium (Krakow, Poland, 2012), pp. 449\u2013452","DOI":"10.1109\/PCS.2012.6213251"},{"key":"649_CR35","unstructured":"L. Leal-Taix\u00e9, A. Milan, I. Reid, S. Roth, K. Schindler, Motchallenge 2015: towards a benchmark for multi-target tracking, arXiv preprint arXiv:1504.01942, (2015)"},{"key":"649_CR36","unstructured":"A. Milan, L. Leal-Taix\u00e9, I. Reid, S. Roth, K. Schindler, MOT16: a benchmark for multi-object tracking, arXiv preprint arXiv:1603.00831, (2016)"},{"key":"649_CR37","unstructured":"P. Dendorfer, H. Rezatofighi, A. Milan, J. Shi, D. Cremers, I. Reid, S. Roth, K. Schindler, L. Leal-Taix\u00e9, Mot20: a benchmark for multi object tracking in crowded scenes, arXiv preprint arXiv:2003.09003, (2020)"},{"key":"649_CR38","doi-asserted-by":"crossref","unstructured":"Z. Wang, L. Zheng, Y. Liu, Y. Li, S. Wang, Towards real-time multi-object tracking, in Proceedings 2020 European conference on computer vision (ECCV), (2020), pp. 107\u2013122","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"649_CR39","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"S. Ren, K. He, R. Girshick, J. Sun, Faster R-CNN: towards real-time object object detection with region proposal networks. Adv. Neural Inform. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"649_CR40","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in Proceedings 2016 IEEE conference on computer vision and pattern recognition (CVPR), (Las Vegas, USA, 2016), pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"649_CR41","unstructured":"D. Reis, J. Kupec, J. Hong, A. Daoudi, Real-time flying object detection with YOLOv8, arXiv preprint arXiv:2305.09972, (2023)"}],"container-title":["EURASIP Journal on Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-024-00649-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13640-024-00649-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13640-024-00649-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T05:24:47Z","timestamp":1727155487000},"score":1,"resource":{"primary":{"URL":"https:\/\/jivp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13640-024-00649-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,20]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["649"],"URL":"https:\/\/doi.org\/10.1186\/s13640-024-00649-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4346457\/v1","asserted-by":"object"}]},"ISSN":["1687-5281"],"issn-type":[{"value":"1687-5281","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,20]]},"assertion":[{"value":"30 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"32"}}