{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T06:55:37Z","timestamp":1766732137127,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","funder":[{"name":"Foundation for Food & Agriculture Research (FFAR) and McDonald\u2019s Corporation under the SMART Broiler Programme","award":["21-000053"],"award-info":[{"award-number":["21-000053"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1145\/3773276.3774285","type":"proceedings-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T08:16:18Z","timestamp":1766564178000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Video Analytics Inference Pipelines: A Case Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3799-5702","authenticated-orcid":false,"given":"Saeid","family":"Ghafouri","sequence":"first","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, Belfast, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9546-2809","authenticated-orcid":false,"given":"Yuming","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, Belfast, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8860-8082","authenticated-orcid":false,"given":"Katerine","family":"Diaz Chito","sequence":"additional","affiliation":[{"name":"Momentum 1.0, Queen's University Belfast, Belfast, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9574-4138","authenticated-orcid":false,"given":"Jes\u00fas","family":"Mart\u00ednez del Rinc\u00f3n","sequence":"additional","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, Belfast, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6831-2041","authenticated-orcid":false,"given":"Niamh","family":"O'Connell","sequence":"additional","affiliation":[{"name":"School of Biological Sciences, Queen's University Belfast, Belfast, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5868-9259","authenticated-orcid":false,"given":"Hans","family":"Vandierendonck","sequence":"additional","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, Belfast, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2025. CUDA Runtime API - CUDA Streams. https:\/\/docs.nvidia.com\/cuda\/cuda-runtime-api\/group__CUDART__STREAM.html."},{"key":"e_1_3_3_1_3_2","unstructured":"2025. Multi-Process Service (MPS). https:\/\/docs.nvidia.com\/deploy\/mps\/index.html."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Stevan Cakic Tomo Popovic Srdjan Krco Daliborka Nedic Dejan Babic and Ivan Jovovic. 2023. Developing edge AI computer vision for smart poultry farms using deep learning and HPC. Sensors 23 6 (2023) 3002.","DOI":"10.3390\/s23063002"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Mairead Campbell Paul Miller Katerine D\u00edaz-Chito Xin Hong Niall McLaughlin Farzad Parvinzamir Jes\u00fas\u00a0Mart\u00ednez Del\u00a0Rinc\u00f3n and Niamh O\u2019Connell. 2024. A computer vision approach to monitor activity in commercial broiler chickens using trajectory-based clustering analysis. Computers and Electronics in Agriculture 217 (2024) 108591.","DOI":"10.1016\/j.compag.2023.108591"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Mairead Campbell Paul Miller Katerine D\u00edaz-Chito Sean Irvine Mary Baxter Jes\u00fas\u00a0Mart\u00ednez Del\u00a0Rinc\u00f3n Xin Hong Niall McLaughlin Thianantha Arumugam and Niamh O\u2019Connell. 2025. Automated precision weighing: leveraging 2D video feature analysis and machine learning for live body weight estimation of broiler chickens. Smart Agricultural Technology 10 (2025) 100793.","DOI":"10.1016\/j.atech.2025.100793"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Stefania Cristina Vladimir Despotovic Rodrigo P\u00e9rez-Rodr\u00edguez and Slavisa Aleksic. 2024. Audio-and video-based human activity recognition systems in healthcare. IEEE Access 12 (2024) 8230\u20138245.","DOI":"10.1109\/ACCESS.2024.3353138"},{"key":"e_1_3_3_1_9_2","unstructured":"Zheng Ge Songtao Liu Feng Wang Zeming Li and Jian Sun. 2021. Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.08430 (2021)."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3680256.3721266"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486993"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Seungwoo Kum Seungtaek Oh Jeongcheol Yeom and Jaewon Moon. 2022. Optimization of edge resources for deep learning application with batch and model management. Sensors 22 17 (2022) 6717.","DOI":"10.3390\/s22176717"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Jie Lin Peng Yang Ning Zhang Feng Lyu Xianfu Chen and Li Yu. 2022. Low-latency edge video analytics for on-road perception of autonomous ground vehicles. IEEE Transactions on Industrial Informatics 19 2 (2022) 1512\u20131523.","DOI":"10.1109\/TII.2022.3181986"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Zhiyan Liu Qiao Lan and Kaibin Huang. 