{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T04:35:34Z","timestamp":1774931734334,"version":"3.50.1"},"reference-count":46,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62141220"],"award-info":[{"award-number":["62141220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Yunnan Key Research Program","award":["202402AD080004"],"award-info":[{"award-number":["202402AD080004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Auton. Adapt. Syst."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>\n                    With the improvement of edge-based autonomous systems such as mobile Industrial IoT (IIoT) networks, edge devices can capture and upload videos with increasing bitrates. Massive edge-computing end nodes are eager for adequate multimedia data to satisfy the requirements of real-time video services. However, existing encoding standards for video services in Web 2.0 are specifically designed for something other than IoT video streaming. We have improved our Adaptive Compression-Reconstruction (ACORN) framework to obtain ACORN+, based on compressed sensing and recent advances in deep learning. At end nodes, we compress multiple sequential video frames into a single frame to reduce video volume. Given that multiple kinds of intelligent tasks are expected to be finished on the device side, we also designed a device-cloud collaboration scheme where deep learning-based algorithms can be executed on both the device and server sides. Experiments reveal that video analytics can be conducted on compressed frames. Taking action recognition as a device-cloud collaboration use case, we find ACORN\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(+\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    obtains more than 3\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    speedup on compressed frames. The reconstruction algorithm in ACORN\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(+\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    is with 1\u2013 4 dB improvements. Moreover, the encoding time cost and the encoded video volume are reduced by more than 4\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    under the ACORN\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(+\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    framework.\n                    <jats:xref ref-type=\"fn\">\n                      <jats:sup>1<\/jats:sup>\n                    <\/jats:xref>\n                  <\/jats:p>","DOI":"10.1145\/3703000","type":"journal-article","created":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T07:50:34Z","timestamp":1730793034000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["ACORN+: Adaptive Compression-Reconstruction for Device-Cloud Collaboration Video Services"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0052-5581","authenticated-orcid":false,"given":"Jiale","family":"Lei","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3082-3852","authenticated-orcid":false,"given":"Peihao","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9266-3044","authenticated-orcid":false,"given":"Linghe","family":"Kong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8595-1619","authenticated-orcid":false,"given":"Yehan","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1400-4769","authenticated-orcid":false,"given":"Deyu","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6934-1685","authenticated-orcid":false,"given":"Guihai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9025-7777","authenticated-orcid":false,"given":"E.","family":"Zhao","sequence":"additional","affiliation":[{"name":"Aerospace Technology Holding Group Co., Ltd, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"285","article-title":"ACORN: Adaptive compression-reconstruction for video services in 5G-U industrial IoT","author":"Lei Jiale","year":"2023","unstructured":"Jiale Lei, Peihao Yang, Linghe Kong, Yehan Ma, Xingjian Lu, Deyu Lin, Guihai Chen, and E. Zhao. 2023. ACORN: Adaptive compression-reconstruction for video services in 5G-U industrial IoT. In IEEE MSN, 285\u2013292.","journal-title":"IEEE MSN"},{"key":"e_1_3_2_3_2","unstructured":"Tech. Spec. Group Services and System Aspects. 2021. Service Requirements for the 5G System. 3GPP TS 22.261 V18.1.1 1\u201385."},{"key":"e_1_3_2_4_2","unstructured":"Vasanth Ganesan Yubing Ji and Mark Patel. Video Meets the Internet of Things. Retrieved July 4 2021 from https:\/\/www.mckinsey.com\/industries\/technology-media-and-telecommunications\/our-insights\/video-meets-the-internet-of-things"},{"key":"e_1_3_2_5_2","first-page":"39","article-title":"Analyzing video services in Web 2.0: A global perspective","author":"Saxena Mohit","year":"2008","unstructured":"Mohit Saxena, Umang Sharan, and Sonia Fahmy. 