{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:44:24Z","timestamp":1777653864671,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T00:00:00Z","timestamp":1698364800000},"content-version":"vor","delay-in-days":1,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2038658, IIS-2107200"],"award-info":[{"award-number":["CNS-2038658, IIS-2107200"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612412","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"1698-1706","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["ScaleFlow: Efficient Deep Vision Pipeline with Closed-Loop Scale-Adaptive Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9376-0880","authenticated-orcid":false,"given":"Yuyang","family":"Leng","sequence":"first","affiliation":[{"name":"George Mason University, Fairfax, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9710-6116","authenticated-orcid":false,"given":"Renyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2714-7550","authenticated-orcid":false,"given":"Hongpeng","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4650-7125","authenticated-orcid":false,"given":"Songqing","family":"Chen","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7446-1430","authenticated-orcid":false,"given":"Shuochao","family":"Yao","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. Intel Neural Compute Stick 2. https:\/\/rb.gy\/nv8h4m."},{"key":"e_1_3_2_1_2_1","unstructured":"2022. Nvidia Jetson AGX Xavier. https:\/\/rb.gy\/samxtg."},{"key":"e_1_3_2_1_3_1","volume-title":"Multiresolution signal decomposition: transforms, subbands, and wavelets","author":"Akansu Ali N","unstructured":"Ali N Akansu, Richard A Haddad, and Paul A Haddad. 2001. Multiresolution signal decomposition: transforms, subbands, and wavelets. Academic press."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360044"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"e_1_3_2_1_6_1","volume-title":"Davide Del Testa","author":"Bojarski Mariusz","year":"2016","unstructured":"Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, et al. 2016. End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems. 155--168","author":"Yu-Han Chen Tiffany","year":"2015","unstructured":"Tiffany Yu-Han Chen, Lenin Ravindranath, Shuo Deng, Paramvir Bahl, and Hari Balakrishnan. 2015. Glimpse: Continuous, real-time object recognition on mobile devices. In Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems. 155--168."},{"key":"e_1_3_2_1_9_1","volume-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to 1 or-1. arXiv preprint arXiv:1602.02830","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to 1 or-1. arXiv preprint arXiv:1602.02830 (2016)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405887"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Machine Learning. PMLR, 1745--1754","author":"Dziedzic Adam","year":"2019","unstructured":"Adam Dziedzic, John Paparrizos, Sanjay Krishnan, Aaron Elmore, and Michael Franklin. 2019. Band-limited training and inference for convolutional neural networks. In International Conference on Machine Learning. PMLR, 1745--1754."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131895"},{"key":"e_1_3_2_1_14_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_1_15_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_16_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_17_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Hsieh Kevin","year":"2018","unstructured":"Kevin Hsieh, Ganesh Ananthanarayanan, Peter Bodik, Shivaram Venkataraman, Paramvir Bahl, Matthai Philipose, Phillip B Gibbons, and Onur Mutlu. 2018. Focus: Querying large video datasets with low latency and low cost. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 269--286."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483274"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917494"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3569468"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460700"},{"key":"e_1_3_2_1_26_1","first-page":"776","article-title":"Image segmentation by using histogram thresholding","volume":"2","author":"Raju P Daniel Ratna","year":"2012","unstructured":"P Daniel Ratna Raju and G Neelima. 2012. Image segmentation by using histogram thresholding. International Journal of Computer Science Engineering and Technology 2, 1 (2012), 776--779.","journal-title":"International Journal of Computer Science Engineering and Technology"},{"key":"e_1_3_2_1_27_1","volume-title":"Searching for activation functions. arXiv preprint arXiv:1710.05941","author":"Ramachandran Prajit","year":"2017","unstructured":"Prajit Ramachandran, Barret Zoph, and Quoc V Le. 2017. Searching for activation functions. arXiv preprint arXiv:1710.05941 (2017)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_1_31_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_32_1","volume-title":"Spectral representations for convolutional neural networks. Advances in neural information processing systems 28","author":"Rippel Oren","year":"2015","unstructured":"Oren Rippel, Jasper Snoek, and Ryan P Adams. 2015. Spectral representations for convolutional neural networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_33_1","volume-title":"On the kronecker product. Master's thesis","author":"Schacke Kathrin","unstructured":"Kathrin Schacke. 2004. On the kronecker product. Master's thesis, University of Waterloo (2004)."},{"key":"e_1_3_2_1_34_1","volume-title":"Scale-Equivariant Steerable Networks. In International Conference on Learning Representations.","author":"Sosnovik Ivan","year":"2020","unstructured":"Ivan Sosnovik, Micha\u0140 Szmaja, and Arnold Smeulders. 2020. Scale-Equivariant Steerable Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 6105--6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_3_2_1_37_1","first-page":"1922","article-title":"Fcos: A simple and strong anchor-free object detector","volume":"44","author":"Tian Zhi","year":"2020","unstructured":"Zhi Tian, Chunhua Shen, Hao Chen, and Tong He. 2020. Fcos: A simple and strong anchor-free object detector. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 4 (2020), 1922--1933.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_38_1","volume-title":"Scale-Equalizing Pyramid Convolution for Object Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Wang Xinjiang","year":"2020","unstructured":"Xinjiang Wang, Shilong Zhang, Zhuoran Yu, Litong Feng, and Wayne Zhang. 2020. Scale-Equalizing Pyramid Convolution for Object Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_39_1","volume-title":"Cnnpack: Packing convolutional neural networks in the frequency domain. Advances in neural information processing systems 29","author":"Wang Yunhe","year":"2016","unstructured":"Yunhe Wang, Chang Xu, Shan You, Dacheng Tao, and Chao Xu. 2016. Cnnpack: Packing convolutional neural networks in the frequency domain. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_40_1","volume-title":"Deep scale-spaces: Equivariance over scale. Advances in Neural Information Processing Systems 32","author":"Worrall Daniel","year":"2019","unstructured":"Daniel Worrall and Max Welling. 2019. Deep scale-spaces: Equivariance over scale. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3274840"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3161181"},{"key":"e_1_3_2_1_43_1","volume-title":"Enhancing geometric factors in model learning and inference for object detection and instance segmentation","author":"Zheng Zhaohui","year":"2021","unstructured":"Zhaohui Zheng, Ping Wang, Dongwei Ren, Wei Liu, Rongguang Ye, Qinghua Hu, and Wangmeng Zuo. 2021. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Transactions on Cybernetics (2021)."},{"key":"e_1_3_2_1_44_1","unstructured":"Xingyi Zhou Dequan Wang and Philipp Kr\u00e4henb\u00fchl. 2019. Objects as points. arXiv preprint arXiv:1904.07850 (2019)"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612412","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612412","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:03:12Z","timestamp":1755820992000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":44,"alternative-id":["10.1145\/3581783.3612412","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612412","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}