2023. Resource allocation for multiuser edge inference with batching and early exiting. IEEE Journal on Selected Areas in Communications 41 4 (2023) 1186\u20131200.","DOI":"10.1109\/JSAC.2023.3242724"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568501"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2015.17"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Yanjinlkham Myagmar-Ochir and Wooseong Kim. 2023. A survey of video surveillance systems in smart city. Electronics 12 17 (2023) 3567.","DOI":"10.3390\/electronics12173567"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Thanh-Tung Nguyen Lucas Liebe Nhat-Quang Tau Yuheng Wu Jinghan Cheng and Dongman Lee. 2025. OCTOPINF: Workload-Aware Inference Serving for Edge Video Analytics. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01277 (2025).","DOI":"10.1109\/PerCom64205.2025.00032"},{"key":"e_1_3_3_1_19_2","unstructured":"NVIDIA Corporation. 2023. DeepStream SDK Documentation. https:\/\/docs.nvidia.com\/metropolis\/deepstream\/dev-guide\/."},{"key":"e_1_3_3_1_20_2","first-page":"973","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Padmanabhan Arthi","year":"2023","unstructured":"Arthi Padmanabhan, Neil Agarwal, Anand Iyer, Ganesh Ananthanarayanan, Yuanchao Shu, Nikolaos Karianakis, Guoqing\u00a0Harry Xu, and Ravi Netravali. 2023. Gemel: Model merging for { Memory-Efficient}, { Real-Time} video analytics at the edge. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 973\u2013994."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.23919\/FRUCT64283.2024.10749903"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Francisco Romero Johann Hauswald Aditi Partap Daniel Kang Matei Zaharia and Christos Kozyrakis. 2022. Optimizing video analytics with declarative model relationships. Proceedings of the VLDB Endowment 16 3 (2022) 447\u2013460.","DOI":"10.14778\/3570690.3570695"},{"key":"e_1_3_3_1_23_2","first-page":"397","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero, Qian Li, Neeraja\u00a0J Yadwadkar, and Christos Kozyrakis. 2021. { INFaaS} : Automated model-less inference serving. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). 397\u2013411."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486972"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610231"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Ramasamy Srinivasagan Mohammed\u00a0Shawky El\u00a0Sayed Mohammed\u00a0Ibrahim Al-Rasheed and Ali\u00a0Saeed Alzahrani. 2025. Edge intelligence for poultry welfare: Utilizing tiny machine learning neural network processors for vocalization analysis. PloS one 20 1 (2025) e0316920.","DOI":"10.1371\/journal.pone.0316920"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_3"},{"key":"e_1_3_3_1_28_2","first-page":"59","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Wu Hao","year":"2024","unstructured":"Hao Wu, Yue Yu, Junxiao Deng, Shadi Ibrahim, Song Wu, Hao Fan, Ziyue Cheng, and Hai Jin. 2024. { StreamBox} : A Lightweight { GPU}{ SandBox} for Serverless Inference Workflow. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). 59\u201373."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006018"},{"key":"e_1_3_3_1_30_2","first-page":"1049","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Zhang Chengliang","year":"2019","unstructured":"Chengliang Zhang, Minchen Yu, Wei Wang, and Feng Yan. 2019. MArk: Exploiting cloud services for Cost-Effective, SLO-Aware machine learning inference serving. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). 1049\u20131062."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587584"}],"event":{"name":"BDCAT '25: IEEE\/ACM 12th International Conference on Big Data Computing, Applications and Technologies","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Nantes France","acronym":"BDCAT '25"},"container-title":["Proceedings of the IEEE\/ACM 12th International Conference on Big Data Computing, Applications and Technologies"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3773276.3774285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T06:52:24Z","timestamp":1766731944000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773276.3774285"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":30,"alternative-id":["10.1145\/3773276.3774285","10.1145\/3773276"],"URL":"https:\/\/doi.org\/10.1145\/3773276.3774285","relation":{},"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"2025-12-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}