Lin Mei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lin Mei has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Zheng Xu
School of Computer and Information Engineering, Institute for Artificial Intelligence, Shanghai Polytechnic University, Shanghai, China
5 shared publications - Xu Xu
Donghai Laboratory
3 shared publications - Chao Wang
School of Information Engineering, Zhejiang Ocean University, ZhouShan, China
2 shared publications Chuanping Hu
Third Research Institute of the Ministry of Public Security, Shanghai, China
2 shared publications- Guangming Zhu
Xidian University, Xi'an, China
2 shared publications - Liang Zhang
Xidian University, Xi'an, China
2 shared publications
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4907-4911
WaveCSI-Net: Adaptive Multi-Resolution Wavelet Network for Massive MIMO CSI Feedback
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4907-4911
WaveCSI-Net: Adaptive Multi-Resolution Wavelet Network for Massive MIMO CSI Feedback
- Top Cited Papers
- 10 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-13
DMM: Disparity-Guided Multispectral Mamba for Oriented Object Detection in Remote Sensing
Multispectral oriented object detection faces challenges due to both inter-modal and intra-modal discrepancies. Recent studies often rely on transformer-based models to address these issues and achieve cross-modal fusion detection. However, the quadratic computational complexity of transformers limits their performance in remote sensing imagery. Inspired by the efficiency and lower complexity of Mamba in long sequence tasks, we propose Disparity-guided Multispectral Mamba (DMM), a multispectral oriented object detection framework comprised of a Disparity-guided Cross-modal Fusion Mamba (DCFM) module, a Multi-scale Target-aware Attention (MTA) module, and a Target-Prior Aware (TPA) auxiliary task. The DCFM module leverages disparity information between modalities to adaptively merge features from RGB and IR images, mitigating inter-modal conflicts. The MTA module aims to enhance feature representation by focusing on relevant target regions within the RGB modality, addressing intra-modal variations. The TPA auxiliary task utilizes single-modal labels to guide the optimization of the MTA module, ensuring it focuses on targets and their local context. Extensive experiments on the DroneVehicle and VEDAI datasets demonstrate the effectiveness of our method, which outperforms state-of-the-art methods while maintaining computational efficiency. Code will be available at https://github.com/Another-0/DMM.
- 10 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-13
Top Cited PapersDMM: Disparity-Guided Multispectral Mamba for Oriented Object Detection in Remote Sensing
Multispectral oriented object detection faces challenges due to both inter-modal and intra-modal discrepancies. Recent studies often rely on transformer-based models to address these issues and achieve cross-modal fusion detection. However, the quadratic computational complexity of transformers limits their performance in remote sensing imagery. Inspired by the efficiency and lower complexity of Mamba in long sequence tasks, we propose Disparity-guided Multispectral Mamba (DMM), a multispectral oriented object detection framework comprised of a Disparity-guided Cross-modal Fusion Mamba (DCFM) module, a Multi-scale Target-aware Attention (MTA) module, and a Target-Prior Aware (TPA) auxiliary task. The DCFM module leverages disparity information between modalities to adaptively merge features from RGB and IR images, mitigating inter-modal conflicts. The MTA module aims to enhance feature representation by focusing on relevant target regions within the RGB modality, addressing intra-modal variations. The TPA auxiliary task utilizes single-modal labels to guide the optimization of the MTA module, ensuring it focuses on targets and their local context. Extensive experiments on the DroneVehicle and VEDAI datasets demonstrate the effectiveness of our method, which outperforms state-of-the-art methods while maintaining computational efficiency. Code will be available at https://github.com/Another-0/DMM.
- 4 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 13 (10) , 2937-2941
HCC-Net: Holistic Cross-Joint Convolutional Network for CSI Feedback in Massive MIMO Systems
With the rapid development of massive multiple-input multiple-output (mMIMO) techniques, the network capacity, number of served users and communication efficiency have been improved dramatically compared to that with limited number of antennas. These advantages are established based on accurate channel state information (CSI) at the base station (BS), which comes with a very high cost due to continuous CSI feedback from all the user equipments (UEs). In this letter, we propose a neural network-based CSI compression scheme with simple encoder-decoder framework for mMIMO systems. To achieve high accuracy, our proposed framework constructs an overall perceptual encoder-decoder structure with holistic cross-joint convolution (HCC) modules of different scales. In addition, a perceptual loss is introduced into the proposed design to further improve the accuracy in matrix recovery and limits the computational cost. Substantial experimental results demonstrate that the proposed HCC network (HCC-Net) is superior to several advanced algorithms in terms of estimation accuracy and computational complexity, such as the CSiNet+ and TransNet.
