In this work, we propose a novel framework leveraging the advantages of the representational ability of deep learning and domain generalization for face spoofing detection. In particular, the generalized deep feature representation is achieved by taking both spatial and temporal information into consideration, and a 3D Convolutional Neural Network (3D CNN) architecture tailored for the spatial-temporal input is proposed. The network is first initialized by training with augmented facial samples based on cross-entropy loss and further enhanced with a specifically designed generalization loss, which coherently serves as the regularization term. The training samples from different domains can seamlessly work together for learning the generalized feature representation by manipulating their feature distribution distances. We evaluate the proposed framework with different experimental setups using various databases. Experimental results indicate that our method can learn more discriminative and generalized information compared with the state-of-the-art methods.

With Generative Adversarial Networks (GAN) achieving realistic image generation, fake image detection research has become an imminent need. In this paper, a novel detection algorithm is designed to exploit the structural defect in GAN, taking advantage of the most vulnerable link in GAN generators — the Up-sampling process conducted by the Transposed Convolution operation. The Transposed Convolution in the process will cause the lack of global information in the generated images. Therefore, the Self-Attention mechanism is adopted correspondingly, equipping the algorithm with a much better comprehension of the global information than the other current work adopting pure CNN network, which is reflected in the significant increase in the detection accuracy. With the thorough comparison to the current work and corresponding careful analysis, it is verified that our proposed algorithm outperforms other current works in the field. Also, with experiments conducted on other image-generation categories and images undergone usual real-life post-processing methods, our proposed algorithm shows decent robustness for various categories of images under different reality circumstances, rather than restricted by image types and pure laboratory situation.

Skeleton-based human action recognition has been a popular research field during the past few years. With the help of cameras equipping deep sensors, such as the Kinect, a human action can be represented by a sequence of human skeleton data. Inspired by the skeleton descriptors based on Lie group, a Spatial Temporal Skeleton Transformation Descriptor (ST-STD) is proposed in this paper. The ST-STD describes the relative transformations of skeletons, including the rotation and translation during movement. It gives a comprehensive view of the skeleton in both spatial and temporal domain for each frame. To capture the temporal connections in the skeleton sequence, a Denoising Sparse Long Short Term Memory (DS-LSTM) network is proposed in this paper. The DS-LSTM is designed to deal with two problems in action recognition. Firstly, to decrease the intra-class diversity, the Spatial Temporal Auto-Encoder (STAE) is proposed in this paper to generate representations with higher abstractness. The denoising constraint and the sparsity constraint are applied on both spatial and temporal domain to enhance robustness and to reduce action misalignment. Secondly, to model the action sequence, a three-layer LSTM structure is trained with STAE representations for temporal modelling and classification. The experiments are carried out on four popular datasets. The results show that our approach performs better than several existing skeleton-based action recognition methods, which prove the effectiveness of our method.

Anomaly detection and localization in videos is still a challenging task in computer vision field. Previous methods took this task as a one-class deviation problem, which computed the deviation between test samples and normal patterns. In this paper, an Adaptive Intra-frame Classification Network (AICN) is proposed to transform this task to a multi-class classification problem. The contributions of our method are: 1) AICN is a more effective anomaly evaluation network. It evaluates abnormality based on intra-frame classification results, which reserves more connection information of sub-regions and makes the model outperform previous one-class classifiers. 2) AICN reduces the computational cost. Motion Convolutional Layers (MCLs) and Shape Convolutional Layers (SCLs) are proposed to extract feature maps, which utilize the simplicity of convolution to reduce computational cost. Adaptive Region Pooling Layer (ARPL) is also proposed to reduce the calculation cost of overlapped sub-regions. 3) AICN enhances the adaptiveness of model. Only one multi-class classifier is used rather than multiple one-class classifiers. It makes the network easier to be applied on other scenes and makes the model adaptive to samples with different resolutions. The proposed method is examined on four public datasets with different background complexities and resolutions: UCSD Ped1 dataset, UCSD Ped2 dataset, Avenue dataset and Subway dataset. The results are further compared with previous approaches to confirm the effectiveness and the advantage of our method.

The steganography research of videos leads to excellent communication methods for transmitting secret message, and high efficiency video coding(HEVC) video is one popular steganographic carrier. This paper proposes a prediction unit(PU) based wide residual-net steganography(PWRN) for HEVC videos. The visual quality distortion of modifying PUs is theoretically analyzed, which illustrates that modifying PUs only has a little negative effect on visual quality. Therefore, the data hiding method in this paper allows to modify all types of PUs except for 2N2N to each other according to the secret data. In this way, high embedding efficiency is achieved, and the PU distributions in stego-videos can be kept similar to those of cover-videos, which is essential for resisting steganalysis. Meanwhile, a super-resolution convolutional neural network(CNN) with wide residual-net filter(WRNF) is proposed to replace the in-loop filter in HEVC for reconstructing I-pictures, which results in more precisely predicted P-pictures, and it further leads to less bitrate cost and better visual quality of stego-videos. The experimental results show that the proposed PWRN successfully resists the latest PU-targeted steganalysis algorithms, and compared with the state-of-the-art work, PWRN has achieved the lowest bitrate cost and the highest visual quality under the same capacity.