With the strong robusticity on illumination variations, near-infrared (NIR) can be an effective and essential complement to visible (VIS) facial expression recognition in low lighting or complete darkness conditions. However, facial expression recognition (FER) from NIR images presents more challenging problem than traditional FER due to the limitations imposed by the data scale and the difficulty of extracting discriminative features from incomplete visible lighting contents. In this paper, we give the first attempt to deep NIR facial expression recognition and proposed a novel method called near-infrared facial expression transformer (NFER-Former). Specifically, to make full use of the abundant label information in the field of VIS, we introduce a Self-Attention Orthogonal Decomposition mechanism that disentangles the expression information and spectrum information from the input image, so that the expression features can be extracted without the interference of spectrum variation. We also propose a Hypergraph-Guided Feature Embedding method that models some key facial behaviors and learns the structure of the complex correlations between them, thereby alleviating the interference of inter-class similarity. Additionally, we have constructed a large NIR-VIS Facial Expression dataset that includes 360 subjects to better validate the efficiency of NFER-Former. Extensive experiments and ablation studies show that NFER-Former significantly improves the performance of NIR FER and achieves state-of-the-art results on the only two available NIR FER datasets, Oulu-CASIA and Large-HFE.

Illumination variation has been a long-term challenge in real-world facial expression recognition(FER). Under uncontrolled or non-visible light conditions, Near-infrared (NIR) can provide a simple and alternative solution to obtain high-quality images and supplement the geometric and texture details that are missing in the visible domain. Due to the lack of existing large-scale NIR facial expression datasets, directly extending VIS FER methods to the NIR spectrum may be ineffective. Additionally, previous heterogeneous image synthesis methods are restricted by low controllability without prior task knowledge. To tackle these issues, we present the first approach, called for NIR-FER Stochastic Differential Equations (NFER-SDE), that transforms face expression appearance between heterogeneous modalities to the overfitting problem on small-scale NIR data. NFER-SDE is able to take the whole VIS source image as input and, together with domain-specific knowledge, guide the preservation of modality-invariant information in the high-frequency content of the image. Extensive experiments and ablation studies show that NFER-SDE significantly improves the performance of NIR FER and achieves state-of-the-art results on the only two available NIR FER datasets, Oulu-CASIA and Large-HFE.

Biometric systems are vulnerable to the Presentation Attacks (PA) performed using various Presentation Attack Instruments (PAIs). Even though there are numerous Presentation Attack Detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem. The common problem with existing deep learning-based PAD techniques is that they may struggle with local optima, resulting in weak generalization against different PAs. In this work, we propose to use self-supervised learning to find a reasonable initialization against local trap, so as to improve the generalization ability in detecting PAs on the biometric system.The proposed method, denoted as IF-OM, is based on a global-local view coupled with De-Folding and De-Mixing to derive the task-specific representation for PAD.During De-Folding, the proposed technique will learn region-specific features to represent samples in a local pattern by explicitly maximizing cycle consistency. While, De-Mixing drives detectors to obtain the instance-specific features with global information for more comprehensive representation by maximizing topological consistency. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both face and fingerprint PAD in more complicated and hybrid datasets, when compared with the state-of-the-art methods. Specifically, when training in CASIA-FASD and Idiap Replay-Attack, the proposed method can achieve 18.60% Equal Error Rate (EER) in OULU-NPU and MSU-MFSD, exceeding baseline performance by 9.54%. Code will be made publicly available.

In this new release of our series showcasing the plenary and keynote talks from the IEEE/RSJ IROS2020 (International Conference on Intelligent Robots and Systems) you'll meet Steve LaValle (University of Oulu) talking about the area of perception, action and control, and Sarah Bergbreiter (Carnegie Mellon University) talking about bio-inspired microrobotics. Bio: Steve LaValle is Professor of Computer Science and Engineering, in Particular Robotics and Virtual Reality, at the University of Oulu. From 2001 to 2018, he was a professor in the Department of Computer Science at the University of Illinois. He has also held positions at Stanford University and Iowa State University. His research interests include robotics, virtual and augmented reality, sensing, planning algorithms, computational geometry, and control theory.

