{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:46:34Z","timestamp":1782405994568,"version":"3.54.5"},"reference-count":65,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2023YFB4502805"],"award-info":[{"award-number":["2023YFB4502805"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["GZC20251091"],"award-info":[{"award-number":["GZC20251091"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>With the rapid growth of video-based applications, edge-cloud collaboration has become a mainstream paradigm for large-scale visual inference. However, existing edge-cloud systems primarily emphasize task offloading and static resource allocation, often overlooking the dynamic and heterogeneous nature of real-world scenarios. The significant variability in scene complexity across tasks leads to inefficient system performance. In this article, we propose CLAP, a cross-layer adaptive pipelining inference scheduling framework for edge-cloud vision systems. First, CLAP introduces a lightweight multiscale scene-aware module that accurately characterizes the visual complexity of incoming tasks at different granularities with minimal overhead. Based on this complexity profile, we design an adaptive multi-stage pipeline scheduling strategy, which dynamically adjusts processing granularity and selectively activates stages across edge and cloud nodes. Furthermore, we formulate the resource allocation as a multi-agent decision-making problem and employ cross-layer reinforcement learning to optimize task distribution under complex objectives, efficiently balancing accuracy, delay, and energy consumption. Extensive evaluations on public datasets demonstrate that CLAP can improve the throughput by more than 2.1x compared to traditional cloud-only and edge-only solutions while meeting accuracy requirements. Compared to state-of-the-art edge-cloud methods, CLAP achieves a 3% improvement in inference accuracy while simultaneously reducing end-to-end resource overhead, delay, and energy consumption by over 35%, proving its effectiveness in dynamic, large-scale vision applications.<\/jats:p>","DOI":"10.1145\/3803806","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T20:47:40Z","timestamp":1774471660000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["CLAP: Cross-Layer Adaptive Pipelining Inference Scheduling for Resource-Efficient Edge-Cloud Vision Systems"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9957-5792","authenticated-orcid":false,"given":"Zheming","family":"Yang","sequence":"first","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6895-3404","authenticated-orcid":false,"given":"Wen","family":"Ji","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS","place":["Beijing, China"]},{"name":"Institute of AI for Industries, CAS","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3997-6930","authenticated-orcid":false,"given":"Qi","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9799-0831","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4404-5454","authenticated-orcid":false,"given":"Chang","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1442-1864","authenticated-orcid":false,"given":"Xingzhou","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9582-6953","authenticated-orcid":false,"given":"Yangyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1020-5148","authenticated-orcid":false,"given":"Zhicheng","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2816-4384","authenticated-orcid":false,"given":"Yang","family":"You","sequence":"additional","affiliation":[{"name":"National University of Singapore","place":["Singapore, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"issue":"2","key":"e_1_3_1_2_2","first-page":"792","article-title":"RES: Real-time video stream analytics using edge enhanced clouds","volume":"10","author":"Ali Muhammad","year":"2020","unstructured":"Muhammad Ali, Ashiq Anjum, Omer Rana, Ali Reza Zamani, Daniel Balouek-Thomert, and Manish Parashar. 2020. RES: Real-time video stream analytics using edge enhanced clouds. IEEE Transactions on Cloud Computing 10, 2 (2020), 792\u2013804.","journal-title":"IEEE Transactions on Cloud Computing"},{"key":"e_1_3_1_3_2","first-page":"3243","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Barrett Thomas","year":"2020","unstructured":"Thomas Barrett, William Clements, Jakob Foerster, and Alex Lvovsky. 