2008. Analyzing video services in Web 2.0: A global perspective. In ACM SIGDC (NOSSDAV \u201908), 39\u201344.","journal-title":"ACM SIGDC (NOSSDAV \u201908)"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2016.2517653"},{"key":"e_1_3_2_7_2","first-page":"4471","article-title":"Free-form image inpainting with gated convolution","author":"Yu Jiahui","year":"2019","unstructured":"Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, and Thomas S. Huang. 2019. Free-form image inpainting with gated convolution. In IEEE\/CVF ICCV, 4471\u20134480.","journal-title":"IEEE\/CVF ICCV"},{"key":"e_1_3_2_8_2","first-page":"1276","article-title":"Towards distributed cyberinfrastructure for smart cities using big data and deep learning technologies","author":"Shams Shayan","year":"2018","unstructured":"Shayan Shams, Sayan Goswami, Kisung Lee, Seungwon Yang, and Seung-Jong Park. 2018. Towards distributed cyberinfrastructure for smart cities using big data and deep learning technologies. In IEEE ICDCS, 1276\u20131283.","journal-title":"IEEE ICDCS"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3366506"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3309321"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3321679"},{"key":"e_1_3_2_12_2","first-page":"243","article-title":"Event-driven bandwidth allocation with formal guarantees for camera networks","author":"Seetanadi Gautham Nayak","year":"2017","unstructured":"Gautham Nayak Seetanadi, Javier Camara, Luis Almeida, Karl-Erik Arzen, and Martina Maggio. 2017. Event-driven bandwidth allocation with formal guarantees for camera networks. In IEEE RTSS, 243\u2013254.","journal-title":"IEEE RTSS"},{"key":"e_1_3_2_13_2","first-page":"157","article-title":"Aerial video stream over multi-hop using adaptive TDMA slots","author":"Pinto Luis Ramos","year":"2017","unstructured":"Luis Ramos Pinto, Luis Almeida, Hassan Alizadeh, and Anthony Rowe. 2017. Aerial video stream over multi-hop using adaptive TDMA slots. In IEEE RTSS, 157\u2013166.","journal-title":"IEEE RTSS"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2018.01.012"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2685630"},{"key":"e_1_3_2_16_2","first-page":"123","article-title":"MCDNN: An approximation-based execution framework for deep stream processing under resource constraints","author":"Han Seungyeop","year":"2016","unstructured":"Seungyeop Han, Haichen Shen, Matthai Philipose, Sharad Agarwal, Alec Wolman, and Arvind Krishnamurthy. 2016. MCDNN: An approximation-based execution framework for deep stream processing under resource constraints. In ACM MobiSys, 123\u2013136.","journal-title":"ACM MobiSys"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485905"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEC50012.2020.00015"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057025"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486406"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2017.2653116"},{"key":"e_1_3_2_22_2","first-page":"31","article-title":"Wireless camera nodes on a cyber-physical system","author":"Gardel A.","year":"2016","unstructured":"A. Gardel, F. Espinosa, R. Nieto, J. L. L\u00e1zaro, and I. Bravo. 2016. Wireless camera nodes on a cyber-physical system. In ACM ICDSC (ICDSC \u201916), 31\u201336.","journal-title":"ACM ICDSC (ICDSC \u201916)"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1364\/OE.21.010526"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3163539"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6726"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2873587"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2989550"},{"key":"e_1_3_2_28_2","first-page":"1447","article-title":"Plug-and-play algorithms for large-scale snapshot compressive imaging","author":"Yuan Xin","year":"2020","unstructured":"Xin Yuan, Yang Liu, Jinli Suo, and Qionghai Dai. 2020. Plug-and-play algorithms for large-scale snapshot compressive imaging. In IEEE\/CVF CVPR, 1447\u20131457.","journal-title":"IEEE\/CVF CVPR"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2018.2865511"},{"key":"e_1_3_2_32_2","unstructured":"FFmpeg Team. FFmpeg Homepage. Retrieved May 4 2021 from https:\/\/www.ffmpeg.org\/"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057057"},{"key":"e_1_3_2_34_2","first-page":"197","article-title":"Neural adaptive video streaming with Pensieve","author":"Mao Hongzi","year":"2017","unstructured":"Hongzi Mao, Ravi Netravali, and Mohammad Alizadeh. 