Junlan Jin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junlan Jin has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Kai Hu
School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China
8 shared publications - Liguo Weng
Nanjing University of Information Science and Technology, Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing, China
5 shared publications - Min Xia
Nanjing University of Information Science and Technology
3 shared publications - Yiwu Ding
School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China
3 shared publications - Qingfeng Xia
School of Automation, Wuxi University, Wuxi 214105, China
2 shared publications - Chaowen Shen
School of Automation, Nanjing University of Information Science and Technology, Nanjing, China
1 shared publication
Latest Publications
- 1 April 2023
- Published by Springer Nature in Multimedia Systems
- Vol. 29 (4) , 1941-1954
Attentional weighting strategy-based dynamic GCN for skeleton-based action recognition
- 1 April 2023
- Published by Springer Nature in Multimedia Systems
- Vol. 29 (4) , 1941-1954
Attentional weighting strategy-based dynamic GCN for skeleton-based action recognition
- Open Access
Multiple Attention Mechanism Graph Convolution HAR Model Based on Coordination Theory
Human action recognition (HAR) is the foundation of human behavior comprehension. It is of great significance and can be used in many real-world applications. From the point of view of human kinematics, the coordination of limbs is an important intrinsic factor of motion and contains a great deal of information. In addition, for different movements, the HAR algorithm provides important, multifaceted attention to each joint. Based on the above analysis, this paper proposes a HAR algorithm, which adopts two attention modules that work together to extract the coordination characteristics in the process of motion, and strengthens the attention of the model to the more important joints in the process of moving. Experimental data shows these two modules can improve the recognition accuracy of the model on the public HAR dataset (NTU-RGB + D, Kinetics-Skeleton).
Open AccessMultiple Attention Mechanism Graph Convolution HAR Model Based on Coordination Theory
Human action recognition (HAR) is the foundation of human behavior comprehension. It is of great significance and can be used in many real-world applications. From the point of view of human kinematics, the coordination of limbs is an important intrinsic factor of motion and contains a great deal of information. In addition, for different movements, the HAR algorithm provides important, multifaceted attention to each joint. Based on the above analysis, this paper proposes a HAR algorithm, which adopts two attention modules that work together to extract the coordination characteristics in the process of motion, and strengthens the attention of the model to the more important joints in the process of moving. Experimental data shows these two modules can improve the recognition accuracy of the model on the public HAR dataset (NTU-RGB + D, Kinetics-Skeleton).
- 21 June 2022
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (3) , 1833-1865
Overview of behavior recognition based on deep learning
- 21 June 2022
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (3) , 1833-1865
Overview of behavior recognition based on deep learning
- Open Access
- 7 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (12) , 5784
Human Action Recognition Based on Improved Two-Stream Convolution Network
Two-stream convolution network (2SCN) is a classical method of action recognition. It is capable of extracting action information from two dimensions: spatial and temporal streams. However, the method of extracting motion features from a spatial stream is single-frame recognition, and there is still room for improvement in the perception ability of appearance coherence features. The classical two-stream convolution network structure is modified in this paper by utilizing the strong mining capabilities of the bidirectional gated recurrent unit (BiGRU) to allow the neural network to extract the appearance coherence features of actions. In addition, this paper introduces an attention mechanism (SimAM) based on neuroscience theory, which improves the accuracy and stability of neural networks. Experiments show that the method proposed in this paper (BS-2SCN, BiGRU-SimAM Two-stream convolution network) has high accuracy. The accuracy is improved by 2.6% on the UCF101 data set and 11.7% on the HMDB51 data set.
- 7 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (12) , 5784
Open AccessHuman Action Recognition Based on Improved Two-Stream Convolution Network
Two-stream convolution network (2SCN) is a classical method of action recognition. It is capable of extracting action information from two dimensions: spatial and temporal streams. However, the method of extracting motion features from a spatial stream is single-frame recognition, and there is still room for improvement in the perception ability of appearance coherence features. The classical two-stream convolution network structure is modified in this paper by utilizing the strong mining capabilities of the bidirectional gated recurrent unit (BiGRU) to allow the neural network to extract the appearance coherence features of actions. In addition, this paper introduces an attention mechanism (SimAM) based on neuroscience theory, which improves the accuracy and stability of neural networks. Experiments show that the method proposed in this paper (BS-2SCN, BiGRU-SimAM Two-stream convolution network) has high accuracy. The accuracy is improved by 2.6% on the UCF101 data set and 11.7% on the HMDB51 data set.
