{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:56:42Z","timestamp":1773154602077,"version":"3.50.1"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"9","license":[{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>Convolutional Neural Networks (CNN) have given rise to numerous visual analytics applications at the edge of the Internet. The image is typically captured by cameras and then live-streamed to edge servers for analytics due to the prohibitive cost of running CNN on computation-constrained end devices. A critical component to ensure low-latency and accurate visual analytics offloading over low bandwidth networks is image compression which minimizes the amount of visual data to offload and maximizes the decoding quality of salient pixels for analytics. Despite the wide adoption, JPEG standards and traditional image compression techniques do not address the accuracy of analytics tasks, leading to ineffective compression for visual analytics offloading. Although recent machine-centric image compression techniques leverage sophisticated neural network models or hardware architecture to support the accuracy-bandwidth tradeoff, they introduce excessive latency in the visual analytics offloading pipeline. This article presents CICO, a Context-aware Image Compression Optimization framework to achieve low-bandwidth and low-latency visual analytics offloading. CICO contextualizes image compression for offloading by employing easily-computable low-level image features to understand the importance of different image regions for a visual analytics task. Accordingly, CICO can optimize the tradeoff between compression size and analytics accuracy. Extensive real-world experiments demonstrate that CICO reduces the bandwidth consumption of existing compression methods by up to 40% under comparable analytics accuracy. Regarding the low-latency support, CICO achieves up to a 2\u00d7 speedup over state-of-the-art compression techniques.<\/jats:p>","DOI":"10.1145\/3638768","type":"journal-article","created":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T22:11:01Z","timestamp":1703715061000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Context-aware Optimization for Bandwidth-Efficient Image Analytics Offloading"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3392-4834","authenticated-orcid":false,"given":"Bo","family":"Chen","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6722-5517","authenticated-orcid":false,"given":"Zhisheng","family":"Yan","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax County, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6813-3043","authenticated-orcid":false,"given":"Klara","family":"Nahrstedt","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,16]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88693-8_8"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"e_1_3_2_4_2","unstructured":"Johannes Ball\u00e9 Valero Laparra and Eero P Simoncelli. 2017. End-to-end optimized image compression. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_5_2","unstructured":"Johannes Ball\u00e9 David Minnen Saurabh Singh Sung Jin Hwang and Nick Johnston. 2018. Variational image compression with a scale hyperprior. In Proceedings of the International Conference on Learning Representations 1\u201310."},{"key":"e_1_3_2_6_2","volume-title":"BPG Image Format","author":"Bellard Fabrice","year":"2018","unstructured":"Fabrice Bellard. 2018. BPG Image Format. Retrieved from https:\/\/bellard.org\/bpg\/. Accessed 2021."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2010.2049053"},{"key":"e_1_3_2_8_2","article-title":"The OpenCV library","author":"Bradski G.","year":"2000","unstructured":"G. Bradski. 2000. The OpenCV library. Dr. Dobb\u2019s Journal of Software Tools (2000).","journal-title":"Dr. Dobb\u2019s Journal of Software Tools"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.384"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3493452"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3304109.3306234"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524273.3528178"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Robert P. Dick and Niraj K. Jha. 1997. MOGAC: A multiobjective genetic algorithm for the co-synthesis of hardware-software embedded systems. In Proceedings of the ACM International Conference on Computer-Aided Design. 522\u2013529.","DOI":"10.1109\/ICCAD.1997.643589"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405887"},{"key":"e_1_3_2_16_2","volume-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results","author":"Everingham M.","year":"2012","unstructured":"M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. 2012. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. Retrieved from http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html. Accessed 2021."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019791213967"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2020.100520"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2001.968593"},{"key":"e_1_3_2_21_2","volume-title":"A New Image Format for the Web","year":"2020","unstructured":"Google. 2020. A New Image Format for the Web. Retrieved from https:\/\/developers.google.com\/speed\/webp. Accessed 2021."},{"key":"e_1_3_2_22_2","volume-title":"Libjpeg","author":"Group The Independent JPEG","year":"2014","unstructured":"The Independent JPEG Group. 2014. Libjpeg. Retrieved from https:\/\/github.com\/LuaDist\/libjpeg. Accessed 2021."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4154370"},{"key":"e_1_3_2_25_2","first-page":"33","volume-title":"Proceedings of the Monterey Workshop","author":"Kang Eunsuk","year":"2010","unstructured":"Eunsuk Kang, Ethan Jackson, and Wolfram Schulte. 2010. An approach for effective design space exploration. In Proceedings of the Monterey Workshop. Springer, 33\u201354."},{"key":"e_1_3_2_26_2","unstructured":"Okan K\u00f6p\u00fckl\u00fc Xiangyu Wei and Gerhard Rigoll. 2019. You only watch once: A unified cnn architecture for realtime spatiotemporal action localization. arXiv preprint arXiv:1911.06644 (2019)."},{"key":"e_1_3_2_27_2","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3300116"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321729"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2013.2253108"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkg509"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2009.2028681"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/774789.774804"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Omkar M. Parkhi Andrea Vedaldi and Andrew Zisserman. 2015. Deep face recognition. In BMVC 2015-Proceedings of the British Machine Vision Conference 2015. British Machine Vision Association.","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_2_38_2","unstructured":"Hieu Pham Qizhe Xie Zihang Dai and Quoc V Le. 2021. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2017.56"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_34"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Jianbo Shi. 1994. Good features to track. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition IEEE 593\u2013600.","DOI":"10.1109\/CVPR.1994.323794"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/79.952804"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2967058"},{"key":"e_1_3_2_46_2","first-page":"9279","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Suzuki Shinya","year":"2020","unstructured":"Shinya Suzuki, Shion Takeno, Tomoyuki Tamura, Kazuki Shitara, and Masayuki Karasuyama. 2020. Multi-objective bayesian optimization using pareto-frontier entropy. In Proceedings of the International Conference on Machine Learning. PMLR, 9279\u20139288."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/30.125072"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2010.3"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430898"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230554"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638768","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3638768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:34Z","timestamp":1750291414000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638768"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,16]]},"references-count":49,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3638768"],"URL":"https:\/\/doi.org\/10.1145\/3638768","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,16]]},"assertion":[{"value":"2023-04-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}