{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T18:17:09Z","timestamp":1782152229147,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680561","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"11080-11088","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Towards Real-time Video Compressive Sensing on Mobile Devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2308-4388","authenticated-orcid":false,"given":"Miao","family":"Cao","sequence":"first","affiliation":[{"name":"Zhejiang University & Westlake University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3245-9265","authenticated-orcid":false,"given":"Lishun","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-901X","authenticated-orcid":false,"given":"Huan","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3938-5994","authenticated-orcid":false,"given":"Guoqing","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8311-7524","authenticated-orcid":false,"given":"Xin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Yuanhao Cai Jing Lin Xiaowan Hu Haoqian Wang Xin Yuan Yulun Zhang Radu Timofte and Luc Van Gool. 2022. Coarse-to-fine sparse transformer for hyperspectral image reconstruction. In ECCV."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Miao Cao Lishun Wang Huan Wang and Xin Yuan. 2024. A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging. In ECCV.","DOI":"10.1007\/978-3-031-72943-0_7"},{"key":"e_1_3_2_1_3_1","volume-title":"Hybrid CNNTransformer Architecture for Efficient Large-Scale Video Snapshot Compressive Imaging. IJCV","author":"Cao Miao","year":"2024","unstructured":"Miao Cao, Lishun Wang, Mingyu Zhu, and Xin Yuan. 2024. Hybrid CNNTransformer Architecture for Efficient Large-Scale Video Snapshot Compressive Imaging. IJCV (2024), 1--20."},{"key":"e_1_3_2_1_4_1","volume-title":"Mobile-former: Bridging mobilenet and transformer. In CVPR.","author":"Chen Yinpeng","year":"2022","unstructured":"Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Xiaoyi Dong, Lu Yuan, and Zicheng Liu. 2022. Mobile-former: Bridging mobilenet and transformer. In CVPR."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Ziheng Cheng Bo Chen Guanliang Liu Hao Zhang Ruiying Lu ZhengjueWang and Xin Yuan. 2021. Memory-efficient network for large-scale video compressive sensing. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01598"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161934"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2946567"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.871582"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1364\/OL.503788"},{"key":"e_1_3_2_1_10_1","volume-title":"Ghostnet: More features from cheap operations. In CVPR.","author":"Han Kai","year":"2020","unstructured":"Kai Han, YunheWang, Qi Tian, Jianyuan Guo, Chunjing Xu, and Chang Xu. 2020. Ghostnet: More features from cheap operations. In CVPR."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Yasunobu Hitomi Jinwei Gu Mohit Gupta Tomoo Mitsunaga and Shree K Nayar. 2011. Video from a single coded exposure photograph using a learned over-complete dictionary. In ICCV.","DOI":"10.1109\/ICCV.2011.6126254"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Andrew Howard Mark Sandler Grace Chu Liang-Chieh Chen Bo Chen Mingxing Tan Weijun Wang Yukun Zhu Ruoming Pang Vijay Vasudevan et al. 2019. Searching for mobilenetv3. In ICCV.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_2_1_13_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_14_1","volume-title":"Adam: A Method for Stochastic Optimization. In ICLR.","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_1_15_1","volume-title":"CasFormer: Cascaded transformers for fusion-aware computational hyperspectral imaging. Information Fusion","author":"Li Chenyu","year":"2024","unstructured":"Chenyu Li, Bing Zhang, Danfeng Hong, Jun Zhou, Gemine Vivone, Shutao Li, and Jocelyn Chanussot. 2024. CasFormer: Cascaded transformers for fusion-aware computational hyperspectral imaging. Information Fusion (2024), 102408."},{"key":"e_1_3_2_1_16_1","unstructured":"Yanyu Li Ju Hu Yang Wen Georgios Evangelidis Kamyar Salahi Yanzhi Wang Sergey Tulyakov and Jian Ren. 2023. Rethinking vision transformers for mobilenet size and speed. In ICCV."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2873587"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1364\/OL.505657"},{"key":"e_1_3_2_1_19_1","unstructured":"Ningning Ma Xiangyu Zhang Hai-Tao Zheng and Jian Sun. 2018. Shufflenet v2: Practical guidelines for efficient cnn architecture design. In ECCV."},{"key":"e_1_3_2_1_20_1","unstructured":"Andrew L Maas Awni Y Hannun Andrew Y Ng et al. 2013. Rectifier nonlinearities improve neural network acoustic models. In ICML."},{"key":"e_1_3_2_1_21_1","volume-title":"Rao Muhammad Anwer, and Fahad Shahbaz Khan.","author":"Maaz Muhammad","year":"2022","unstructured":"Muhammad Maaz, Abdelrahman Shaker, Hisham Cholakkal, Salman Khan, Syed Waqas Zamir, Rao Muhammad Anwer, and Fahad Shahbaz Khan. 2022. Edgenext: efficiently amalgamated cnn-transformer architecture for mobile vision applications. In ECCV."},{"key":"e_1_3_2_1_22_1","volume-title":"Edgevits: Competing light-weight cnns on mobile devices with vision transformers. In ECCV.","author":"Pan Junting","year":"2022","unstructured":"Junting Pan, Adrian Bulat, Fuwen Tan, Xiatian Zhu, Lukasz Dudziak, Hongsheng Li, Georgios Tzimiropoulos, and Brais Martinez. 2022. Edgevits: Competing light-weight cnns on mobile devices with vision transformers. In ECCV."