As an important part of intelligent surveillance systems, person re-identification (PReID) has drawn wide attention of the public in recent years. Many recent deep learning-based PReID methods have used attention or multi-scale feature learning modules to enhance the discrimination of the learned deep features. However, the attention mechanisms may lose some important feature information. Moreover, the multi-scale models usually embed the multi-scale feature learning module into the backbone network, which increases the complexity of testing network. To address the two issues, we propose a multi-scale deep supervision with attention feature learning deep model for PReID. Specifically, we introduce a reverse attention module to remedy the feature information losing issue caused by the attention module, and a multi-scale feature learning layer with deep supervision to train the network. The proposed modules are only used at the training phase and discarded during the test phase. Experiments on Market-1501, DukeMTMC-reID, CUHK03 and MSMT17 datasets. demonstrate that our model notably beats other competitive state-of-the-art models.

Deep learning approach has been used extensively in image analysis tasks. However, implementing the methods in 3D data is a bit complex because most of the previously designed deep learning architectures used 1D or 2D as input. In this work, the performance of deep learning methods on different 3D data representations has been reviewed. Based on the categorization of the different 3D data representations proposed in this paper, the importance of choosing a suitable 3D data representation which depends on simplicity, usability, and efficiency has been highlighted. Furthermore, the origin and contents of the major 3D datasets were discussed in detail. Due to growing interest in 3D object retrieval and classification tasks, the performance of different 3D object retrieval and classification on ModelNet40 dataset were compared. According to the findings in this work, multi views methods surpass voxel-based methods and with increased layers and enough data augmentation the performance can still be increased. Therefore, it can be concluded that deep learning together with a suitable 3D data representation gives an effective approach for improving the performance of 3D shape analysis. Finally, some possible directions for future researches were suggested.

This paper proposes a dual-stream 3D space-time convolutional neural network action recognition framework. The original depth map sequence data is set as the input in order to study the global space-time characteristics of each action category. The high correlation within the human action itself is considered in the time domain, and then the deep motion map sequence is introduced as the input to another stream of the 3D space-time convolutional network. Furthermore, the corresponding 3D skeleton sequence data is set as the third input of the whole recognition framework. Although the skeleton sequence data has the advantage of including 3D information, it is also confronted with the problems of the existence of rate change, temporal mismatch and noise. Thus, specially designed space-time features are applied to cope with these problems. The proposed methods allow the whole recognition system to fully exploit and utilize the discriminatory space-time features from different perspectives, and ultimately improve the classification accuracy of the system. Experimental results on different public 3D data sets illustrate the effectiveness of the proposed method.

For 3D action recognition, the main challenge is to extract long-range semantic information in both temporal and spatial dimensions. In this paper, in order to better excavate long-range semantic information from large number of unlabelled skeleton sequences, we propose Self-supervised Spatial-temporal Representation Learning (SSRL), a contrastive learning framework to learn skeleton representation. SSRL consists of two novel inference tasks that enable the network to learn global semantic information in the temporal and spatial dimensions, respectively. The temporal inference task learns the temporal persistence of human actions through temporally incomplete skeleton sequences. And the spatial inference task learns the spatially coordinated nature of human action through spatially partially skeleton sequence. We design two transformation modules to efficiently realize these two tasks while fitting the encoder network. To avoid the difficulty of constructing and maintaining high-quality negative samples, our proposed framework learns by maintaining consistency among positive samples without the need of any negative sample. Experiments demonstrate that our proposed method can achieve better results in comparison with state-of-the-art methods under a variety of evaluation protocols on NTU RGB+D 60, PKU-MMD and NTU RGB+D 120 datasets.

Self-supervised representation learning for videos has been very attractive recently because these methods exploit the information inherently obtained from the video itself instead of annotated labels that is quite time-consuming. However, existing methods ignore the importance of global observation while performing spatio-temporal transformation perception, which highly limits the expression capabilities of the video representation. This paper proposes a novel pretext task that combines the temporal information perception of the video with the motion amplitude perception of moving objects to learn the spatio-temporal representation of the video. Specifically, given a video clip containing several video segments, each video segment is sampled by different sampling rates and the order of video segments is disrupted. Then, the network is used to regress the sampling rate of each video segment and classify the order of input video segments. In the pre-training stage, the network can learn rich spatio-temporal semantic information where content-related contrastive learning is introduced to make the learned video representation more discriminative. To alleviate the appearance dependency caused by contrastive learning, we design a novel and robust vector similarity measurement approach, which can take feature alignment into consideration. Moreover, a view synthesis framework is proposed to further improve the performance of contrastive learning by automatically generating reasonable transformed views. We conduct benchmark experiments with several 3D backbone networks on two datasets. The results show that our proposed method outperforms the existing state-of-the-art methods across the three backbones on two downstream tasks of human action recognition and video retrieval.

The classical person re-identification methods are mostly focused on employing discriminative features amongst which the distance is measured on Euclidean space, while the effort of re-ranking is constrained as the lack of the utilization of quality context representation in embedding set. In this paper, we incorporate graph models on feature subsets resorting to the initial ranking by adopting the integration of the attention mechanism into graph convolution network. On the one hand, the context information regarding embedding pairs is considered to compute feature group similarity through the aggregation operation by using graph convolution networks. On the other hand, we adopt a channel attention mechanism to enhance the contribution of relevant feature channels, further strengthening the ability of similarity pulling and dissimilarity pushing of the overall network. Experimental study shows that the proposed network structure is superior to the state-of-the-art deep neural networks on three very challenging datasets that are popular in examining person re-identification techniques.