Gait recognition is a biometric technology that identifies people by their walking patterns. The silhouettes-based method and the skeletons-based method are the two most popular approaches. However, the silhouette data are easily affected by clothing occlusion, and the skeleton data lack body shape information. To obtain a more robust and comprehensive gait representation for recognition, we propose a transformer-based gait recognition framework called MMGaitFormer, which effectively fuses and aggregates the spatial-temporal information from the skeletons and silhouettes. Specifically, a Spatial Fusion M odule (SFM) and a Temporal Fusion Module (TFM) are proposed for effective spatial-level and temporal-level feature fusion, respectively. The SFM performs fine-grained body parts spatial fusion and guides the alignment of each part of the silhouette and each joint of the skeleton through the attention mechanism. The TFM performs temporal modeling through Cycle Position Embedding (CPE) andfuses temporal information of two modalities. Experiments demonstrate that our MMGaitFormer achieves state-of-the-art performance on popular gait datasets. For the most challenging “CL” (i.e., walking in different clothes) condition in CASIA-B, our method achieves a rank-l accuracy of 94. 8%, which outperforms the state-of-the-art single-modal methods by a large margin.

Gait recognition aims to identify different people by walking patterns in a long-distance. At present, most gait recognition methods mainly focus on short-term temporal frame-level feature modeling, while long-term temporal relations and some prior information such as view angle, walking condition are not fully exploited. To alleviate this issue, we propose a transformer-based gait recognition framework called GaitTransformer. A Multiple-Temporal-Scale Transformer (MTST), which consists of multiple transformer encoders with multi-scale position embedding is proposed for the framework to integrate various long-term information of the sequence. Moreover, we further design a knowledge embedding for the MTST to model prior knowledge information. Experiments demonstrate that our GaitTransformer achieves state-of-the-art performance on popular gait datasets.

Local features have been shown effective in supervised person re-identification (Re-ID). However, it is hard to obtain workable local features in an unsupervised situation. In this paper, we propose a novel method to learn discriminative multiple granularity features in unsupervised domain adaptation (UDA) Re-ID. Firstly, we propose Multiple Granularity Memory Dictionary Group (MGMDG) to learn discriminative local features and global features respectively by contrastive learning for features of each granularity with the corresponding memory dictionary. Secondly, we design a teacher-student framework in which the teacher model supervises the student model to learn the multiple granularity features with a soft triplet loss. Finally, we use the concatenation of multiple granularity features to generate better pseudo labels for local features. Extensive experimental results show that the performance of the proposed method on Market1501, DukeMTMC, MSMT17 datasets significantly outperforms the state-of-the-art UDA Re-ID methods by a large margin.

In practical application, the existing gender and age recognition algorithms can’t meet the requirements of both smallsized model and high accuracy simultaneously. Moreover, most models based on CNNs have a even larger size of more than 200M. In this paper a multi-layer multi-channel attentive network based on the idea of divide-and-conquer is proposed. This method uses multi-layer processes in each channel to extract features of different layers and improves accuracy by layer refinement. We use some dynamic parameters to fine- tune each layer to make the model fit better. Each layer uses the same classifier to reduce parameters to make the model smaller. And we import attention mechanisms to increase the ability of the network to use the features. Experiments show that the accuracy of this method is better than several mainstream networks and the size of the model is less than 0.5M, which can be used in mobile terminals well.

Time-of-arrival (TOA) is a widely used localization technique in robotic localization systems. However, TOA-based methods require strict time synchronization between the source (target) and sensors (receivers), which significantly influences the localization accuracy. In this paper, we propose an iterative Time-of-arrival (iTOA) localization technique to eliminate the time synchronization error in robotic localization systems. iTOA first measures the distance between the source and sensors according to the travel time of the signal. Then, iTOA constructs the multivariate linear model based on the measured distances, position of sensors, and unknown synchronization error, and uses the least square method to calculate the synchronization error. Finally, by using the constructed model and iteratively subtracting the synchronization error, we obtain the precise source localization with the near-zero synchronization error. For the synchronization error elimination, iTOA can work well in both the two-dimensional (2-D) and 3-D space. We conduct experiments in both a simulation environment and a real sensor system to demonstrate the effectiveness of the proposed scheme. The experimental results show that the accuracy of localization is improved by more than 31% and 26% on average compared with the representative algorithms in the simulation and real environments, respectively.

In this paper, we propose a reliable video storage architecture in hybrid SLC/MLC storage systems. In this architecture, the video stream is reconstructed as the key cluster and the non-key cluster according to the importance of video restoration. The key cluster is stored in SLC blocks to ensure the reliability, while the non-key cluster is stored in MLC blocks to utilize its capacity. The experimental results show that the proposed scheme can significantly improve the storage reliability of the video files and prolong the lifetime of the storage system 18x.