- 4 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 13 (10) , 2937-2941
HCC-Net: Holistic Cross-Joint Convolutional Network for CSI Feedback in Massive MIMO Systems
With the rapid development of massive multiple-input multiple-output (mMIMO) techniques, the network capacity, number of served users and communication efficiency have been improved dramatically compared to that with limited number of antennas. These advantages are established based on accurate channel state information (CSI) at the base station (BS), which comes with a very high cost due to continuous CSI feedback from all the user equipments (UEs). In this letter, we propose a neural network-based CSI compression scheme with simple encoder-decoder framework for mMIMO systems. To achieve high accuracy, our proposed framework constructs an overall perceptual encoder-decoder structure with holistic cross-joint convolution (HCC) modules of different scales. In addition, a perceptual loss is introduced into the proposed design to further improve the accuracy in matrix recovery and limits the computational cost. Substantial experimental results demonstrate that the proposed HCC network (HCC-Net) is superior to several advanced algorithms in terms of estimation accuracy and computational complexity, such as the CSiNet+ and TransNet.
- Open Access
- 27 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56 (5) , 1-51
A Systematic Collection of Medical Image Datasets for Deep Learning
The astounding success made by artificial intelligence in healthcare and other fields proves that it can achieve human-like performance. However, success always comes with challenges. Deep learning algorithms are data dependent and require large datasets for training. Many junior researchers face a lack of data for a variety of reasons. Medical image acquisition, annotation, and analysis are costly, and their usage is constrained by ethical restrictions. They also require several other resources, such as professional equipment and expertise. That makes it difficult for novice and non-medical researchers to have access to medical data. Thus, as comprehensively as possible, this article provides a collection of medical image datasets with their associated challenges for deep learning research. We have collected the information of approximately 300 datasets and challenges mainly reported between 2007 and 2020 and categorized them into four categories: head and neck, chest and abdomen, pathology and blood, and others. The purpose of our work is to provide a list, as up-to-date and complete as possible, that can be used as a reference to easily find the datasets for medical image analysis and the information related to these datasets.
- 27 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56 (5) , 1-51
Open AccessA Systematic Collection of Medical Image Datasets for Deep Learning
The astounding success made by artificial intelligence in healthcare and other fields proves that it can achieve human-like performance. However, success always comes with challenges. Deep learning algorithms are data dependent and require large datasets for training. Many junior researchers face a lack of data for a variety of reasons. Medical image acquisition, annotation, and analysis are costly, and their usage is constrained by ethical restrictions. They also require several other resources, such as professional equipment and expertise. That makes it difficult for novice and non-medical researchers to have access to medical data. Thus, as comprehensively as possible, this article provides a collection of medical image datasets with their associated challenges for deep learning research. We have collected the information of approximately 300 datasets and challenges mainly reported between 2007 and 2020 and categorized them into four categories: head and neck, chest and abdomen, pathology and blood, and others. The purpose of our work is to provide a list, as up-to-date and complete as possible, that can be used as a reference to easily find the datasets for medical image analysis and the information related to these datasets.
- 18 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Adaptive Temporal-Frequency Network for Time-Series Forecasting
A novel adaptive temporal-frequency network (ATFN), which is an end-to-end hybrid model incorporating deep learning networks and frequency patterns, is proposed for mid- and long-term time series forecasting. Within the framework of the ATFN, an augmented sequence to sequence model is used to learn the trend feature of complicated nonstationary time series, a frequency-domain block is used to capture dynamic and complicated periodic patterns of time series data, and a fully connected neural network is used to combine the trend and periodic features for producing a final forecast. An adaptive frequency mechanism consisting of phase adaption, frequency adaption, and amplitude adaption is designed for mapping the frequency spectrum of the current sliding window to that of the forecasting interval. The multilayer neural networks conduct a transformation similar to the inverse discrete Fourier transform for generating a periodic feature forecast. Synthetic data and real-world data with different periodic characteristics are used to evaluate the effectiveness of the proposed model. The experimental results indicate that the ATFN has promising performance and strong adaptability for long-term time-series forecasting.