Hospitals are likely to increasingly rely on Internet of Things systems as the coronavirus pandemic ... [ ] persists or worsens. The European Commission has launched an €8 million project that aims to use the Internet of Things (IoT) to increase and enhance the remote care provided by hospitals. At a time when the coronavirus pandemic is stretching health systems to their limits, the project is one of several actions the EC is funding with the aim of developing "Next-Generation Internet of Things" tech that could help hospitals and other organisations operate more efficiently. Dubbed IntellIoT, the project is a consortium of 13 participating companies and institutions, including Siemens, Philips, EURECOM, Aalborg University, University of Oulu, Philips, Sphynx Analytics, and the University of St. Gallen. Over the next three years, the 13 partners will trial a range of initiatives and tools intended to autonomously conduct health monitoring and interventions, while also analysing large quantities of medical data.

There is still a long way to go before we see 5G's real power. But its technological force is such that it's invoked trade wars between the US and China, both vying to be the leading edge in 5G deployment. The potential of 5G hasn't been met, but it's tipped to provide lightning-fast connectivity required for smart city infrastructure and autonomous vehicles, among a raft of next-gen use cases. But as we ponder 5G's future applications, some are choosing to look even further ahead. In Finland, the University of Oulu in announced project "6Geneis"-- the first research programs that focused on developing the future of communication.

Facial expression editing is a challenging task as it needs a high-level semantic understanding of the input face image. In conventional methods, either paired training data is required or the synthetic face’s resolution is low. Moreover,only the categories of facial expression can be changed. To address these limitations, we propose an Expression Generative Adversarial Network (ExprGAN) for photo-realistic facial expression editing with controllable expression intensity. An expression controller module is specially designed to learn an expressive and compact expression code in addition to the encoder-decoder network. This novel architecture enables the expression intensity to be continuously adjusted from low to high. We further show that our ExprGAN can be applied for other tasks, such as expression transfer, image retrieval, and data augmentation for training improved face expression recognition models. To tackle the small size of the training database, an effective incremental learning scheme is proposed. Quantitative and qualitative evaluations on the widely used Oulu-CASIA dataset demonstrate the effectiveness of ExprGAN.

Trying to handle and hide our true emotions is a challenge we all share as humans, and trying to discern what other people are hiding from us is something that fascinates us even more. Yet latest technological developments seem to signal that there is no place to hide anymore: Scientists at the University of Oulu in Finland have developed facial recognition software that can read human microexpressions at a success rate that beats humans at the same task. But what exactly are microexpressions? According to the Paul Ekman Group, founded by renowned psychologist Paul Ekman, who conducted groundbreaking research in the correlations between emotions and facial expressions – and has been dubbed "the best human lie detector in the world" in the process – microexpressions are "facial expressions that occur within 1/25th of a second and expose a person's true emotions". We make them involuntarily, even when we are trying to conceal our true emotional response.

Even though Finland-based unloaded its mobile handset business on in 2014, it remains the second-largest mobile equipment manufacturer in the world after Sweden-based . The company has about 100,000 employees after its acquisition of in 2016. Microsoft shuttered the handset business a scant two years after the company acquired it, freeing up hundreds of skilled technical resources, especially in Oulu, as I discussed in my last article. In spite of these disruptions, Nokia still employs over 2,000 people in this small city near the Arctic Circle. In fact, the company still operates a factory there, manufacturing mobile base stations for telco service providers.

The development centre of the global telecommunications operator Orange, Orange Silicon Valley (OSV), starts cooperation with Finnish artificial intelligence (AI) startup Valossa. Orange, which is one of the world's leading telecommunications operators, will be using Valossa's Val.ai platform for identifying objects and people in real-time across more than 25 simultaneous HD video streams. Val.ai platform is based on years of research at the computer vision and AI labs of the University of Oulu in Finland. The platform is capable of analysing movies and streaming videos in real-time and identifying thousands of concepts, like places, objects and unique topics, from any video stream. "We are excited to collaborate with Valossa and OSV to bring High Performance Server and Storage platforms, which normally are only available in Supercomputing Data Centers, to the Media and Entertainment industry," says Andy Lee, Echo Streams' Director of Product Marketing.