This paper focuses on predicting the category of an ongoing action with incomplete observations. We propose a novel Action Prediction Network with Auxiliary Observation Ratio regression (AORAP Net), which enhances the discriminative power of partial video features by encoding the prior knowledge of complete actions. The proposed AORAP Net consists of an encoder, an observation ratio regression module, and an action classifier. The encoder transfers global action information from full videos to construct enhanced partial video features. The observation ratio regression module is developed to achieve an auxiliary task of inferring the progress level of an ongoing action. We demonstrate that this module can guide the encoder to learn enhanced features similar to full video features and discriminative for action prediction. The classifier makes the final decision of the action category in terms of the enhanced features. Considering the fact that there is not enough discriminative information at the early stage of actions, a new classification loss is designed to adapt to the action prediction task and alleviate the over-fitting of training videos. Extensive experiments on the BIT-Interaction dataset and the UT-Interaction dataset validate the effectiveness of the proposed method.

In this paper, we propose a new artifact-free variational model for JPEG/JPEG 2000 decompression based on a cartoon-texture decomposition scheme. The new infimal convolution type regularization associated with total generalized variation (TGV) and shearlet transform can reconstruct piecewise smooth images with structured textures well, due to the property of shearlet of representing the positions and orientations of singularities, which can be interpreted as the oscillation texture parts. In order to enhance the qualities of reconstructed images, we incorporate an L2 cost functional into the model, then the discretization of such functional can be easily solved by the generic proximal Primal-Dual method. Numerical experiments show that our proposed model is competitive with the learning method-Trainable Nonlinear Reaction Diffusion (TNRD) [33, 34] in term of texture preservation, and outperforms the TV-based and TGV-based variational methods.

We propose a new type of regularization functional for images called oscillation total generalized variation (TGV) which can represent structured textures with oscillatory character in a specified direction and scale. The infimal convolution of oscillation TGV with respect to several directions and scales is then used to model images with structured oscillatory texture. Such functionals constitute a regularizer with good texture preservation properties and can flexibly be incorporated into many imaging problems. We give a detailed theoretical analysis of the infimal-convolution-type model with oscillation TGV in function spaces. Furthermore, we consider appropriate discretizations of these functionals and introduce a first-order primal-dual algorithm for solving general variational imaging problems associated with this regularizer. Finally, numerical experiments are presented which show that our proposed models can recover textures well and are competitive in comparison to existing state-of-the-art methods.