Abstract

Digital watermarking has been proposed as a solution to the problem of copyright protection of multimedia documents in networked environments. There are two important issues that watermarking algorithms need to address. First, watermarking schemes are required to provide trustworthy evidence for protecting rightful ownership. Second, good watermarking schemes should satisfy the requirement of robustness and resist distortions due to common image manipulations (such as filtering, compression, etc.). In this paper, we propose a novel watermarking algorithm based on singular value decomposition (SVD). Analysis and experimental results show that the new watermarking method performs well in both security and robustness.

We propose a new method for calculating the skew angle of scanned document images. The method is designed to be insensitive to document layout, line spacing, font, graphicshmages and, most importantly, the language or script of the document. This is achieved by examining the Fourier spectra of blocks of the document image for peak pairs corresponding to the angle of skew. From a histogram compiled over all blocks in the document image the correct skew angle can be determined to within approximately 0.5 3 regardless of document script, even when the image contains considerable graphical information.

No abstract

Deep learning based methods have achieved remarkable progress in action recognition. Existing works mainly focus on designing novel deep architectures to achieve video representations learning for action recognition. Most methods treat sampled frames equally and average all the frame-level predictions at the testing stage. However, within a video, discriminative actions may occur sparsely in a few frames and most other frames are irrelevant to the ground truth and may even lead to a wrong prediction. As a result, we think that the strategy of selecting relevant frames would be a further important key to enhance the existing deep learning based action recognition. In this paper, we propose an attentionaware sampling method for action recognition, which aims to discard the irrelevant and misleading frames and preserve the most discriminative frames. We formulate the process of mining key frames from videos as a Markov decision process and train the attention agent through deep reinforcement learning without extra labels. The agent takes features and predictions from the baseline model as input and generates importance scores for all frames. Moreover, our approach is extensible, which can be applied to different existing deep learning based action recognition models. We achieve very competitive action recognition performance on two widely used action recognition datasets.