{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:47:09Z","timestamp":1787017629046,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:00:00Z","timestamp":1699747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["C4072-21G"],"award-info":[{"award-number":["C4072-21G"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["C4034-21G"],"award-info":[{"award-number":["C4034-21G"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["14214022"],"award-info":[{"award-number":["14214022"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202407"],"award-info":[{"award-number":["62202407"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Chinese University of Hong Kong","award":["4055167"],"award-info":[{"award-number":["4055167"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3625687.3625793","type":"proceedings-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T08:07:18Z","timestamp":1714118838000},"page":"111-124","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0032-2539","authenticated-orcid":false,"given":"Bufang","family":"Yang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2130-1385","authenticated-orcid":false,"given":"Lixing","family":"He","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2072-1502","authenticated-orcid":false,"given":"Neiwen","family":"Ling","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4433-5211","authenticated-orcid":false,"given":"Zhenyu","family":"Yan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1772-7751","authenticated-orcid":false,"given":"Guoliang","family":"Xing","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6750-6706","authenticated-orcid":false,"given":"Xian","family":"Shuai","sequence":"additional","affiliation":[{"name":"Noah's Ark Lab, Huawei Technologies, Shatin, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0432-5510","authenticated-orcid":false,"given":"Xiaozhe","family":"Ren","sequence":"additional","affiliation":[{"name":"Noah's Ark Lab, Huawei Technologies, Shatin, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9117-8247","authenticated-orcid":false,"given":"Xin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Noah's Ark Lab, Huawei Technologies, Shatin, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Michael Ahn Anthony Brohan Noah Brown Yevgen Chebotar Omar Cortes Byron David Chelsea Finn Keerthana Gopalakrishnan Karol Hausman Alex Herzog et al. 2022. Do As I Can and Not As I Say: Grounding Language in Robotic Affordances. In arXiv preprint arXiv:2204.01691."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302506.3310391"},{"key":"e_1_3_2_1_3_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation. 119--135","author":"Bhardwaj Romil","year":"2022","unstructured":"Romil Bhardwaj, Zhengxu Xia, Ganesh Ananthanarayanan, Junchen Jiang, Yuanchao Shu, Nikolaos Karianakis, Kevin Hsieh, Paramvir Bahl, and Ion Stoica. 2022. Ekya: Continuous learning of video analytics models on edge compute servers. In 19th USENIX Symposium on Networked Systems Design and Implementation. 119--135."},{"key":"e_1_3_2_1_4_1","unstructured":"Rishi Bommasani Drew A Hudson Ehsan Adeli Russ Altman Simran Arora Sydney von Arx Michael S Bernstein Jeannette Bohg Antoine Bosselut Emma Brunskill et al. 2021. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)."},{"key":"e_1_3_2_1_5_1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems 33 (2020), 1877--1901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","first-page":"1","article-title":"MobiVQA: Efficient On-Device Visual Question Answering","volume":"6","author":"Cao Qingqing","year":"2022","unstructured":"Qingqing Cao, Prerna Khanna, Nicholas D Lane, and Aruna Balasubramanian. 2022. MobiVQA: Efficient On-Device Visual Question Answering. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6, 2 (2022), 1--23.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_3_2_1_7_1","volume-title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance. arXiv preprint arXiv:2305.05176","author":"Chen Lingjiao","year":"2023","unstructured":"Lingjiao Chen, Matei Zaharia, and James Zou. 2023. FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance. arXiv preprint arXiv:2305.05176 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"e_1_3_2_1_9_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_10_1","volume-title":"Yu-Chiang Frank Wang, and Jia-Bin Huang","author":"Chen Wei-Yu","year":"2019","unstructured":"Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang. 2019. A closer look at few-shot classification. arXiv preprint arXiv:1904.04232 (2019)."