Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJune 2024
Hybrid SLM and LLM for Edge-Cloud Collaborative Inference
EdgeFM '24: Proceedings of the Workshop on Edge and Mobile Foundation ModelsJune 2024, Pages 36–41https://doi.org/10.1145/3662006.3662067Edge-Cloud collaboration for deep learning inference has been actively studied, to enhance the inference performance by leveraging both Edge and Cloud resources. However, traditional Edge-Cloud collaboration based on model partitioning or confidence ...
- research-articleJune 2024
Empowering In-Browser Deep Learning Inference on Edge Through Just-In-Time Kernel Optimization
- Fucheng Jia,
- Shiqi Jiang,
- Ting Cao,
- Wei Cui,
- Tianrui Xia,
- Xu Cao,
- Yuanchun Li,
- Qipeng Wang,
- Deyu Zhang,
- Ju Ren,
- Yunxin Liu,
- Lili Qiu,
- Mao Yang
MOBISYS '24: Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and ServicesJune 2024, Pages 438–450https://doi.org/10.1145/3643832.3661892Web is increasingly becoming the primary platform to deliver AI services onto edge devices, making in-browser deep learning (DL) inference more prominent. Nevertheless, the heterogeneity of edge devices, combined with the underdeveloped state of Web ...
AutoDroid: LLM-powered Task Automation in Android
- Hao Wen,
- Yuanchun Li,
- Guohong Liu,
- Shanhui Zhao,
- Tao Yu,
- Toby Jia-Jun Li,
- Shiqi Jiang,
- Yunhao Liu,
- Yaqin Zhang,
- Yunxin Liu
ACM MobiCom '24: Proceedings of the 30th Annual International Conference on Mobile Computing and NetworkingMay 2024, Pages 543–557https://doi.org/10.1145/3636534.3649379Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones. However, existing approaches suffer from poor scalability due to the limited language understanding ability and the non-...
DoodleTunes: Interactive Visual Analysis of Music-Inspired Children Doodles with Automated Feature Annotation
- Shuqi Liu,
- Jia Bu,
- Huayuan Ye,
- Juntong Chen,
- Shiqi Jiang,
- Mingtian Tao,
- Liping Guo,
- Changbo Wang,
- Chenhui Li
CHI '24: Proceedings of the CHI Conference on Human Factors in Computing SystemsMay 2024, Article No.: 889, Pages 1–19https://doi.org/10.1145/3613904.3642346Music and visual arts are essential in children’s arts education, and their integration has garnered significant attention. Existing data analysis methods for exploring audio-visual correlations are limited. Yet, relevant research is necessary for ...
- research-articleFebruary 2024
Automatic Flange Alignment System Using Multiple Visions
CECCT '23: Proceedings of the 2023 International Conference on Electronics, Computers and Communication TechnologyNovember 2023, Pages 82–86https://doi.org/10.1145/3637494.3637509Abstract—Flanges play a crucial role in ensuring the normal operation and performance of mechanical systems. Traditional flange alignment methods often require exhausting manual intervention that is time-consuming and inefficient, and have limited ...
-
- research-articleOctober 2023
Large-scale Video Analytics with Cloud–Edge Collaborative Continuous Learning
ACM Transactions on Sensor Networks (TOSN), Volume 20, Issue 1Article No.: 14, Pages 1–23https://doi.org/10.1145/3624478Deep learning–based video analytics demands high network bandwidth to ferry the large volume of data when deployed on the cloud. When incorporated at the edge side, only lightweight deep neural network (DNN) models are affordable due to computational ...
AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments
ACM MobiCom '23: Proceedings of the 29th Annual International Conference on Mobile Computing and NetworkingOctober 2023, Article No.: 28, Pages 1–17https://doi.org/10.1145/3570361.3592529Deep learning models are increasingly deployed to edge devices for real-time applications. To ensure stable service quality across diverse edge environments, it is highly desirable to generate tailored model architectures for different conditions. ...
- research-articleAugust 2023
MicroscopeSketch: Accurate Sliding Estimation Using Adaptive Zooming
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 2660–2671https://doi.org/10.1145/3580305.3599432High-accuracy real-time data stream estimations are critical for various applications, and sliding-window-based techniques have attracted wide attention. However, existing solutions struggle to achieve high accuracy, generality, and low memory usage ...
NN-Stretch: Automatic Neural Network Branching for Parallel Inference on Heterogeneous Multi-Processors
MobiSys '23: Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and ServicesJune 2023, Pages 70–83https://doi.org/10.1145/3581791.3596870Mobile devices are increasingly equipped with heterogeneous multiprocessors, e.g., CPU + GPU + DSP. Yet existing Neural Network (NN) inference fails to fully utilize the computing power of the heterogeneous multi-processors due to the sequential ...
- articleFebruary 2023
Propaganda Information of Internet Celebrity Influence: Young Adult Purchase Intention by Big Data Analysis
Journal of Organizational and End User Computing (JOEUC-IGI), Volume 35, Issue 1Jul 2023, Pages 1–18https://doi.org/10.4018/JOEUC.318128At present, internet celebrity marketing has become a driving force for the growth of mobile e-commerce; however, it has also become more apparent that the credibility and authenticity of the internet celebrity is directly correlated to the success of ...