- Top Cited PapersOpen Access
- 10 February 2022
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 10 (2) , 241
An Overview of Underwater Vision Enhancement: From Traditional Methods to Recent Deep Learning
Underwater video images, as the primary carriers of underwater information, play a vital role in human exploration and development of the ocean. Due to the optical characteristics of water bodies, underwater video images generally have problems such as color bias and unclear image quality, and image quality degradation is severe. Degenerated images have adverse effects on the visual tasks of underwater vehicles, such as recognition and detection. Therefore, it is vital to obtain high-quality underwater video images. Firstly, this paper analyzes the imaging principle of underwater images and the reasons for their decline in quality and briefly classifies various existing methods. Secondly, it focuses on the current popular deep learning technology in underwater image enhancement, and the underwater video enhancement technologies are also mentioned. It also introduces some standard underwater data sets, common video image evaluation indexes and underwater image specific indexes. Finally, this paper discusses possible future developments in this area.
- 10 February 2022
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 10 (2) , 241
Top Cited PapersOpen AccessAn Overview of Underwater Vision Enhancement: From Traditional Methods to Recent Deep Learning
Underwater video images, as the primary carriers of underwater information, play a vital role in human exploration and development of the ocean. Due to the optical characteristics of water bodies, underwater video images generally have problems such as color bias and unclear image quality, and image quality degradation is severe. Degenerated images have adverse effects on the visual tasks of underwater vehicles, such as recognition and detection. Therefore, it is vital to obtain high-quality underwater video images. Firstly, this paper analyzes the imaging principle of underwater images and the reasons for their decline in quality and briefly classifies various existing methods. Secondly, it focuses on the current popular deep learning technology in underwater image enhancement, and the underwater video enhancement technologies are also mentioned. It also introduces some standard underwater data sets, common video image evaluation indexes and underwater image specific indexes. Finally, this paper discusses possible future developments in this area.
- Open Access
- 19 January 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (3) , 1028
Skeleton Motion Recognition Based on Multi-Scale Deep Spatio-Temporal Features
In the task of human motion recognition, the overall action span is changeable, and there may be an inclusion relationship between action semantics. This paper proposes a novel multi-scale time sampling module and a deep spatiotemporal feature extraction module, which strengthens the receptive field of the feature map and strengthens the extraction of spatiotemporal-related feature information via the network. We study and compare the performance of three existing multi-channel fusion methods to improve the recognition accuracy of the network on the open skeleton recognition dataset. In this paper, several groups of comparative experiments are carried out on two public datasets. The experimental results show that compared with the classical 2s-AGCN algorithm, the accuracy of the algorithm proposed in this paper shows an improvement of 1% on the Kinetics dataset and 0.4% and 1% on the two evaluating indicators of the NTU-RGB+D dataset, respectively.
- 19 January 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (3) , 1028
Open AccessSkeleton Motion Recognition Based on Multi-Scale Deep Spatio-Temporal Features
In the task of human motion recognition, the overall action span is changeable, and there may be an inclusion relationship between action semantics. This paper proposes a novel multi-scale time sampling module and a deep spatiotemporal feature extraction module, which strengthens the receptive field of the feature map and strengthens the extraction of spatiotemporal-related feature information via the network. We study and compare the performance of three existing multi-channel fusion methods to improve the recognition accuracy of the network on the open skeleton recognition dataset. In this paper, several groups of comparative experiments are carried out on two public datasets. The experimental results show that compared with the classical 2s-AGCN algorithm, the accuracy of the algorithm proposed in this paper shows an improvement of 1% on the Kinetics dataset and 0.4% and 1% on the two evaluating indicators of the NTU-RGB+D dataset, respectively.