2020. Exploratory combinatorial optimization with reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence. 3243\u20133250."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.disopt.2006.10.011"},{"key":"e_1_3_1_5_2","article-title":"Scaling video analytics on constrained edge nodes","author":"Canel Christopher","year":"2019","unstructured":"Christopher Canel, Thomas Kim, Giulio Zhou, Conglong Li, Hyeontaek Lim, David G. Andersen, Michael Kaminsky, and Subramanya Dulloor. 2019. Scaling video analytics on constrained edge nodes. Proceedings of Machine Learning and Systems 2019, 1 (2019), 406\u2013417.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524273.3528178"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"e_1_3_1_8_2","article-title":"Delay-optimal distributed edge computation offloading with correlated computation and communication workloads","author":"Chen Mingyu","year":"2022","unstructured":"Mingyu Chen, Xiaowen Gong, and Yang Cao. 2022. Delay-optimal distributed edge computation offloading with correlated computation and communication workloads. IEEE Transactions on Mobile Computing 22, 10 (2022), 5846\u20135857.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/RTSS62706.2024.00014","volume-title":"Proceedings of the 2024 IEEE Real-Time Systems Symposium (RTSS)","author":"Chen Qiang","year":"2024","unstructured":"Qiang Chen and Changlong Li. 2024. Argus: Real-time HQ video decoding with CPU coordinating on consumer devices. In Proceedings of the 2024 IEEE Real-Time Systems Symposium (RTSS). 43\u201356."},{"issue":"23","key":"e_1_3_1_10_2","doi-asserted-by":"crossref","first-page":"23941","DOI":"10.1109\/JIOT.2022.3189035","article-title":"Joint front\u2013edge\u2013cloud IoVT analytics: Resource-effective design and scheduling","volume":"9","author":"Chen Youjia","year":"2022","unstructured":"Youjia Chen, Tiesong Zhao, Peng Cheng, Ming Ding, and Chang Wen Chen. 2022. Joint front\u2013edge\u2013cloud IoVT analytics: Resource-effective design and scheduling. IEEE Internet of Things Journal 9, 23 (2022), 23941\u201323953.","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3172402"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3218527"},{"key":"e_1_3_1_13_2","first-page":"1383","volume-title":"Proceedings of the 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS)","author":"Elgamal Tarek","year":"2020","unstructured":"Tarek Elgamal, Shu Shi, Varun Gupta, Rittwik Jana, and Klara Nahrstedt. 2020. Sieve: Semantically encoded video analytics on edge and cloud. In Proceedings of the 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS). 1383\u20131388."},{"key":"e_1_3_1_14_2","first-page":"115","volume-title":"Proceedings of the Annual International Conference on Mobile Computing and Networking (MobiCom)","author":"Fang Biyi","year":"2018","unstructured":"Biyi Fang, Xiao Zeng, and Mi Zhang. 2018. Nestdnn: Resource-aware multi-tenant on-device deep learning for continuous mobile vision. In Proceedings of the Annual International Conference on Mobile Computing and Networking (MobiCom). 115\u2013127."},{"key":"e_1_3_1_15_2","first-page":"15","volume-title":"Proceedings of the 2024 IEEE Real-Time Systems Symposium (RTSS)","author":"Gao Chuanchao","year":"2024","unstructured":"Chuanchao Gao, Niraj Kumar, and Arvind Easwaran. 2024. Energy-efficient real-time job mapping and resource management in mobile-edge computing. In Proceedings of the 2024 IEEE Real-Time Systems Symposium (RTSS). 15\u201328."},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3698857"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3236256"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3173685"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2022.3214614"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900594"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3014013"},{"key":"e_1_3_1_22_2","first-page":"1","volume-title":"Proceedings of the 26th Annual International Conference on Mobile Computing and Networking (MobiCom)","author":"Huang Jin","year":"2020","unstructured":"Jin Huang, Colin Samplawski, Deepak Ganesan, Benjamin Marlin, and Heesung Kwon. 2020. Clio: Enabling automatic compilation of deep learning pipelines across IoT and cloud. In Proceedings of the 26th Annual International Conference on Mobile Computing and Networking (MobiCom). 1\u201312."