No abstract

Despite recent interest and advances in facial micro-expression research, there is still plenty of room for improvement in terms of micro-expression recognition. Conventional feature extraction approaches for micro-expression video consider either the whole video sequence or a part of it, for representation. However, with the high-speed video capture of microexpressions (100-200 fps), are all frames necessary to provide a sufficiently meaningful representation? Is the luxury of data a bane to accurate recognition? A novel proposition is presented in this paper, whereby we utilize only two images per video, namely, the apex frame and the onset frame. The apex frame of a video contains the highest intensity of expression changes among all frames, while the onset is the perfect choice of a reference frame with neutral expression. A new feature extractor, Bi-Weighted Oriented Optical Flow (Bi-WOOF) is proposed to encode essential expressiveness of the apex frame. We evaluated the proposed method on five micro-expression databases-CAS(ME) 2 , CASME II, SMIC-HS, SMIC-NIR and SMIC-VIS. Our experiments lend credence to our hypothesis, with our proposed technique achieving a state-of-the-art F1-score recognition performance of 0.61 and 0.62 in the high frame rate CASME II and SMIC-HS databases respectively.

Facial micro-expression (ME) recognition has posed a huge challenge to researchers for its subtlety in motion and limited databases. Recently, handcrafted techniques have achieved superior performance in micro-expression recognition but at the cost of domain specificity and cumbersome parametric tunings. In this paper, we propose an Enriched Long-term Recurrent Convolutional Network (ELRCN) that first encodes each micro-expression frame into a feature vector through CNN module(s), then predicts the micro-expression by passing the feature vector through a Long Short-term Memory (LSTM) module. The framework contains two different network variants: (1) Channel-wise stacking of input data for spatial enrichment, (2) Feature-wise stacking of features for temporal enrichment. We demonstrate that the proposed approach is able to achieve reasonably good performance, without data augmentation. In addition, we also present ablation studies conducted on the framework and visualizations of what CNN "sees" when predicting the micro-expression classes.

No abstract

The Internet of Things (IoT) has penetrated deeply into our lives and the number of IoT devices per person is expected to increase substantially over the next few years. Due to the characteristics of IoT devices (i.e., low power and low battery), usage of these devices in critical applications requires sophisticated security measures. Researchers from academia and industry now increasingly exploit the concept of blockchains to achieve security in IoT applications. The basic idea of the blockchain is that the data generated by users or devices in the past are verified for correctness and cannot be tampered once it is updated on the blockchain. Even though the blockchain supports integrity and non-repudiation to some extent, confidentiality and privacy of the data or the devices are not preserved. The content of the data can be seen by anyone in the network for verification and mining purposes. In order to address these privacy issues, we propose a new privacy-preserving blockchain architecture for IoT applications based on attribute-based encryption (ABE) techniques. Security, privacy, and numerical analyses are presented to validate the proposed model.