- 18 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Adaptive Temporal-Frequency Network for Time-Series Forecasting
A novel adaptive temporal-frequency network (ATFN), which is an end-to-end hybrid model incorporating deep learning networks and frequency patterns, is proposed for mid- and long-term time series forecasting. Within the framework of the ATFN, an augmented sequence to sequence model is used to learn the trend feature of complicated nonstationary time series, a frequency-domain block is used to capture dynamic and complicated periodic patterns of time series data, and a fully connected neural network is used to combine the trend and periodic features for producing a final forecast. An adaptive frequency mechanism consisting of phase adaption, frequency adaption, and amplitude adaption is designed for mapping the frequency spectrum of the current sliding window to that of the forecasting interval. The multilayer neural networks conduct a transformation similar to the inverse discrete Fourier transform for generating a periodic feature forecast. Synthetic data and real-world data with different periodic characteristics are used to evaluate the effectiveness of the proposed model. The experimental results indicate that the ATFN has promising performance and strong adaptability for long-term time-series forecasting.
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 31 (4) , 1323-1335
Redundancy and Attention in Convolutional LSTM for Gesture Recognition
Convolutional long short-term memory (ConvLSTM) networks have been widely used for action/gesture recognition, and different attention mechanisms have also been embedded into ConvLSTM networks. This paper explores the redundancy of spatial convolutions and the effects of the attention mechanism in ConvLSTM, based on our previous gesture recognition architectures that combine the 3-D convolutional neural network (CNN) and ConvLSTM. Depthwise separable, group, and shuffle convolutions are used to replace the convolutional structures in ConvLSTM for the redundancy analysis. In addition, four ConvLSTM variants are derived for attention analysis: 1) by removing the convolutional structures of the three gates in ConvLSTM; 2) by applying the attention mechanism on the ConvLSTM input; and 3) by reconstructing the input and 4) output gates with the modified channelwise attention mechanism. Evaluation results demonstrate that the spatial convolutions in the three gates scarcely contribute to the spatiotemporal feature fusion and that the attention mechanisms embedded into the input and output gates cannot improve the feature fusion. In other words, ConvLSTM mainly contributes to the temporal fusion along with the recurrent steps to learn long-term spatiotemporal features when taking spatial or spatiotemporal features as input. A new LSTM variant is derived on this basis in which the convolutional structures are embedded only into the input-to-state transition of LSTM. The code of the LSTM variants is publicly available.\footnotehttps://github.com/GuangmingZhu/ConvLSTMForGR.
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 31 (4) , 1323-1335
Redundancy and Attention in Convolutional LSTM for Gesture Recognition
Convolutional long short-term memory (ConvLSTM) networks have been widely used for action/gesture recognition, and different attention mechanisms have also been embedded into ConvLSTM networks. This paper explores the redundancy of spatial convolutions and the effects of the attention mechanism in ConvLSTM, based on our previous gesture recognition architectures that combine the 3-D convolutional neural network (CNN) and ConvLSTM. Depthwise separable, group, and shuffle convolutions are used to replace the convolutional structures in ConvLSTM for the redundancy analysis. In addition, four ConvLSTM variants are derived for attention analysis: 1) by removing the convolutional structures of the three gates in ConvLSTM; 2) by applying the attention mechanism on the ConvLSTM input; and 3) by reconstructing the input and 4) output gates with the modified channelwise attention mechanism. Evaluation results demonstrate that the spatial convolutions in the three gates scarcely contribute to the spatiotemporal feature fusion and that the attention mechanisms embedded into the input and output gates cannot improve the feature fusion. In other words, ConvLSTM mainly contributes to the temporal fusion along with the recurrent steps to learn long-term spatiotemporal features when taking spatial or spatiotemporal features as input. A new LSTM variant is derived on this basis in which the convolutional structures are embedded only into the input-to-state transition of LSTM. The code of the LSTM variants is publicly available.\footnotehttps://github.com/GuangmingZhu/ConvLSTMForGR.
- 24 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 5 (4) , 529-539
Multi-Modal Description of Public Safety Events Using Surveillance and Social Media
A public safety event is a danger and urgent event that need early detection, quick response, and accuracy recover. The efficient method for responding to a happening public safety event is to collect and describe the related data. Besides the surveillance cameras from the physical space, the social media data can also be used to collect and describe the related data of a public safety event. In this work, the proposed method focuses on the step for describing public safety events. Given a public safety event, videos from the surveillance cameras and social messages from social sensors are collected. The multi-modal information including texts, images, videos, and spatial-temporal data is mined to give a description precisely and concisely. First, the social sensors are associated to surveillance cameras by the spatial and temporal information. In the second stage, the social messages are associated to surveillance cameras by the semantic information. In the third stage, the social messages are associated to surveillance cameras by the visual feature. Besides the text, social sensors may upload images or videos. Finally, the multi-modal description step is given based on the three different associations. The experiments on the real data demonstrate the superiority of the proposed framework. Case studies on the real public safety event show the proposed model has good performance and high effectiveness.
