Pedestrian reidentification (ReID) is a challenging task that involves identifying and retrieving specific pedestrians across different cameras and scenes. This problem has significant implications for security surveillance, and has thus received substantial attention in recent years. However, traditional convolutional neural networks (CNNs) have limited receptive fields and cannot capture global information. Moreover, transformer networks, which excel in long-range feature capture, are prone to accuracy degradation due to loss of details. To address these limitations, we propose a transformer-based pedestrian ReID network with double-branch information mutual gain (DIMGNet), which leverages hierarchical parallel levels to support multi-granularity feature information mutual gain. Our model also incorporates an auxiliary camera information (ACI) module to improve feature representation ability. We further embed a cross-attention mechanism into the architecture to enhance mutual gain between multi-granularity features and improve feature discrimination. Finally, we introduce a shuffling technique to increase the robustness of the extracted features. We evaluate the proposed method on several benchmark datasets, including Market-1501[1], MSMT17[2], DukeMTMC-reID [3], and Occluded-Duke [4], achieving $mAP$ values of 90.7%, 68.4%, 83.7%, and 60.6%, respectively. Our method outperforms most state-of-the-art methods, demonstrating the effectiveness of our method. The code will be publicly released at https://github.com/ZhenlinZhu/DIMGNet .

Traditional methods of electroencephalograms(EEG) data augmentation, such as segmentation-reassembly and noise mixing, suffer from data distortion that can alter the original temporal and spatial feature distributions of the brain signals. Deep learning-based methods for generating augmentation EEG data, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), have shown promising performance but require a large number of comparative learning samples for model training. To address these issues, this paper introduces an EEG data augmentation method based on Gaussian Mixture Model microstates, which retains the spatiotemporal dynamic features of the EEG signals in the generated data. The method first performs Gaussian mixture clustering on data samples of the same class, using the product of the probability coefficients and weight matrices of each Gaussian model as corresponding microstate features. Next, it randomly selects two EEG data samples of the same type, analyzes the similarity of the main components of the microstate features, and swaps the similar main components to form new Gaussian mixture model features. Finally, new data is generated according to the Gaussian mixture model using the respective model probabilities, weights, means, and variances. Experimental results on publicly available datasets demonstrate that the proposed method effectively characterizes the original data's spatiotemporal and microstate features, improving the accuracy of subject task classification.

Shape descriptors are extensively used in shape analysis tasks such as shape correspondence, segmentation and retrieval, just to name a few. Their performances significantly determine the efficiency and effectiveness of subsequent applications. For this problem, we propose a novel powerful descriptor called Anisotropic Fractional Spectral Manifold Wavelet Descriptor (AFSMWD), built upon an extended manifold signal processing tool named Anisotropic Fractional Spectral Manifold Wavelet (AFSMW), which is also presented for the first time in this paper. The novelty of AFSMW is integrating the fractional theory into the common anisotropic spectral manifold wavelet. Compared to the existing wavelets, it provides one more new parameter, namely, the fractional order, to balance or enhance the transform coefficients among different shape vertices, enabling more flexible local shape analysis and more hidden shape structural information explored. Due to the advantages of this added parameter and the capability of analyzing shape features from multiple scales and orientations, the AFSMW allows us to construct the powerful descriptor AFSMWD just using the AFSMW transform coefficients of a very simple function. The proposed descriptor appears to be especially localizable, discriminative, and robust to noises. Extensive experiments have demonstrated that our descriptor has outperformed the state-of-the-art descriptors, nearly achieving 22% improvements to the most related work ASMWD and 69% to the recent popular work WEDS on the FAUST dataset. Its superiorities are also announced in some challenging occasions such as shapes with large deformation or topological partiality.

Traditional methods of electroencephalograms(EEG) data augmentation, such as segmentation-reassembly and noise mixing, suffer from data distortion that can alter the original temporal and spatial feature distributions of the brain signals. Deep learning-based methods for generating augmentation EEG data, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), have shown promising performance but require a large number of comparative learning samples for model training. To address these issues, this paper introduces an EEG data augmentation method based on Gaussian Mixture Model microstates, which retains the spatiotemporal dynamic features of the EEG signals in the generated data. The method first performs Gaussian mixture clustering on data samples of the same class, using the product of the probability coefficients and weight matrices of each Gaussian model as corresponding microstate features. Next, it randomly selects two EEG data samples of the same type, analyzes the similarity of the main components of the microstate features, and swaps the similar main components to form new Gaussian mixture model features. Finally, new data is generated according to the Gaussian mixture model using the respective model probabilities, weights, means, and variances. Experimental results on publicly available datasets demonstrate that the proposed method effectively characterizes the original data's spatiotemporal and microstate features, improving the accuracy of subject task classification.