User Re-Identification via Confusion of the Contrastive Distillation Network and Attention Mechanism.

With the rise of social networks, more and more users share their location on social networks. This gives us a new perspective on the study of user movement patterns. In this paper, we solve the trajectory re-identification task by identifying human movement patterns and then linking unknown trajectories to the user who generated them. Existing solutions generally focus on the location point and the location point information, or a single trajectory, and few studies pay attention to the information between the trajectory and the trajectory. For this reason, in this paper, we propose a new model based on a contrastive distillation network, which uses a contrastive distillation model and attention mechanisms to capture latent semantic information for trajectory sequences and focuses on common key information between pairs of trajectories. Combined with the trajectory library composed of historical trajectories, it not only reduces the number of candidate trajectories but also improves the accuracy of trajectory re-identification. Our extensive experiments on three real-world location-based social network (LBSN) datasets show that our method outperforms existing methods.

CrossFuNet: RGB and Depth Cross-Fusion Network for Hand Pose Estimation.

Despite recent successes in hand pose estimation from RGB images or depth maps, inherent challenges remain. RGB-based methods suffer from heavy self-occlusions and depth ambiguity. Depth sensors rely heavily on distance and can only be used indoors, thus there are many limitations to the practical application of depth-based methods. The aforementioned challenges have inspired us to combine the two modalities to offset the shortcomings of the other. In this paper, we propose a novel RGB and depth information fusion network to improve the accuracy of 3D hand pose estimation, which is called CrossFuNet. Specifically, the RGB image and the paired depth map are input into two different subnetworks, respectively. The feature maps are fused in the fusion module in which we propose a completely new approach to combine the information from the two modalities. Then, the common method is used to regress the 3D key-points by heatmaps. We validate our model on two public datasets and the results reveal that our model outperforms the state-of-the-art methods.

EANet: Depth Estimation Based on EPI of Light Field.

The light field is an important way to record the spatial information of the target scene. The purpose of this paper is to obtain depth information through the processing of light field information and provide a basis for intelligent medical treatment. In this paper, we first design an attention module to extract the features of light field images and connect all the features as a feature map to generate an attention image. Then, the attention map is integrated with the convolution layer in the neural network in the form of weights to enhance the weight of the subaperture viewpoint, which is more meaningful for depth estimation. Finally, the obtained initial depth results were optimized. The experimental results show that the MSE, PSNR, and SSIM of the depth map obtained by this method are increased by about 13%, 10 dB, and 4%, respectively, in some scenarios with good performance.