},{"key":"e_1_3_2_1_23_1","volume-title":"Alex Sorkine- Hornung, and Luc Van Gool","author":"Pont-Tuset Jordi","year":"2017","unstructured":"Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Arbel\u00e1ez, Alex Sorkine- Hornung, and Luc Van Gool. 2017. The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.5140721"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Dikpal Reddy Ashok Veeraraghavan and Rama Chellappa. 2011. P2C2: Programmable pixel compressive camera for high speed imaging. In CVPR.","DOI":"10.1109\/CVPR.2011.5995542"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov and Liang- Chieh Chen. 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In CVPR.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_27_1","volume-title":"Mi-gan: A simple baseline for image inpainting on mobile devices. In ICCV.","author":"Sargsyan Andranik","year":"2023","unstructured":"Andranik Sargsyan, Shant Navasardyan, Xingqian Xu, and Humphrey Shi. 2023. Mi-gan: A simple baseline for image inpainting on mobile devices. In ICCV."},{"key":"e_1_3_2_1_28_1","unstructured":"Wenzhe Shi Jose Caballero Ferenc Husz\u00e1r Johannes Totz Andrew P Aitken Rob Bishop Daniel Rueckert and ZehanWang. 2016. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In CVPR."},{"key":"e_1_3_2_1_29_1","unstructured":"Yehui Tang Kai Han Jianyuan Guo Chang Xu Chao Xu and Yunhe Wang. 2022. GhostNetv2: Enhance cheap operation with long-range attention. In NeurIPS."},{"key":"e_1_3_2_1_30_1","volume-title":"Mobileone: An improved one millisecond mobile backbone. In CVPR.","author":"Anasosalu Vasu Pavan Kumar","year":"2023","unstructured":"Pavan Kumar Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel, and Anurag Ranjan. 2023. Mobileone: An improved one millisecond mobile backbone. In CVPR."},{"key":"e_1_3_2_1_31_1","volume-title":"Efficientsci: Densely connected network with space-time factorization for large-scale video snapshot compressive imaging. In CVPR.","author":"Wang Lishun","year":"2023","unstructured":"Lishun Wang, Miao Cao, and Xin Yuan. 2023. Efficientsci: Densely connected network with space-time factorization for large-scale video snapshot compressive imaging. In CVPR."},{"key":"e_1_3_2_1_32_1","first-page":"9072","article-title":"Spatial-temporal transformer for video snapshot compressive imaging","volume":"45","author":"Wang Lishun","year":"2022","unstructured":"Lishun Wang, Miao Cao, Yong Zhong, and Xin Yuan. 2022. Spatial-temporal transformer for video snapshot compressive imaging. TPAMI 45, 7 (2022), 9072-- 9089.","journal-title":"TPAMI"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1364\/PRJ.458231"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_1_35_1","volume-title":"Metasci: Scalable and adaptive reconstruction for video compressive sensing. In CVPR.","author":"Wang Zhengjue","year":"2021","unstructured":"Zhengjue Wang, Hao Zhang, Ziheng Cheng, Bo Chen, and Xin Yuan. 2021. Metasci: Scalable and adaptive reconstruction for video compressive sensing. In CVPR."},{"key":"e_1_3_2_1_36_1","unstructured":"Zhuoyuan Wu Jian Zhang and Chong Mou. 2021. Dense Deep Unfolding Network With 3D-CNN Prior for Snapshot Compressive Imaging. In ICCV."},{"key":"e_1_3_2_1_37_1","unstructured":"Chengshuai Yang Shiyu Zhang and Xin Yuan. 2022. Ensemble learning priors unfolding for scalable Snapshot Compressive Sensing. In ECCV."},{"key":"e_1_3_2_1_38_1","first-page":"106","article-title":"Compressive sensing by learning a Gaussian mixture model from measurements","volume":"24","author":"Yang Jianbo","year":"2014","unstructured":"Jianbo Yang, Xuejun Liao, Xin Yuan, Patrick Llull, David J Brady, Guillermo Sapiro, and Lawrence Carin. 2014. Compressive sensing by learning a Gaussian mixture model from measurements. TIP 24, 1 (2014), 106--119.","journal-title":"TIP"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Xin Yuan. 2016. Generalized alternating projection based total variation minimization for compressive sensing. In ICIP.","DOI":"10.1109\/ICIP.2016.7532817"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3023869"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Xin Yuan Yang Liu Jinli Suo and Qionghai Dai. 2020. Plug-and-play algorithms for large-scale snapshot compressive imaging. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00152"},{"key":"e_1_3_2_1_42_1","first-page":"1","article-title":"Plug-and- Play Algorithms for Video Snapshot Compressive Imaging","volume":"01","author":"Yuan Xin","year":"2021","unstructured":"Xin Yuan, Yang Liu, Jinli Suo, Fredo Durand, and Qionghai Dai. 2021. Plug-and- Play Algorithms for Video Snapshot Compressive Imaging. TPAMI 01 (2021), 1--1.","journal-title":"TPAMI"},{"key":"e_1_3_2_1_43_1","volume-title":"Fahad Shahbaz Khan, and Ming-Hsuan Yang","author":"Zamir SyedWaqas","year":"2022","unstructured":"SyedWaqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, and Ming-Hsuan Yang. 2022. Restormer: Efficient transformer for highresolution image restoration. In CVPR."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Jiangning Zhang Xiangtai Li Jian Li Liang Liu Zhucun Xue Boshen Zhang Zhengkai Jiang Tianxin Huang Yabiao Wang and Chengjie Wang. 2023. Rethinking mobile block for efficient attention-based models. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Siming Zheng and Xin Yuan. 2023. Unfolding framework with prior of convolution-transformer mixture and uncertainty estimation for video snapshot compressive imaging. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01170"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680561","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:45Z","timestamp":1750291425000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":45,"alternative-id":["10.1145\/3664647.3680561","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680561","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}