},{"key":"e_1_3_2_1_11_1","unstructured":"Google Cloud and Vertex AI. 2021. [Online]. Available: https:\/\/cloud.google.com\/vertex-ai."},{"key":"e_1_3_2_1_12_1","volume-title":"Findings of the Association for Computational Linguistics: ACL","author":"Dai Wenliang","year":"2022","unstructured":"Wenliang Dai, Lu Hou, Lifeng Shang, Xin Jiang, Qun Liu, and Pascale Fung. 2022. Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation. In Findings of the Association for Computational Linguistics: ACL 2022. Association for Computational Linguistics, Dublin, Ireland, 2383--2395."},{"key":"e_1_3_2_1_13_1","volume-title":"Edge AI chip shipments by device worldwide 2020 and","year":"2024","unstructured":"Deloitte. 2019. Edge AI chip shipments by device worldwide 2020 and 2024. https:\/\/www.statista.com\/statistics\/1084670\/edge-ai-chips-shipment-worldwide\/."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430735"},{"key":"e_1_3_2_1_16_1","volume-title":"2017 IEEE 37th International Conference on Distributed Computing Systems. IEEE, 276--286","author":"Drolia Utsav","year":"2017","unstructured":"Utsav Drolia, Katherine Guo, Jiaqi Tan, Rajeev Gandhi, and Priya Narasimhan. 2017. Cachier: Edge-caching for recognition applications. In 2017 IEEE 37th International Conference on Distributed Computing Systems. IEEE, 276--286."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3322706.3361996"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360020"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","volume-title":"NIPS Deep Learning and Representation Learning Workshop.","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. In NIPS Deep Learning and Representation Learning Workshop."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_2_1_23_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_24_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_25_1","first-page":"153","article-title":"mmSampler: Efficient Frame Sampler for Multimodal Video Retrieval","volume":"4","author":"Hu Zhiming","year":"2022","unstructured":"Zhiming Hu, Ning Ye, and Iqbal Mohomed. 2022. mmSampler: Efficient Frame Sampler for Multimodal Video Retrieval. Proceedings of Machine Learning and Systems 4 (2022), 153--171.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 28th Annual International Conference on Mobile Computing and Networking. 200--213","author":"Huang Kai","year":"2022","unstructured":"Kai Huang and Wei Gao. 2022. Real-time neural network inference on extremely weak devices: agile offloading with explainable AI. In Proceedings of the 28th Annual International Conference on Mobile Computing and Networking. 200--213."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 18th International Conference on Information Processing in Sensor Networks. 217--228","author":"Islam Md Tamzeed","year":"2019","unstructured":"Md Tamzeed Islam and Shahriar Nirjon. 2019. Soundsemantics: exploiting semantic knowledge in text for embedded acoustic event classification. In Proceedings of the 18th International Conference on Information Processing in Sensor Networks. 217--228."},{"key":"e_1_3_2_1_28_1","unstructured":"Dugan Jon Elliott Seth Bruce A. Mah Poskanzer Jeff and Prabhu Kaustubh. 2014. iPerf. https:\/\/software.es.net\/iperf\/."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_2_1_30_1","volume-title":"RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics. In 20th USENIX Symposium on Networked Systems Design and Implementation. 917--932","author":"Khani Mehrdad","year":"2023","unstructured":"Mehrdad Khani, Ganesh Ananthanarayanan, Kevin Hsieh, Junchen Jiang, Ravi Netravali, Yuanchao Shu, Mohammad Alizadeh, and Victor Bahl. 2023. RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics. In 20th USENIX Symposium on Networked Systems Design and Implementation. 917--932."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/381677.381705"},{"key":"e_1_3_2_1_32_1","volume-title":"Segment Anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4015--4026","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollar, and Ross Girshick. 2023. Segment Anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4015--4026."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 1517--1526","author":"Kishida Ikki","year":"2021","unstructured":"Ikki Kishida, Hong Chen, Masaki Baba, Jiren Jin, Ayako Amma, and Hideki Nakayama. 2021. Object recognition with continual open set domain adaptation for home robot. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 1517--1526."