Conference paper · 2021 · Open access

Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications

Hongjia Li, Geng Yuan, Wei Niu, Yuxuan Cai, Mengshu Sun, Zhengang Li, Bin Ren, Xue Lin, Yanzhi Wang

Asia and South Pacific Design Automation Conference (ASP-DAC), 581–586 · Published 18 January 2021 · DOI 10.1145/3394885.3431627

Open PDFView at the publisherCite this paper

In brief

“Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications” is a 2021 conference paper by Hongjia Li and 8 co-authors, published in Asia and South Pacific Design Automation Conference (ASP-DAC). OpenAlex counts 14 citations as of 19 November 2026. It is open access: the full text is free to read at Asia and South Pacific Design Automation Conference (ASP-DAC).

Citations
14
Most cited in
2021 (5)
Field-weighted impact
0.70
References
25
Authors
9

Abstract

With the growth of mobile vision applications, there is a growing need to break through the current performance limitation of mobile platforms, especially for computationally intensive applications, such as object detection, action recognition, and medical diagnosis. To achieve this goal, we present our unified real-time mobile DNN inference acceleration framework, seamlessly integrating hardware-friendly, structured model compression with mobile-targeted compiler optimizations. We aim at an unprecedented, realtime performance of such large-scale neural network inference on mobile devices. A fine-grained block-based pruning scheme is proposed to be universally applicable to all types of DNN layers, such as convolutional layers with different kernel sizes and fully connected layers. Moreover, it is also successfully extended to 3D convolutions. With the assist of our compiler optimizations, the fine-grained block-based sparsity is fully utilized to achieve high model accuracy and high hardware acceleration simultaneously. To validate our framework, three representative fields of applications are implemented and demonstrated, object detection, activity detection, and medical diagnosis. All applications achieve real-time inference using an off-the-shelf smartphone, outperforming the representative mobile DNN inference acceleration frameworks by up to 6.7x in speed. The demonstrations of these applications can be found in the following link: https://bit.ly/39lWpYu.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Li, H., Yuan, G., Niu, W., Cai, Y., Sun, M., Li, Z., Ren, B., Lin, X., & Wang, Y. (2021). Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications. Asia and South Pacific Design Automation Conference (ASP-DAC), 581–586. https://doi.org/10.1145/3394885.3431627

MLA 9

Li, Hongjia, et al. “Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications.” Asia and South Pacific Design Automation Conference (ASP-DAC), 2021, pp. 581–586. https://doi.org/10.1145/3394885.3431627.

Chicago

Li, Hongjia, Geng Yuan, Wei Niu, Yuxuan Cai, Mengshu Sun, Zhengang Li, Bin Ren, Xue Lin, and Yanzhi Wang. 2021. “Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications.” Asia and South Pacific Design Automation Conference (ASP-DAC): 581–586. https://doi.org/10.1145/3394885.3431627.

Harvard

Li, H. et al. (2021) ‘Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications’, Asia and South Pacific Design Automation Conference (ASP-DAC), pp. 581–586. doi:10.1145/3394885.3431627.

IEEE

H. Li et al., “Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications,” Asia and South Pacific Design Automation Conference (ASP-DAC), pp. 581–586, 2021, doi: 10.1145/3394885.3431627.

BibTeX

@inproceedings{li2021real,
  title     = {{Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications}},
  author    = {Li, Hongjia and Yuan, Geng and Niu, Wei and Cai, Yuxuan and Sun, Mengshu and Li, Zhengang and Ren, Bin and Lin, Xue and Wang, Yanzhi},
  booktitle = {Asia and South Pacific Design Automation Conference (ASP-DAC)},
  year      = {2021},
  pages     = {581--586},
  doi       = {10.1145/3394885.3431627},
  url       = {https://doi.org/10.1145/3394885.3431627}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202155
202244
202322
202411
202522

Its field-weighted citation impact is 0.70: it has been cited 0.70 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • compiler optimization
  • sparse neural networks
  • 3D convolution
  • object detection
  • activity recognition
  • diagnosis

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Li, H., Yuan, G., Niu, W., Cai, Y., Sun, M., Li, Z., Ren, B., Lin, X., & Wang, Y. (2021). Real-Time Mobile Acceleration of DNNs: From Computer Vision to Medical Applications. Asia and South Pacific Design Automation Conference (ASP-DAC), 581–586. https://doi.org/10.1145/3394885.3431627

How many times has this paper been cited?

14 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Asia and South Pacific Design Automation Conference (ASP-DAC): sign in and open the PDF from this page.

Who wrote this paper?

Hongjia Li, Geng Yuan, Wei Niu, Yuxuan Cai, Mengshu Sun, Zhengang Li, Bin Ren, Xue Lin, Yanzhi Wang.

What is the DOI of this paper?

10.1145/3394885.3431627, permanently at https://doi.org/10.1145/3394885.3431627. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.