2017. Neural adaptive video streaming with Pensieve. In ACM SIGCOMM, 197\u2013210.","journal-title":"ACM SIGCOMM"},{"key":"e_1_3_2_35_2","first-page":"44","article-title":"Oboe: Auto-tuning video ABR algorithms to network conditions","author":"Akhtar Zahaib","year":"2018","unstructured":"Zahaib Akhtar, Yun Seong Nam, Ramesh Govindan, Sanjay Rao, Jessica Chen, Ethan Katz-Bassett, Bruno Ribeiro, Jibin Zhan, and Hui Zhang. 2018. Oboe: Auto-tuning video ABR algorithms to network conditions. In ACM SIGCOMM, 44\u201358.","journal-title":"ACM SIGCOMM"},{"key":"e_1_3_2_36_2","first-page":"1331","article-title":"Real-time video quality of experience monitoring for HTTPS and QUIC","author":"Mazhar M. Hammad","year":"2018","unstructured":"M. Hammad Mazhar and Zubair Shafiq. 2018. Real-time video quality of experience monitoring for HTTPS and QUIC. In IEEE INFOCOM. IEEE, 1331\u20131339.","journal-title":"IEEE INFOCOM"},{"key":"e_1_3_2_37_2","first-page":"2351","article-title":"Quality assessment of in-the-wild videos","author":"Li Dingquan","year":"2019","unstructured":"Dingquan Li, Tingting Jiang, and Ming Jiang. 2019. Quality assessment of in-the-wild videos. In ACM Multimedia, 2351\u20132359.","journal-title":"ACM Multimedia"},{"key":"e_1_3_2_38_2","first-page":"82","article-title":"DeepMon: Mobile GPU-based deep learning framework for continuous vision applications","author":"Huynh Loc N.","year":"2017","unstructured":"Loc N. Huynh, Youngki Lee, and Rajesh Krishna Balan. 2017. DeepMon: Mobile GPU-based deep learning framework for continuous vision applications. In ACM MobiCom, 82\u201395.","journal-title":"ACM MobiCom"},{"key":"e_1_3_2_39_2","first-page":"4724","article-title":"Quo vadis, action recognition? A new model and the kinetics dataset","author":"Carreira Jo\u00e3o","year":"2017","unstructured":"Jo\u00e3o Carreira and Andrew Zisserman. 2017. Quo vadis, action recognition? A new model and the kinetics dataset. In IEEE CVPR, 4724\u20134733.","journal-title":"IEEE CVPR"},{"key":"e_1_3_2_40_2","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In IEEE CVPR, 770\u2013778.","journal-title":"IEEE CVPR"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs9050446"},{"key":"e_1_3_2_42_2","first-page":"971","article-title":"Self-normalizing neural networks","author":"Klambauer G\u00fcnter","year":"2017","unstructured":"G\u00fcnter Klambauer, Thomas Unterthiner, Andreas Mayr, and Sepp Hochreiter. 2017. Self-normalizing neural networks. In NeurIPS, 971\u2013980.","journal-title":"NeurIPS"},{"issue":"1","key":"e_1_3_2_43_2","first-page":"348","article-title":"TBDB: Token bucket-based dynamic batching for resource scheduling supporting neural network inference in intelligent consumer electronics","volume":"73","author":"Gao Honghao","year":"2023","unstructured":"Honghao Gao, Binyang Qiu, Ye Wang, Si Yu, Yueshen Xu, and Xinheng Wang. 2023. TBDB: Token bucket-based dynamic batching for resource scheduling supporting neural network inference in intelligent consumer electronics. IEEE Transactions on Consumer Electronics 73, 1 (2023), 348\u2013361.","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"e_1_3_2_44_2","first-page":"95","article-title":"Simulation framework for HTTP-based adaptive streaming applications","author":"Ott Harald","year":"2017","unstructured":"Harald Ott, Konstantin Miller, and Adam Wolisz. 2017. Simulation framework for HTTP-based adaptive streaming applications. In ACM WNS3, 95\u2013102.","journal-title":"ACM WNS3"},{"key":"e_1_3_2_45_2","first-page":"2556","article-title":"HMDB: A large video database for human motion recognition","author":"Kuehne Hildegard","year":"2011","unstructured":"Hildegard Kuehne, Hueihan Jhuang, Est\u00edbaliz Garrote, Tomaso Poggio, and Thomas Serre. 2011. HMDB: A large video database for human motion recognition. In IEEE CVPR. IEEE, 2556\u20132563.","journal-title":"IEEE CVPR"},{"key":"e_1_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Khurram Soomro Amir Roshan Zamir and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402. Retrieved from https:\/\/doi.org\/10.1109\/TIP.2003.819861","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"container-title":["ACM Transactions on Autonomous and Adaptive Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T13:28:58Z","timestamp":1764163738000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703000"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,26]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3703000"],"URL":"https:\/\/doi.org\/10.1145\/3703000","relation":{},"ISSN":["1556-4665","1556-4703"],"issn-type":[{"value":"1556-4665","type":"print"},{"value":"1556-4703","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,26]]},"assertion":[{"value":"2024-01-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}