},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267828"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900349"},{"issue":"1","key":"e_1_3_1_25_2","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1109\/TCC.2024.3525076","article-title":"Cloud-edge collaborative service architecture with large-tiny models based on deep reinforcement learning","volume":"13","author":"Ji Xiaofeng","year":"2025","unstructured":"Xiaofeng Ji, Faming Gong, Nuanlai Wang, Junjie Xu, and Xing Yan. 2025. Cloud-edge collaborative service architecture with large-tiny models based on deep reinforcement learning. IEEE Transactions on Cloud Computing 13, 1 (2025), 288\u2013302.","journal-title":"IEEE Transactions on Cloud Computing"},{"key":"e_1_3_1_26_2","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1109\/RTSS62706.2024.00024","volume-title":"Proceedings of the 2024 IEEE Real-Time Systems Symposium (RTSS)","author":"Jiang Zhe","year":"2024","unstructured":"Zhe Jiang, Shuai Zhao, Ran Wei, Xin Si, Gang Chen, and Nan Guan. 2024. ROTA-I\/O: Hardware\/algorithm co-design for real-time i\/o control with improved timing accuracy and robustness. In Proceedings of the 2024 IEEE Real-Time Systems Symposium (RTSS). 174\u2013186."},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3672608.3707792"},{"key":"e_1_3_1_28_2","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","author":"Li Chenghao","year":"2021","unstructured":"Chenghao Li, Tonghan Wang, Chengjie Wu, Qianchuan Zhao, Jun Yang, and Chongjie Zhang. 2021. Celebrating diversity in shared multi-agent reinforcement learning. Advances in Neural Information Processing Systems 2021, 34 (2021), 3991\u20134002.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_29_2","first-page":"409","volume-title":"Proceedings of the ACM\/IEEE Design Automation Conference (DAC)","author":"Li Min","year":"2021","unstructured":"Min Li, Yu Li, Ye Tian, Li Jiang, and Qiang Xu. 2021. AppealNet: An efficient and highly-accurate edge\/cloud collaborative architecture for DNN inference. In Proceedings of the ACM\/IEEE Design Automation Conference (DAC). 409\u2013414."},{"issue":"1","key":"e_1_3_1_30_2","first-page":"648","article-title":"Resource price-aware offloading for edge-cloud collaboration: A two-timescale online control approach","volume":"10","author":"Li Rui","year":"2019","unstructured":"Rui Li, Zhi Zhou, Xu Chen, and Qing Ling. 2019. Resource price-aware offloading for edge-cloud collaboration: A two-timescale online control approach. IEEE Transactions on Cloud Computing 10, 1 (2019), 648\u2013661.","journal-title":"IEEE Transactions on Cloud Computing"},{"key":"e_1_3_1_31_2","article-title":"A unified framework for joint sensing and communication in resource constrained mobile edge networks","author":"Li Xiaoqian","year":"2022","unstructured":"Xiaoqian Li, Gang Feng, Yao Sun, Shuang Qin, and Yijing Liu. 2022. A unified framework for joint sensing and communication in resource constrained mobile edge networks. IEEE Transactions on Mobile Computing 22, 10 (2022), 5643\u20135656.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3647750.3647765"},{"key":"e_1_3_1_33_2","first-page":"385","volume-title":"Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems","author":"Lin Changyao","year":"2025","unstructured":"Changyao Lin, Zhenming Chen, Ziyang Zhang, and Jie Liu. 2025. E3: Early exiting with explainable ai for real-time and accurate DNN inference in edge-cloud systems. In Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems. 385\u2013397."},{"key":"e_1_3_1_34_2","first-page":"421","volume-title":"Proceedings of the ACM\/IEEE Design Automation Conference (DAC)","author":"Liu Ruoyang","year":"2021","unstructured":"Ruoyang Liu, Lu Zhang, Jingyu Wang, Huazhong Yang, and Yongpan Liu. 2021. PETRI: Reducing bandwidth requirement in smart surveillance by edge-cloud collaborative adaptive frame clustering and pipelined bidirectional tracking. In Proceedings of the ACM\/IEEE Design Automation Conference (DAC). 421\u2013426."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548033"},{"key":"e_1_3_1_36_2","first-page":"505","volume-title":"Proceedings of the ACM\/IEEE Design Automation Conference (DAC)","author":"Liu Weihong","year":"2022","unstructured":"Weihong Liu, Jiawei Geng, Zongwei Zhu, Jing Cao, and Zirui Lian. 2022. Sniper: Cloud-edge collaborative inference scheduling with neural network similarity modeling. In Proceedings of the ACM\/IEEE Design Automation Conference (DAC). 505\u2013510."