In the task of person re-identification, the attention mechanism and fine-grained information have been proved to be effective. However, it has been observed that models often focus on the extraction of features with strong discrimination, and neglect other valuable features. The extracted fine-grained information may include redundancies. In addition, current methods lack an effective scheme to remove background interference. Therefore, this paper proposes the feature refinement and filter network to solve the above problems from three aspects: first, by weakening the high response features, we aim to identify highly valuable features and extract the complete features of persons, thereby enhancing the robustness of the model; second, by positioning and intercepting the high response areas of persons, we eliminate the interference arising from background information and strengthen the response of the model to the complete features of persons; finally, valuable fine-grained features are selected using a multi-branch attention network for person re-identification to enhance the performance of the model. Our extensive experiments on the benchmark Market-1501, DukeMTMC-reID, CUHK03 and MSMT17 person re-identification datasets demonstrate that the performance of our method is comparable to that of state-of-the-art approaches.

At present, effectively aggregating and transferring the local features of point cloud is still an unresolved technological conundrum. In this study, we propose a new space-cover convolutional neural network (SC-CNN) for tasks such as point cloud classification and segmentation. The core of this network is space-cover convolution (SC-Conv), which implements depthwise separable convolution on the point cloud. In addition, a newly designed space-cover operator (SCOP) replaces depthwise convolution. The key to SC-Conv is constructing anisotropic spatial geometry in the local point cloud. The SCOP achieves this by utilizing the positional and feature relationships to learn the high-order relationship expression between points. First, data-driven adaptive learning from the 3-D coordinate relationship between the local points is used to determine the weight of the SCOP. Then, the edge feature of the neighboring point relative to the sampling point is used as the input of the SCOP. Finally, a deformable spatial geometry is constructed in the feature space between local points to aggregate the local high-order features. By stacking SC-Conv to construct SC-CNN with a hierarchical network structure for point cloud analysis, we can better perceive the shape information of point cloud and improve network robustness. Finally, we provide numerous experiments to verify that SC-CNN parallels or even outperforms advanced methods in shape classification, part segmentation, and large-scale indoor scene segmentation tasks. The open-source code was published at https://github.com/changshuowang/SC-CNN .

Different face regions have different contributions to recognition. Especially in the wild environment, the difference of contributions will be further amplified due to a lot of interference. Based on this, this paper proposes an attention-aware face recognition method based on a deep convolutional neural network and reinforcement learning. The proposed method composes of an Attention-Net and a Feature-net. The Attention-Net is used to select patches in the input face image according to the facial landmarks and trained with reinforcement learning to maximize the recognition accuracy. The Feature-net is used for extracting discriminative embedding features. In addition, a regularization method has also been introduced. The mask of the input layer is also applied to the intermediate feature maps, which is an approximation to train a series of models for different face patches and provide a combined model. Our method achieves satisfactory recognition performance on its application to the public prevailing face verification database.

Modeling, prediction, and recognition tasks depend on the proper representation of the objective curves and surfaces. Polynomial functions have been proved to be a powerful tool for representing curves and surfaces. Until now, various methods have been used for polynomial fitting. With a recent boom in neural networks, researchers have attempted to solve polynomial fitting by using this end-to-end model, which has a powerful fitting ability. However, the current neural network-based methods are poor in stability and slow in convergence speed. In this article, we develop a novel neural network-based method, called Encoder-X, for polynomial fitting, which can solve not only the explicit polynomial fitting but also the implicit polynomial fitting. The method regards polynomial coefficients as the feature value of raw data in a polynomial space expression and therefore polynomial fitting can be achieved by a special autoencoder. The entire model consists of an encoder defined by a neural network and a decoder defined by a polynomial mathematical expression. We input sampling points into an encoder to obtain polynomial coefficients and then input them into a decoder to output the predicted function value. The error between the predicted function value and the true function value can update parameters in the encoder. The results prove that this method is better than the compared methods in terms of stability, convergence, and accuracy. In addition, Encoder-X can be used for solving other mathematical modeling tasks.

Finger vein recognition has attracted considerable attention from the biometric identification technology community owing to its convenience and security. Unlike most previous works only pay attention to one part of finger vein recognition, we propose a joint Bayesian framework in this paper, which is based on partial least squares discriminant analysis (PLS-DA). It involves three major stages: 1) robust feature description, 2) discriminative feature mapping, and 3) separative verification. In stage 1), we extract line responses and orientation of finger veins using a bank of Gabor filter, and histograms are constructed in local patches as primitive features. Subsequently, in stage 2), a discriminant feature mapping based the PLS-DA (PLS-DA-FM) method is proposed to project these primitive features into low-dimensional forms in a supervised manner. Thus, highly compact and discriminative features are obtained in this stage. Finally, in stage 3), we directly build a Bayesian model based on the joint distribution of finger vein feature pairs to measure the similarity between the features. Extensive experiments on five finger vein datasets demonstrate the superior performance of the proposed method to most state-of-the-art finger vein recognition methods.