- Open Access
- 27 October 2021
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 9 (11) , 1189
A Control Algorithm for Sea–Air Cooperative Observation Tasks Based on a Data-Driven Algorithm
There is tremendous demand for marine environmental observation, which requires the development of a multi-agent cooperative observation algorithm to guide Unmanned Surface Vehicles (USVs) and Unmanned Aerial Vehicles (UAVs) to observe isotherm data of the mesoscale vortex. The task include two steps: firstly, USVs search out the isotherm, navigate independently along the isotherm, and collect marine data; secondly, a UAV takes off, and in its one round trip, the UAV and USVs jointly perform the task of the UAV reading the observation data from USVs. In this paper, aiming at the first problem of the USV following the isotherm in an unknown environment, a data-driven Deep Deterministic Policy Gradient (DDPG) control algorithm is designed that allows USVs to navigate independently along isotherms in unknown environments. In addition, a hybrid cooperative control algorithm based on a multi-agent DDPG is adopted to solve the second problem, which enables USVs and a UAV to complete data reading tasks with the shortest flight distance of the UAV. The experimental simulation results show that the trained system can complete this tas, with good stability and accuracy.
- 27 October 2021
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 9 (11) , 1189
Open AccessA Control Algorithm for Sea–Air Cooperative Observation Tasks Based on a Data-Driven Algorithm
There is tremendous demand for marine environmental observation, which requires the development of a multi-agent cooperative observation algorithm to guide Unmanned Surface Vehicles (USVs) and Unmanned Aerial Vehicles (UAVs) to observe isotherm data of the mesoscale vortex. The task include two steps: firstly, USVs search out the isotherm, navigate independently along the isotherm, and collect marine data; secondly, a UAV takes off, and in its one round trip, the UAV and USVs jointly perform the task of the UAV reading the observation data from USVs. In this paper, aiming at the first problem of the USV following the isotherm in an unknown environment, a data-driven Deep Deterministic Policy Gradient (DDPG) control algorithm is designed that allows USVs to navigate independently along isotherms in unknown environments. In addition, a hybrid cooperative control algorithm based on a multi-agent DDPG is adopted to solve the second problem, which enables USVs and a UAV to complete data reading tasks with the shortest flight distance of the UAV. The experimental simulation results show that the trained system can complete this tas, with good stability and accuracy.
- Open Access
- 26 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (17) , 7876
Action Recognition Algorithm of Spatio–Temporal Differential LSTM Based on Feature Enhancement
The Long Short-Term Memory (LSTM) network is a classic action recognition method because of its ability to extract time information. Researchers proposed many hybrid algorithms based on LSTM for human action recognition. In this paper, an improved Spatio–Temporal Differential Long Short-Term Memory (ST-D LSTM) network is proposed, an enhanced input differential feature module and a spatial memory state differential module are added to the network. Furthermore, a transmission mode of ST-D LSTM is proposed; this mode enables ST-D LSTM units to transmit the spatial memory state horizontally. Finally, these improvements are added into classical Long-term Recurrent Convolutional Networks (LRCN) to test the new network’s performance. Experimental results show that ST-D LSTM can effectively improve the accuracy of LRCN.
- 26 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (17) , 7876
Open AccessAction Recognition Algorithm of Spatio–Temporal Differential LSTM Based on Feature Enhancement
The Long Short-Term Memory (LSTM) network is a classic action recognition method because of its ability to extract time information. Researchers proposed many hybrid algorithms based on LSTM for human action recognition. In this paper, an improved Spatio–Temporal Differential Long Short-Term Memory (ST-D LSTM) network is proposed, an enhanced input differential feature module and a spatial memory state differential module are added to the network. Furthermore, a transmission mode of ST-D LSTM is proposed; this mode enables ST-D LSTM units to transmit the spatial memory state horizontally. Finally, these improvements are added into classical Long-term Recurrent Convolutional Networks (LRCN) to test the new network’s performance. Experimental results show that ST-D LSTM can effectively improve the accuracy of LRCN.