Keywords
Deep learning
Convolutional neural network
Video surveillance
Artificial intelligence
Bibliometric analysis
How to Cite
Abstract
Action recognition based on convolutional neural networks (AR-CNN) has been developing rapidly in recent years. It is of great significance to conduct a deep analysis to understand the recent development of AR-CNN. However, a limited study examining the research status of this field could be found. Therefore, this study aims to quantitatively assess the publications related to the SciVal topic "Action Recognition; Convolutional Neural Network; Video Surveillance (T.561)" in computer vision research. This study focused on six aspects: literature distribution characteristics analysis, the development trend, citation analysis, collaborative analysis, keyword analysis and thematic evolution, using VOSviewer and Bibliometrix. The relevant publications were retrieved from Scopus in the period 2012–2021. A total of 6633 publications were identified by 9088 different authors, 62% were conference papers, and 35% were research articles. China and the USA contributed 39.7 % and 17.9 % of the total publications, respectively. The authors' production according to Price's Law was inconsistent but consistent according to Lotka's Law. Ling Shao was the most productive author, with 48 papers (%0.7). Chinese Academy of Sciences was the most productive affiliation, with 259 papers (%3.9). The first Bradford site consisted of Computer Science Lecture Notes with 617 publications. A moderately significant correlation was revealed between the country's publications and GDP per capita. The overall results show that the number of AR-CNN-related documents has increased significantly in recent years, with rapid growth from 2016. Although publications on AR-CNN were published mainly in European journals, China led the scientific production.
References
A., P., 1969 Statistical bibliography or bibliometrics. Journal of Documentation 25: 348.
Ahad, M., 2011 Computer vision and action recognition: A guide for image processing and computer vision community for action understanding.
Aria, M. and C. Cuccurullo, 2017 bibliometrix: An r-tool for comprehensive science mapping analysis. Journal of Informetrics 11: 959–975.
Bi, Y., S. Kapoor, and R. Bhatia, 2017 Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016: Volume 2.
Bobick, A. and J. Davis, 1996 An appearance-based representation of action. In Proceedings of the International Conference on Pattern Recognition (ICPR), volume 1, pp. 307–312.
Bradford, S. C., 1948 Documentation. Crosby Lockwood.
Chen, H. and Z. Deng, 2020 Bibliometric analysis of the application of convolutional neural network in computer vision. IEEE Access 8: 155417–155428.
Ci, Y., F. Jiao,W. Tu, and J. Fang, 2021 Analysis on development tendency of computer vision and graphics based on bibliometrics. Journal of Physics: Conference Series 1883: 012054.
Donahue, J. et al., 2015 Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2625–2634.
Karpathy, A., G. Toderici, S. Shetty, T. Leung, R. Sukthankar, et al., 2014 Large-scale video classification with convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1725–1732.
Khan, M. A. et al., 2020 Human action recognition using fusion of multiview and deep features: an application to video surveillance. Multimedia Tools and Applications pp. 1–27.
Kiduk, Y. and L. I. Meho, 2006 Citation analysis: A comparison of google scholar, scopus, and web of science. Proceedings of the American Society for Information Science and Technology 43: 1–15.
LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner, 1998 Gradientbased learning applied to document recognition. Proceedings of mthe IEEE 86: 2278–2323.
Lotka, A. J., 1926 The frequency distribution of scientific productivity. Journal of the Washington Academy of Sciences 16: 317–323. Mongeon, P. and A. Paul-Hus, 2016 The journal coverage of web of science and scopus: a comparative analysis. Scientometrics m106: 213–228.
Oh, S. et al., 2011 A large-scale benchmark dataset for event recognition in surveillance video. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3153–3160.
Popoola, O. P. and K.Wang, 2012 Video-based abnormal human behavior recognition: a review. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 42: 865–878.
Rosales, R. and S. Sclaroff, 2001 Trajectory guided tracking and recognition of actions. In Proceedings of the International Conference on Pattern Recognition (ICPR).
SciVal, 2023 Scival - working with research areas. https:// www.research.uky.edu/uploads/working-research-areas, Accessed: 2023-12-06.
Simonyan, K. and A. Zisserman, 2014 Two-stream convolutional networks for action recognition in videos. In Advances in Neural Information Processing Systems (NIPS), volume 27.
Sudha, M. R., K. Sriraghav, S. S. Abisheck, S. G. Jacob, and S. Manisha, 2017 Approaches and applications of virtual reality and gesture recognition: A review. International Journal of Ambient Computing and Intelligence (IJACI) 8: 1–18.
Xia, L., I. Gori, J. K. Aggarwal, and M. S. Ryoo, 2015 Robot-centric activity recognition from first-person rgb-d videos. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 357–364.
Xuefei, C., 2014 Ideal-oriented policymaking. Chinese Education and Society 44: 8–18.
Zhou, Y., X. Sun, Z.-J. Zha, and W. Zeng, 2018 Mict: Mixed 3d/2d convolutional tube for human action recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 449–458.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.