Conference paper · 2016 · Open access

HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection

Tao Kong, Anbang Yao, Yurong Chen, Fuchun Sun

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 845–853 · Published 1 June 2016 · DOI 10.1109/cvpr.2016.98

Free PDFView at the publisherCite this paper

In brief

“HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection” is a 2016 conference paper by Tao Kong and 3 co-authors, published in IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings. OpenAlex counts 941 citations as of 15 November 2026, which puts it in the top 2% of works published in 2016 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
941
Most cited in
2019 (152)
Field-weighted impact
41.21
References
38
Authors
4

Abstract

Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances. State-of-the-art region proposal methods usually need several thousand proposals to get high recall, thus hurting the detection efficiency. Although the latest Region Proposal Network method gets promising detection accuracy with several hundred proposals, it still struggles in small-size object detection and precise localization (e.g., large IoU thresholds), mainly due to the coarseness of its feature maps. In this paper, we present a deep hierarchical network, namely HyperNet, for handling region proposal generation and object detection jointly. Our HyperNet is primarily based on an elaborately designed Hyper Feature which aggregates hierarchical feature maps first and then compresses them into a uniform space. The Hyper Features well incorporate deep but highly semantic, intermediate but really complementary, and shallow but naturally high-resolution features of the image, thus enabling us to construct HyperNet by sharing them both in generating proposals and detecting objects via an end-to-end joint training strategy. For the deep VGG16 model, our method achieves completely leading recall and state-of-the-art object detection accuracy on PASCAL VOC 2007 and 2012 using only 100 proposals per image. It runs with a speed of 5 fps (including all steps) on a GPU, thus having the potential for real-time processing.

Cite this paper

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

APA 7

Kong, T., Yao, A., Chen, Y., & Sun, F. (2016). HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 845–853. https://doi.org/10.1109/cvpr.2016.98

MLA 9

Kong, Tao, et al. “HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2016, pp. 845–853. https://doi.org/10.1109/cvpr.2016.98.

Chicago

Kong, Tao, Anbang Yao, Yurong Chen, and Fuchun Sun. 2016. “HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings: 845–853. https://doi.org/10.1109/cvpr.2016.98.

Harvard

Kong, T. et al. (2016) ‘HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 845–853. doi:10.1109/cvpr.2016.98.

IEEE

T. Kong, A. Yao, Y. Chen, and F. Sun, “HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 845–853, 2016, doi: 10.1109/cvpr.2016.98.

BibTeX

@inproceedings{kong2016hypernet,
  title     = {{HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection}},
  author    = {Kong, Tao and Yao, Anbang and Chen, Yurong and Sun, Fuchun},
  booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings},
  year      = {2016},
  pages     = {845--853},
  doi       = {10.1109/cvpr.2016.98},
  url       = {https://doi.org/10.1109/cvpr.2016.98}
}

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

Citations by year

YearCitationsShare of the best year
20177171
2018140140
2019152152
2020120120
2021139139
20228686
20239595
20247979
20253434
20261717

Its field-weighted citation impact is 41.21: it has been cited 41.21 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

  • region proposal generation
  • HyperNet
  • hierarchical feature aggregation
  • feature map compression
  • small object detection
  • end-to-end learning
  • region proposal network
  • VGG16

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?

Kong, T., Yao, A., Chen, Y., & Sun, F. (2016). HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 845–853. https://doi.org/10.1109/cvpr.2016.98

How many times has this paper been cited?

941 times, according to OpenAlex on 15 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: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Tao Kong, Anbang Yao, Yurong Chen, Fuchun Sun.

What is the DOI of this paper?

10.1109/cvpr.2016.98. The permanent link is https://doi.org/10.1109/cvpr.2016.98.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.