},{"issue":"2","key":"e_1_3_1_37_2","first-page":"534","article-title":"Ace-Sniper: Cloud\u2013edge collaborative scheduling framework with dnn inference latency modeling on heterogeneous devices","volume":"43","author":"Liu Weihong","year":"2023","unstructured":"Weihong Liu, Jiawei Geng, Zongwei Zhu, Yang Zhao, Cheng Ji, Changlong Li, Zirui Lian, and Xuehai Zhou. 2023. Ace-Sniper: Cloud\u2013edge collaborative scheduling framework with dnn inference latency modeling on heterogeneous devices. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 43, 2 (2023), 534\u2013547.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548249"},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1109\/SEC50012.2020.00012","volume-title":"Proceedings of the 2020 IEEE\/ACM Symposium on Edge Computing (SEC)","author":"Nigade Vinod","year":"2020","unstructured":"Vinod Nigade, Lin Wang, and Henri Bal. 2020. Clownfish: Edge and cloud symbiosis for video stream analytics. In Proceedings of the 2020 IEEE\/ACM Symposium on Edge Computing (SEC). 55\u201369."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3362031"},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1145\/3676151.3719355","volume-title":"Proceedings of the 16th ACM\/SPEC International Conference on Performance Engineering","author":"Saha Ratul Kishore","year":"2025","unstructured":"Ratul Kishore Saha, Sparsh Mittal, Rekha Singhal, and Manoj Nambiar. 2025. CADAEC: Content-aware deployment of AI workloads in Edge-cloud ecosystem. In Proceedings of the 16th ACM\/SPEC International Conference on Performance Engineering. 298\u2013308."},{"issue":"3","key":"e_1_3_1_42_2","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/s10586-024-04828-2","article-title":"Reinforcement learning-based task scheduling for heterogeneous computing in end-edge-cloud environment","volume":"28","author":"Shen Wangbo","year":"2025","unstructured":"Wangbo Shen, Weiwei Lin, Wentai Wu, Haijie Wu, and Keqin Li. 2025. Reinforcement learning-based task scheduling for heterogeneous computing in end-edge-cloud environment. Cluster Computing 28, 3 (2025), 179.","journal-title":"Cluster Computing"},{"key":"e_1_3_1_43_2","article-title":"Prediction-based resource deployment and task scheduling in edge-cloud collaborative computing","author":"Su Mingfeng","year":"2022","unstructured":"Mingfeng Su, Guojun Wang, and Kim-Kwang Raymond Choo. 2022. Prediction-based resource deployment and task scheduling in edge-cloud collaborative computing. Wireless Communications and Mobile Computing 2022, 1 (2022), 1\u201317.","journal-title":"Wireless Communications and Mobile Computing"},{"key":"e_1_3_1_44_2","article-title":"Semantic knowledge base-enabled zero-shot multi-level feature transmission optimization","author":"Sun Yaping","year":"2023","unstructured":"Yaping Sun, Hao Chen, Xiaodong Xu, Ping Zhang, and Shuguang Cui. 2023. Semantic knowledge base-enabled zero-shot multi-level feature transmission optimization. IEEE Transactions on Wireless Communications 23, 5 (2023), 4904\u20134917.","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"e_1_3_1_45_2","first-page":"2531","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Vanh\u00e9e Lo\u00efs","year":"2019","unstructured":"Lo\u00efs Vanh\u00e9e, Laurent Jeanpierre, and Abdel-Illah Mouaddib. 2019. Augmenting markov decision processes with advising. In Proceedings of the AAAI Conference on Artificial Intelligence. 2531\u20132538."},{"key":"e_1_3_1_46_2","first-page":"1","volume-title":"Proceedings of the 2024 International Symposium on Parallel Computing and Distributed Systems (PCDS)","author":"Vechprasit Natthasak","year":"2024","unstructured":"Natthasak Vechprasit, Annop Monsakul, and Pramuk Boonsieng. 2024. Performance analysis of image classification between edge and cloud computing. In Proceedings of the 2024 International Symposium on Parallel Computing and Distributed Systems (PCDS). 1\u20138."},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3377156"},{"key":"e_1_3_1_48_2","first-page":"2519","volume-title":"Proceedings of the IEEE Conference on Computer Communications (INFOCOM)","author":"Wang Shibo","year":"2020","unstructured":"Shibo Wang, Shusen Yang, and Cong Zhao. 2020. SurveilEdge: Real-time video query based on collaborative cloud-edge deep learning. In Proceedings of the IEEE Conference on Computer Communications (INFOCOM). 2519\u20132528."