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications. 15--21","author":"Leontiadis Ilias","year":"2021","unstructured":"Ilias Leontiadis, Stefanos Laskaridis, Stylianos I Venieris, and Nicholas D Lane. 2021. It's always personal: Using early exits for efficient on-device CNN personalisation. In Proceedings of the 22nd International Workshop on Mobile Computing Systems and Applications. 15--21."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586176"},{"key":"e_1_3_2_1_37_1","volume-title":"FreeLM: Fine-Tuning-Free Language Model. arXiv preprint arXiv:2305.01616","author":"Li Xiang","year":"2023","unstructured":"Xiang Li, Xin Jiang, Xuying Meng, Aixin Sun, and Yequan Wang. 2023. FreeLM: Fine-Tuning-Free Language Model. arXiv preprint arXiv:2305.01616 (2023)."},{"key":"e_1_3_2_1_38_1","first-page":"19645","article-title":"Effective adaptation in multi-task co-training for unified autonomous driving","volume":"35","author":"Liang Xiwen","year":"2022","unstructured":"Xiwen Liang, Yangxin Wu, Jianhua Han, Hang Xu, Chunjing Xu, and Xiaodan Liang. 2022. Effective adaptation in multi-task co-training for unified autonomous driving. Advances in Neural Information Processing Systems 35 (2022), 19645--19658.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3386126"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7539--7548","author":"Liu Yu","year":"2020","unstructured":"Yu Liu, Xuhui Jia, Mingxing Tan, Raviteja Vemulapalli, Yukun Zhu, Bradley Green, and Xiaogang Wang. 2020. Search to distill: Pearls are everywhere but not the eyes. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7539--7548."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks. 31--46","author":"Luo Wenjie","year":"2021","unstructured":"Wenjie Luo, Zhenyu Yan, Qun Song, and Rui Tan. 2021. Phyaug: Physics-directed data augmentation for deep sensing model transfer in cyber-physical systems. In Proceedings of the 20th International Conference on Information Processing in Sensor Networks. 31--46."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341162.3345609"},{"key":"e_1_3_2_1_43_1","volume-title":"Enabling High Quality Real-Time Communications with Adaptive Frame-Rate. In 20th USENIX Symposium on Networked Systems Design and Implementation. 1429--1450","author":"Meng Zili","year":"2023","unstructured":"Zili Meng, Tingfeng Wang, Yixin Shen, Bo Wang, Mingwei Xu, Rui Han, Honghao Liu, Venkat Arun, Hongxin Hu, and Xue Wei. 2023. Enabling High Quality Real-Time Communications with Adaptive Frame-Rate. In 20th USENIX Symposium on Networked Systems Design and Implementation. 1429--1450."},{"key":"e_1_3_2_1_44_1","volume-title":"2019 International Conference on Robotics and Automation. IEEE, 2924--2931","author":"Meyer Benjamin J","year":"2019","unstructured":"Benjamin J Meyer and Tom Drummond. 2019. The importance of metric learning for robotic vision: Open set recognition and active learning. In 2019 International Conference on Robotics and Automation. IEEE, 2924--2931."},{"key":"e_1_3_2_1_45_1","volume-title":"Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems 26","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems 26 (2013)."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings, Part XXII 16","author":"Narayan Sanath","year":"2020","unstructured":"Sanath Narayan, Akshita Gupta, Fahad Shahbaz Khan, Cees GM Snoek, and Ling Shao. 2020. Latent embedding feedback and discriminative features for zero-shot classification. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXII 16. Springer, 479--495."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378534"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560519"},{"key":"e_1_3_2_1_50_1","volume-title":"2015 International Conference on Hardware\/Software Codesign and System Synthesis. IEEE, 124--132","author":"Park Eunhyeok","year":"2015","unstructured":"Eunhyeok Park, Dongyoung Kim, Soobeom Kim, Yong-Deok Kim, Gunhee Kim, Sungroh Yoon, and Sungjoo Yoo. 2015. Big\/little deep neural network for ultra low power inference. In 2015 International Conference on Hardware\/Software Codesign and System Synthesis. IEEE, 124--132."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"e_1_3_2_1_52_1","volume-title":"International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_53_1","volume-title":"Conference on Robot Learning. PMLR, 492--504","author":"Shah Dhruv","year":"2023","unstructured":"Dhruv Shah, B\u0142a\u017cej Osi\u0144ski, Sergey Levine, et al. 2023. Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action. In Conference on Robot Learning. PMLR, 492--504."