{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T03:48:14Z","timestamp":1782791294083,"version":"3.54.5"},"reference-count":9,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["GetMobile: Mobile Comp. and Comm."],"published-print":{"date-parts":[[2025,10,29]]},"abstract":"<jats:p>Deep Neural Networks (DNNs) are crucial for applications like autonomous driving, augmented reality, and mixed reality. Growing concerns about latency and privacy increasingly require deploying task-specific networks on mobile and edge devices. Extensive research focuses on accelerating DNNs while preserving output quality, particularly through model adjustments tailored for resource-limited devices [1-5].<\/jats:p>","DOI":"10.1145\/3774505.3774517","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T22:19:07Z","timestamp":1761862747000},"page":"35-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["On-Device Dynamic DNN Inference through Spatial Sparsity Exploitation"],"prefix":"10.1145","volume":"29","author":[{"given":"Renyuan","family":"Liu","sequence":"first","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Leng","sequence":"additional","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilei","family":"Tian","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaohan","family":"Hu","sequence":"additional","affiliation":[{"name":"Global Technology Applied Research Center at JPMorgan Chase"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Chen","sequence":"additional","affiliation":[{"name":"Trustworthy Machine Learning and Computer Vision at Global Technology Applied Research, JPMorgan Chase"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuochao","family":"Yao","sequence":"additional","affiliation":[{"name":"George Mason University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,30]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Proceedings of the IEEE\/ CVF Conference on Computer Vision and Pattern Recognition, 2320--2329","author":"Verelst Thomas","unstructured":"Thomas Verelst and Tinne Tuytelaars. Dynamic convolutions: Exploiting spatial sparsity for faster inference. 2020. Proceedings of the IEEE\/ CVF Conference on Computer Vision and Pattern Recognition, 2320--2329."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430898"},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the 29th Annual International Conference on Mobile Computing and Networking, 1--17","author":"Wen Hao","unstructured":"Hao Wen, Yuanchun Li, Zunshuai Zhang, Shiqi Jiang, Xiaozhou Ye, Ye Ouyang, Yaqin Zhang, and Yunxin Liu. Adaptivenet: Post-deployment neural architecture adaptation for diverse edge environments. 2023. Proceedings of the 29th Annual International Conference on Mobile Computing and Networking, 1--17."},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the 23rd Annual International Conference on Mobile Systems, Applications and Services.","author":"Liu Renyuan","unstructured":"Renyuan Liu, Yuyang Leng, Kaiyan Liu, Shaohan Hu, Chun-Fu Chen, Peijun Zhao, Heechul Yun, and Shuochao Yao. Daf: An efficient end-to-end dynamic activation framework for on-device dnn training. 2025. Proceedings of the 23rd Annual International Conference on Mobile Systems, Applications and Services."},{"key":"e_1_2_1_5_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Guo Peizhen","year":"2021","unstructured":"Peizhen Guo, Bo Hu, and Wenjun Hu. 2021. Mistify: Automating {DNN} model porting for {On-Device} inference at the edge. 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21), 705--719."},{"key":"e_1_2_1_6_1","volume-title":"Nvidia cusparse","author":"NVIDIA.","year":"2023","unstructured":"NVIDIA. Nvidia cusparse, 2023. https:\/\/docs. nvidia.com\/cuda\/cusparse."},{"key":"e_1_2_1_7_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 8711--8720","author":"Ren Mengye","unstructured":"Mengye Ren, Andrei Pokrovsky, Bin Yang, and Raquel Urtasun. Sbnet: Sparse blocks network for fast inference. 2018. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 8711--8720."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2092"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699348"}],"container-title":["GetMobile: Mobile Computing and Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774505.3774517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T03:42:42Z","timestamp":1782790962000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774505.3774517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":9,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,10,29]]}},"alternative-id":["10.1145\/3774505.3774517"],"URL":"https:\/\/doi.org\/10.1145\/3774505.3774517","relation":{},"ISSN":["2375-0529","2375-0537"],"issn-type":[{"value":"2375-0529","type":"print"},{"value":"2375-0537","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"assertion":[{"value":"2025-10-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}