},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534088.3534352"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3393230"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102907"},{"key":"e_1_3_1_52_2","first-page":"294","volume-title":"Proceedings of the 2024 IEEE Real-Time Systems Symposium (RTSS)","author":"Xu Yuhang","year":"2024","unstructured":"Yuhang Xu, Zixuan Liu, Xinzhe Fu, Shengzhong Liu, Fan Wu, and Guihai Chen. 2024. FLEX: Adaptive task batch scheduling with elastic fusion in multi-modal multi-view machine perception. In Proceedings of the 2024 IEEE Real-Time Systems Symposium (RTSS). 294\u2013307."},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3107424"},{"key":"e_1_3_1_54_2","first-page":"505","volume-title":"Proceedings of the 19th European Conference on Computer Systems","author":"Yang Qizheng","year":"2024","unstructured":"Qizheng Yang, Tianyi Yang, Mingcan Xiang, Lijun Zhang, Haoliang Wang, Marco Serafini, and Hui Guan. 2024. GMorph: Accelerating multi-dnn inference via model fusion. In Proceedings of the 19th European Conference on Computer Systems. 505\u2013523."},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613914"},{"issue":"4","key":"e_1_3_1_56_2","doi-asserted-by":"crossref","first-page":"149103","DOI":"10.1007\/s11432-023-3957-4","article-title":"Adaptive joint configuration optimization for collaborative inference in edge-cloud systems","volume":"67","author":"Yang Zheming","year":"2024","unstructured":"Zheming Yang, Wen Ji, and Zhi Wang. 2024. Adaptive joint configuration optimization for collaborative inference in edge-cloud systems. Science China Information Sciences 67, 4 (2024), 149103.","journal-title":"Science China Information Sciences"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3052778"},{"issue":"1","key":"e_1_3_1_58_2","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1109\/TMC.2021.3075947","article-title":"SOAR: Smart online aggregated reservation for mobile edge computing brokerage services","volume":"22","author":"Zang Shizhe","year":"2021","unstructured":"Shizhe Zang, Wei Bao, Phee Lep Yeoh, Branka Vucetic, and Yonghui Li. 2021. SOAR: Smart online aggregated reservation for mobile edge computing brokerage services. IEEE Transactions on Mobile Computing 22, 1 (2021), 527\u2013540.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_1_59_2","first-page":"377","volume-title":"Proceedings of the USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Zhang Haoyu","year":"2017","unstructured":"Haoyu Zhang, Ganesh Ananthanarayanan, Peter Bodik, Matthai Philipose, Paramvir Bahl, and Michael J Freedman. 2017. Live video analytics at scale with approximation and delay-tolerance. In Proceedings of the USENIX Symposium on Networked Systems Design and Implementation (NSDI). 377\u2013392."},{"key":"e_1_3_1_60_2","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1145\/3458305.3463377","volume-title":"Proceedings of the 12th ACM multimedia systems conference","author":"Zhang Miao","year":"2021","unstructured":"Miao Zhang, Fangxin Wang, Yifei Zhu, Jiangchuan Liu, and Zhi Wang. 2021. Towards cloud-edge collaborative online video analytics with fine-grained serverless pipelines. In Proceedings of the 12th ACM multimedia systems conference. 80\u201393."},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547807"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2997091"},{"key":"e_1_3_1_63_2","article-title":"EdgeAdaptor: Online configuration adaption, model selection and resource provisioning for edge DNN inference serving at scale","author":"Zhao Kongyange","year":"2022","unstructured":"Kongyange Zhao, Zhi Zhou, Xu Chen, Ruiting Zhou, Xiaoxi Zhang, Shuai Yu, and Di Wu. 2022. EdgeAdaptor: Online configuration adaption, model selection and resource provisioning for edge DNN inference serving at scale. IEEE Transactions on Mobile Computing 22, 10 (2022), 5870\u20135886.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557080"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T15:54:03Z","timestamp":1782402843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":65,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3803806"],"URL":"https:\/\/doi.org\/10.1145\/3803806","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"value":"1544-3566","type":"print"},{"value":"1544-3973","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2025-09-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}