- 24 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 5 (4) , 529-539
Multi-Modal Description of Public Safety Events Using Surveillance and Social Media
A public safety event is a danger and urgent event that need early detection, quick response, and accuracy recover. The efficient method for responding to a happening public safety event is to collect and describe the related data. Besides the surveillance cameras from the physical space, the social media data can also be used to collect and describe the related data of a public safety event. In this work, the proposed method focuses on the step for describing public safety events. Given a public safety event, videos from the surveillance cameras and social messages from social sensors are collected. The multi-modal information including texts, images, videos, and spatial-temporal data is mined to give a description precisely and concisely. First, the social sensors are associated to surveillance cameras by the spatial and temporal information. In the second stage, the social messages are associated to surveillance cameras by the semantic information. In the third stage, the social messages are associated to surveillance cameras by the visual feature. Besides the text, social sensors may upload images or videos. Finally, the multi-modal description step is given based on the three different associations. The experiments on the real data demonstrate the superiority of the proposed framework. Case studies on the real public safety event show the proposed model has good performance and high effectiveness.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 4 (2) , 245-257
From Latency, Through Outbreak, to Decline: Detecting Different States of Emergency Events Using Web Resources
An emergency event is a sudden, urgent, usually unexpected incident or occurrence that requires an immediate reaction or assistance for emergency situations, which plays an increasingly important role in the global economy and in our daily lives. Recently, the web is becoming an important event information provider and repository due to its real-time, open, and dynamic features. In this paper, web resources based states detecting algorithm of an event is developed in order to let the people know of an emergency event clearly and help the social group or government process the emergency events effectively. The relationship between web and emergency events is first introduced, which is the foundation of using web resources to detect the state of emergency events imaged on the web. Second, five temporal features of emergency events are developed to provide the basis for state detection. Moreover, the outbreak power and the fluctuation power are presented to integrate the above temporal features for measuring the different states of an emergency event. Using these two powers, an automatic state detecting algorithm for emergency events is proposed. In addition, heuristic rules for detecting the states of emergency event on the web are discussed. Our evaluations using real-world data sets demonstrate the utility of the proposed algorithm, in terms of performance and effectiveness in the analysis of emergency events.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 4 (2) , 245-257
From Latency, Through Outbreak, to Decline: Detecting Different States of Emergency Events Using Web Resources
An emergency event is a sudden, urgent, usually unexpected incident or occurrence that requires an immediate reaction or assistance for emergency situations, which plays an increasingly important role in the global economy and in our daily lives. Recently, the web is becoming an important event information provider and repository due to its real-time, open, and dynamic features. In this paper, web resources based states detecting algorithm of an event is developed in order to let the people know of an emergency event clearly and help the social group or government process the emergency events effectively. The relationship between web and emergency events is first introduced, which is the foundation of using web resources to detect the state of emergency events imaged on the web. Second, five temporal features of emergency events are developed to provide the basis for state detection. Moreover, the outbreak power and the fluctuation power are presented to integrate the above temporal features for measuring the different states of an emergency event. Using these two powers, an automatic state detecting algorithm for emergency events is proposed. In addition, heuristic rules for detecting the states of emergency event on the web are discussed. Our evaluations using real-world data sets demonstrate the utility of the proposed algorithm, in terms of performance and effectiveness in the analysis of emergency events.
- 20 April 2016
- Published by Springer Nature
- Vol. 375, 1147-1152
The Intelligent Big Data Analytics Framework for Surveillance Video System
- 20 April 2016
- Published by Springer Nature
- Vol. 375, 1147-1152
The Intelligent Big Data Analytics Framework for Surveillance Video System
- 3 December 2015
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 75 (19) , 12155-12172
Video structured description technology based intelligence analysis of surveillance videos for public security applications
- 3 December 2015
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 75 (19) , 12155-12172
Video structured description technology based intelligence analysis of surveillance videos for public security applications