지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2020.12
- 수록면
- 1,540 - 1,551 (12page)
이용수
초록· 키워드
오류제보하기
Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.
목차
ABSTRACT
1. INTRODUCTION
2. 3D RESIDUAL DENSE NETWORK
3. EXPERIMENT AND RESULT ANALYSIS
4. CONCLUSION
REFERENCE
참고문헌 (20)
참고문헌 신청
F. Zhu, L. Sha, J. Xie, and Y. Fang, “From Handcrafted to Learned Representations for Human Action Recognition: A Survey,” Image and Vision Computing, Vol. 55, No. 1, pp. 42- 52, 2016.
Y. Guangle, L. Tao, and Z. Jiandan, “A Review of Convolutional Neural Network Based Action Recognition,” Pattern Recognition Letters, Vol. 118, No. 1, pp. 14-22, 2019.
K. Wang, “A Survey of Human Body Action Recognition,” Pattern Recognition and Artificial Intelligence, Vol. 27, No. 1, pp. 35-48, 2014.
A. Krizhevsky, I. Sutskever, and G.E. Hinton, “Image-net Classification with Deep Convolutional Neural Networks,” Proceedings of the 25th International Conference on Neural Information Processing Systems, pp. 1097-1105, 2012.
Very Deep Convolutional Networks for Large-scale Image Recognition(2015), https://arxiv.org/pdf/1409.1556.pdf (accessed April 10, 2015).
Y. Guangle, L. Tao, and Z. Jiandan, “A Review of Convolutional Neural Network Based Action Recognition,” Pattern Recognition Letters, Vol. 118, No. 1, pp. 14-22, 2019.
K. Wang, “A Survey of Human Body Action Recognition,” Pattern Recognition and Artificial Intelligence, Vol. 27, No. 1, pp. 35-48, 2014.
A. Krizhevsky, I. Sutskever, and G.E. Hinton, “Image-net Classification with Deep Convolutional Neural Networks,” Proceedings of the 25th International Conference on Neural Information Processing Systems, pp. 1097-1105, 2012.
Very Deep Convolutional Networks for Large-scale Image Recognition(2015), https://arxiv.org/pdf/1409.1556.pdf (accessed April 10, 2015).
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
개선된 Residual Dense Network를 이용한 초해상도 복원 방법
대한전자공학회 학술대회
2019 .06
-
Human Motion Recognition Based on Spatio-temporal Convolutional Neural Network
멀티미디어학회논문지
2020 .08
-
Improved DT Algor ithm Based Human Action Features Detection
멀티미디어학회논문지
2018 .04
-
Convolutional Neural Network를 이용한 빌렛 번호 인식 알고리즘
제어로봇시스템학회 국내학술대회 논문집
2017 .05
-
Efficient Multi-Task CNN for Face and Facial Expression Recognition Using Residual and Dense Architectures for Application in Monitoring Online Learning
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
2023 .09
-
ADD-Net : Attention Based 3D Dense Network for Action Recognition
한국컴퓨터정보학회논문지
2019 .06
-
Evaluation of Deep Convolutional Neural Network Architectures for Human Activity Recognition with Smartphone Sensors
한국정보과학회 학술발표논문집
2015 .06
-
Machine Learning based Pattern Recognition and Classification Framework Development
제어로봇시스템학회 국제학술대회 논문집
2017 .10
-
Vehicle Make and Model Recognition System based on Convolutional Neural Network
정보 및 제어 논문집
2017 .04
-
Residual Dense Block과 Dense Block을 결합한 이미지 디노이징 모델
한국정보과학회 학술발표논문집
2020 .12
-
Physical Activity Recognition With Sensory Data Encoder For Deep Convolutional Neural Network
한국통신학회 학술대회논문집
2019 .06
-
Comparison of Deep Learning Algorithms Based on Face Recognition
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
2015 .06
-
Vehicle Image Recognition Using Deep Convolution Neural Network and Compressed Dictionary Learning
JIPS(Journal of Information Processing Systems)
2021 .01
-
Dense Motion Flow 기반의 Deep Learning을 사용한 표정인식방법
대한전자공학회 학술대회
2016 .11
-
Intelligent Activity Recognition based on Improved Convolutional Neural Network
멀티미디어학회논문지
2022 .06
-
Fully Convolutional Network 를 활용한 빌렛 식별 번호 인식 알고리즘
제어로봇시스템학회 국내학술대회 논문집
2018 .05
-
A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology
Journal of Electrical Engineering & Technology
2017 .01
-
Residual Learning Based CNN for Gesture Recognition in Robot Interaction
JIPS(Journal of Information Processing Systems)
2021 .01
-
Improved Residual Network for Single Image Super Resolution
한국방송미디어공학회 학술발표대회 논문집
2019 .06
-
Facial Emotion Recognition using Convolutional Neural Network Based on Repetitive Learning Blocks Approach
한국정보과학회 학술발표논문집
2020 .07
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2021-004-000061441