As a result of its important role in video surveillance, pedestrian attribute recognition has become an attractive facet of computer vision research. Because of the changes in viewpoints, illumination, resolution and occlusion, the task is very challenging. In order to resolve the issue of unsatisfactory performance of existing pedestrian attribute recognition methods resulting from ignoring the correlation between pedestrian attributes and spatial information, in this paper, the task is regarded as a spatiotemporal, sequential, multi-label image classification problem. An attention-based neural network consisting of convolutional neural networks (CNN), channel attention (CAtt) and convolutional long short-term memory (ConvLSTM) is proposed (CNN-CAtt-ConvLSTM). Firstly, the salient and correlated visual features of pedestrian attributes are extracted by pre-trained CNN and CAtt. Then, ConvLSTM is used to further extract spatial information and correlations from pedestrian attributes. Finally, pedestrian attributes are predicted with optimized sequences based on attribute image area size and importance. Extensive experiments are carried out on two common pedestrian attribute datasets, PEdesTrian Attribute (PETA) dataset and Richly Annotated Pedestrian (RAP) dataset, and higher performance than other state-of-the-art (SOTA) methods is achieved, which proves the superiority and validity of our method.

Language-based person search retrieves images of a target person using natural language description and is a challenging fine-grained cross-modal retrieval task. A novel hybrid attention network is proposed for the task. The network includes the following three aspects: First, a cubic attention mechanism for person image, which combines cross-layer spatial attention and channel attention. It can fully excavate both important midlevel details and key high-level semantics to obtain better discriminative fine-grained feature representation of a person image. Second, a text attention network for language description, which is based on bidirectional LSTM (BiLSTM) and self-attention mechanism. It can better learn the bidirectional semantic dependency and capture the key words of sentences, so as to extract the context information and key semantic features of the language description more effectively and accurately. Third, a cross-modal attention mechanism and a joint loss function for cross-modal learning, which can pay more attention to the relevant parts between text and image features. It can better exploit both the cross-modal and intra-modal correlation and can better solve the problem of cross-modal heterogeneity. Extensive experiments have been conducted on the CUHK-PEDES dataset. Our approach obtains higher performance than state-of-the-art approaches, demonstrating the advantage of the approach we propose.

Person re-identification (Re-ID) has attracted attention due to its wide range of applications. Most recent studies have focused on the extraction of deep features, while ignoring color features that can remain stable, even for illumination variations and the variation in person pose. There are also few studies that combine the powerful learning capabilities of deep learning with color features. Therefore, we hope to use the advantages of both to design a model with low computational resource consumption and excellent performance to solve the task of person re-identification. In this paper, we designed a color feature containing relative spatial information, namely the color feature with spatial information. Then, bidirectional long short-term memory (BLSTM) networks with an attention mechanism are used to obtain the contextual relationship contained in the hand-crafted color features. Finally, experiments demonstrate that the proposed model can improve the recognition performance compared with traditional methods. At the same time, hand-crafted features based on human prior knowledge not only reduce computational consumption compared with deep learning methods but also make the model more interpretable.

This paper treats person re-identification (re-id) as a sequential model, guide person re-id with person detection, combines recurrent neural network (RNN) with attention mechanism, and proposed an end to end person re-id method for surveillance scenarios. The feature of target person is firstly extracted using ResNet, and then the feature is added to the long short-term memory (LSTM) network to guide the attention model for the region of interest in the surveillance image. Finally, combined with the information observed from the image multiple times, the most similar candidate person in the image is deduced, and the feature distance is calculated and ranked for person re-id. This paper strengthens the relationship between person detection and person re-id, and reduces the error between models. Because the number of candidate person matched with target person is reduced, this method can process person re-id task with less calculation and time. This paper also verified the effectiveness of the proposed method by experiments comparing a variety of person detection and re-id methods on several person re-id datasets.

RGB–IR cross modality person re-identification (RGB–IR Re-ID) is an important task for video surveillance in poorly illuminated or dark environments. In addition to the common challenge of Re-ID, the large cross-modality variations between RGB and IR images must be considered. The existing RGB–IR Re-ID methods use different network structures to learn the global shared features associated with multi-modalities. However, most global shared feature learning methods are sensitive to background clutter, and contextual feature relationships are not considered among the mined features. To solve these problems, this paper proposes a dual-path attention network architecture MFCNet. SGA (Spatial-Global Attention) module embedded in MFCNet includes spatial attention and global attention branches to mine discriminative features. First, the SGA module proposed in this paper focuses on the key parts of the input image to obtain robust features. Next, the module mines the contextual relationships among features to obtain discriminative features and improve network performance. Finally, extensive experiments demonstrate that the performance of the network architecture proposed in this paper is better than that of state-of-the-art methods under various settings. In the all-search mode of the SYSU and RegDB data sets, the rank-1 accuracy reaches 51.64% and 69.76%, respectively.

Singer recognition is an important branch of music retrieval and classification. This paper focuses on the application of convolutional deep belief networks (CDBN) for singer recognition. First, the system architecture of singer recognition based on CDBN is given, and then the pre-processing of the song signal is described in detail, including sampling, framing, pre-emphasis and windowing. The feature extraction of song signal based on MFCC is described in detail, and the composition and principle of CDBN and its application in singer recognition are introduced. Experiment based on three different feature extraction techniques of LPCC, MFCC and CDBN is carried out and the result is compared and analysed, the experimental results show that CDBN is effective for singer recognition.