{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:55:07Z","timestamp":1750308907866,"version":"3.41.0"},"reference-count":7,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T00:00:00Z","timestamp":1665100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["GetMobile: Mobile Comp. and Comm."],"published-print":{"date-parts":[[2022,10,7]]},"abstract":"<jats:p>While multi-modal deep learning is useful in distributed sensing tasks like human tracking, activity recognition, and audio and video analysis, deploying state-of-the-art multi-modal models in a wirelessly networked sensor system poses unique challenges. The data sizes for different modalities can be highly asymmetric (e.g., video vs. audio), and these differences can lead to significant delays between streams in the presence of wireless dynamics. Therefore, a slow stream can significantly slow down a multimodal inference system in the cloud, leading to either increased latency (when blocked by the slow stream) or degradation in inference accuracy (if inference proceeds without waiting).<\/jats:p>","DOI":"10.1145\/3568113.3568121","type":"journal-article","created":{"date-parts":[[2022,10,12]],"date-time":"2022-10-12T04:06:47Z","timestamp":1665547607000},"page":"23-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Low-Latency Speculative Inference on Distributed Multi-Modal Data Streams"],"prefix":"10.1145","volume":"26","author":[{"given":"Tianxing","family":"Li","sequence":"first","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Huang","sequence":"additional","affiliation":[{"name":"UMass Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erik","family":"Risinger","sequence":"additional","affiliation":[{"name":"UMass Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepak","family":"Ganesan","sequence":"additional","affiliation":[{"name":"UMass Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,11]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of Asian Conference on Computer Vision, 87--103","author":"Chung Joon Son","year":"2016","unstructured":"Joon Son Chung and Andrew Zisserman . 2016 . Lip reading in the wild . Proceedings of Asian Conference on Computer Vision, 87--103 . Springer. Joon Son Chung and Andrew Zisserman. 2016. Lip reading in the wild. Proceedings of Asian Conference on Computer Vision, 87--103. Springer."},{"volume-title":"Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems, 127--140","author":"Stisen Allan","key":"e_1_2_1_3_1","unstructured":"Allan Stisen , Henrik Blunck , Sourav Bhattacharya , Thor Siiger Prentow , Mikkel Baun Kj\u00e6rgaard , Anind Dey , Tobias Sonne , and Mads M\u00f8ller Jensen . Smart devices are different: Assessing and mitigating mobile sensing heterogeneities for activity recognition. 2015 . Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems, 127--140 . Allan Stisen, Henrik Blunck, Sourav Bhattacharya, Thor Siiger Prentow, Mikkel Baun Kj\u00e6rgaard, Anind Dey, Tobias Sonne, and Mads M\u00f8ller Jensen. Smart devices are different: Assessing and mitigating mobile sensing heterogeneities for activity recognition. 2015. Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems, 127--140."},{"volume-title":"Proceedings of the European Conference on Computer Vision (ECCV), 247--263","author":"Tian Yapeng","key":"e_1_2_1_4_1","unstructured":"Yapeng Tian , Jing Shi , Bochen Li , Zhiyao Duan , and Chenliang Xu . Audiovisual event localization in unconstrained videos. 2018 . Proceedings of the European Conference on Computer Vision (ECCV), 247--263 . Yapeng Tian, Jing Shi, Bochen Li, Zhiyao Duan, and Chenliang Xu. Audiovisual event localization in unconstrained videos. 2018. Proceedings of the European Conference on Computer Vision (ECCV), 247--263."},{"volume-title":"Proceedings of the 8th ACM on Multimedia Systems Conference, 62--75","author":"Bhat Divyashri","key":"e_1_2_1_5_1","unstructured":"Divyashri Bhat , Amr Rizk , Michael Zink , and Ralf Steinmetz . Network assisted content distribution for adaptive bitrate video streaming. 2017 . Proceedings of the 8th ACM on Multimedia Systems Conference, 62--75 . Divyashri Bhat, Amr Rizk, Michael Zink, and Ralf Steinmetz. Network assisted content distribution for adaptive bitrate video streaming. 2017. Proceedings of the 8th ACM on Multimedia Systems Conference, 62--75."},{"volume-title":"Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, 253--266","author":"Jiang Junchen","key":"e_1_2_1_6_1","unstructured":"Junchen Jiang , Ganesh Ananthanarayanan , Peter Bodik , Siddhartha Sen , and Ion Stoica . Chameleon : Scalable adaptation of video analytics. 2018 . Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, 253--266 . Junchen Jiang, Ganesh Ananthanarayanan, Peter Bodik, Siddhartha Sen, and Ion Stoica. Chameleon: Scalable adaptation of video analytics. 2018. Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, 253--266."},{"key":"e_1_2_1_7_1","volume":"201","author":"Zhang Haoyu","unstructured":"Haoyu Zhang , Ganesh Ananthanarayanan , Peter Bodik , Matthai Philipose , Paramvir Bahl , and Michael J. Freedman. 201 7. Live video analytics at scale with approximation and delay-tolerance. Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation. NSDI '17, 377--392. 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. Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation. NSDI '17, 377--392.","journal-title":"Michael J. Freedman."}],"container-title":["GetMobile: Mobile Computing and Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568113.3568121","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3568113.3568121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:26:15Z","timestamp":1750281975000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568113.3568121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,7]]},"references-count":7,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,10,7]]}},"alternative-id":["10.1145\/3568113.3568121"],"URL":"https:\/\/doi.org\/10.1145\/3568113.3568121","relation":{},"ISSN":["2375-0529","2375-0537"],"issn-type":[{"type":"print","value":"2375-0529"},{"type":"electronic","value":"2375-0537"}],"subject":[],"published":{"date-parts":[[2022,10,7]]},"assertion":[{"value":"2022-10-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}