},{"key":"e_1_3_2_1_54_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"e_1_3_2_1_56_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00773"},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 15521--15533","author":"Sun Ximeng","year":"2023","unstructured":"Ximeng Sun, Pengchuan Zhang, Peizhao Zhang, Hardik Shah, Kate Saenko, and Xide Xia. 2023. DIME-FM: Distilling Multimodal and Efficient Foundation Models. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 15521--15533."},{"key":"e_1_3_2_1_59_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_60_1","unstructured":"MLC team. 2023. MLC-LLM. https:\/\/github.com\/mlc-ai\/mlc-llm"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494995"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1109\/TII.2019.2912809","article-title":"Data-driven gearbox failure detection in industrial robots","volume":"16","author":"Vallachira Sathish","year":"2019","unstructured":"Sathish Vallachira, Michal Orkisz, Mikael Norrl\u00f6f, and Sachit Butail. 2019. Data-driven gearbox failure detection in industrial robots. IEEE Transactions on Industrial Informatics 16, 1 (2019), 193--201.","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"e_1_3_2_1_63_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587438"},{"key":"e_1_3_2_1_65_1","volume-title":"Contrastive learning rivals masked image modeling in fine-tuning via feature distillation. arXiv preprint arXiv:2205.14141","author":"Wei Yixuan","year":"2022","unstructured":"Yixuan Wei, Han Hu, Zhenda Xie, Zheng Zhang, Yue Cao, Jianmin Bao, Dong Chen, and Baining Guo. 2022. Contrastive learning rivals masked image modeling in fine-tuning via feature distillation. arXiv preprint arXiv:2205.14141 (2022)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065234"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485937"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241563"},{"key":"e_1_3_2_1_70_1","first-page":"1","article-title":"A novel sleep stage contextual refinement algorithm leveraging conditional random fields","volume":"71","author":"Yang Bufang","year":"2022","unstructured":"Bufang Yang, Wenxuan Wu, Yitian Liu, and Hongxing Liu. 2022. A novel sleep stage contextual refinement algorithm leveraging conditional random fields. IEEE Transactions on Instrumentation and Measurement 71 (2022), 1--13.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102581"},{"key":"e_1_3_2_1_72_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 23497--23506","author":"Yao Lewei","year":"2023","unstructured":"Lewei Yao, Jianhua Han, Xiaodan Liang, Dan Xu, Wei Zhang, Zhenguo Li, and Hang Xu. 2023. Detclipv2: Scalable open-vocabulary object detection pre-training via word-region alignment. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 23497--23506."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430898"},{"key":"e_1_3_2_1_74_1","volume-title":"Proceedings of the 28th Annual International Conference on Mobile Computing And Networking. 228--241","author":"Yuan Mu","year":"2022","unstructured":"Mu Yuan, Lan Zhang, Fengxiang He, Xueting Tong, and Xiang-Yang Li. 2022. Infi: end-to-end learnable input filter for resource-efficient mobile-centric inference. In Proceedings of the 28th Annual International Conference on Mobile Computing And Networking. 228--241."},{"key":"e_1_3_2_1_75_1","volume-title":"Sung Ho Bae, Seungkyu Lee, and Choong Seon Hong.","author":"Zhang Chaoning","year":"2023","unstructured":"Chaoning Zhang, Dongshen Han, Yu Qiao, Jung Uk Kim, Sung Ho Bae, Seungkyu Lee, and Choong Seon Hong. 2023. Faster Segment Anything: Towards Lightweight SAM for Mobile Applications. arXiv preprint arXiv:2306.14289 (2023)."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453520"}],"event":{"name":"SenSys '23: 21st ACM Conference on Embedded Networked Sensor Systems","location":"Istanbul Turkiye","acronym":"SenSys '23","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems","SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625687.3625793","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3625687.3625793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T13:49:11Z","timestamp":1750168151000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625687.3625793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":76,"alternative-id":["10.1145\/3625687.3625793","10.1145\/3625687"],"URL":"https:\/\/doi.org\/10.1145\/3625687.3625793","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2024-04-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}