- research-articleJanuary 2023
Turbo: Opportunistic Enhancement for Edge Video Analytics
SenSys '22: Proceedings of the 20th ACM Conference on Embedded Networked Sensor SystemsNovember 2022, Pages 263–276https://doi.org/10.1145/3560905.3568501Edge computing is being widely used for video analytics. To alleviate the inherent tension between accuracy and cost, various video analytics pipelines have been proposed to optimize the usage of GPU on edge nodes. Nonetheless, we find that GPU compute ...
- research-articleJuly 2022
Face illumination normalization based on generative adversarial network
- Dequan Guo,
- Lingrui Zhu,
- Shenggui Ling,
- Tianxiang Li,
- Gexiang Zhang,
- Qiang Yang,
- Ping Wang,
- Shiqi Jiang,
- Sidong Wu,
- Junbao Liu
Natural Computing: an international journal (NATC), Volume 22, Issue 1Mar 2023, Pages 105–117https://doi.org/10.1007/s11047-022-09892-4AbstractFace recognition technology has been widely used in the field of artificial intelligence. The technology needs to be carried out normally under the appropriate light, however, there is not ideal light, even poor-lighted for the face recognition ...
CoDL: efficient CPU-GPU co-execution for deep learning inference on mobile devices
MobiSys '22: Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and ServicesJune 2022, Pages 209–221https://doi.org/10.1145/3498361.3538932Concurrent inference execution on heterogeneous processors is critical to improve the performance of increasingly heavy deep learning (DL) models. However, available inference frameworks can only use one processor at a time, or hardly achieve speedup by ...
- research-articleOctober 2021
Third-Harmonic Injection PWM Based Control Strategy for A Five-Phase Six-Leg Voltage Source Inverter With Unbalanced Loads
2021 24th International Conference on Electrical Machines and Systems (ICEMS)Oct 2021, Pages 2065–2069https://doi.org/10.23919/ICEMS52562.2021.9634641Compared to conventional n-phase topologies, the n-phase (n+1)-leg inverters are able to work under unbalanced loading conditions. This paper investigates the control strategy of a five-phase six-leg inverter system with unbalanced loads. Based on the ...
- research-articleOctober 2021
A PSO Based Optimal Design Method of LCL Filter for Single-phase Grid-connected Inverter with Multiple Conditions Constraint
2021 24th International Conference on Electrical Machines and Systems (ICEMS)Oct 2021, Pages 2116–2120https://doi.org/10.23919/ICEMS52562.2021.9634316The performance of LCL filter for single-phase grid-connected inverter depends mainly on its parameter design, but the classic method has some shortcomings. Firstly, the inefficiency from repeated trials. Secondly, maybe the results obtained can be ...
- research-articleOctober 2021
Flexible high-resolution object detection on edge devices with tunable latency
MobiCom '21: Proceedings of the 27th Annual International Conference on Mobile Computing and NetworkingOctober 2021, Pages 559–572https://doi.org/10.1145/3447993.3483274Object detection is a fundamental building block of video analytics applications. While Neural Networks (NNs)-based object detection models have shown excellent accuracy on benchmark datasets, they are not well positioned for high-resolution images ...
- ArticleSeptember 2021
CoPaint: Guiding Sketch Painting with Consistent Color and Coherent Generative Adversarial Networks
AbstractArt design plays an important role in attracting users. Thro- ugh art design, some sketches are more in line with aesthetics. Traditionally, we need to artificially color many series of black-and-white sketches using the same color, which is time-...
- research-articleNovember 2020
Extraction of Noise Source Impedance Under Operating Conditions Using a Two-Probe Approach
2020 IEEE 9th International Power Electronics and Motion Control Conference (IPEMC2020-ECCE Asia)Nov 2020, Pages 1858–1862https://doi.org/10.1109/IPEMC-ECCEAsia48364.2020.9367794In this work, a two-probe approach is proposed to extract noise source impedance under operating conditions. The proposed two-probe method is introduced and then validated by several passive components. Compared with the previous impedance extraction ...
- research-articleAugust 2020
Profiling and optimizing deep learning inference on mobile GPUs
APSys '20: Proceedings of the 11th ACM SIGOPS Asia-Pacific Workshop on SystemsAugust 2020, Pages 75–81https://doi.org/10.1145/3409963.3410493Mobile GPU, as the ubiquitous computing hardware on almost every smartphone, is being exploited for the deep learning inference. In this paper, we present our measurements on the inference performance with mobile GPUs. Our observations suggest that ...
- research-articleAugust 2020
WavingSketch: An Unbiased and Generic Sketch for Finding Top-k Items in Data Streams
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningAugust 2020, Pages 1574–1584https://doi.org/10.1145/3394486.3403208Finding top-k items in data streams is a fundamental problem in data mining. Existing algorithms that can achieve unbiased estimation suffer from poor accuracy. In this paper, we propose a new sketch, WavingSketch, which is much more accurate than ...