Notes

Forensic genomics study upon microhaplotypes.
Theories of cognition inform our decisions when designing human-computer interfaces, and immersive systems enable us to examine these theories. This work explores the sensemaking process in an immersive environment through studying both internal and external user behaviors with a classical visualization problem a visual comparison and clustering task. We developed an immersive system to perform a user study, collecting user behavior data from different channels AR HMD for capturing external user interactions, functional near-infrared spectroscopy (fNIRS) for capturing internal neural sequences, and video for references. To examine sensemaking, we assessed how the layout of the interface (planar 2D vs. cylindrical 3D layout) and the challenge level of the task (low vs. high cognitive load) influenced the users' interactions, how these interactions changed over time, and how they influenced task performance. We also developed a visualization system to explore joint patterns among all the data channels. We found that increased interactions and cerebral hemodynamic responses were associated with more accurate performance, especially on cognitively demanding trials. The layout types did not reliably influence interactions or task performance. We discuss how these findings inform the design and evaluation of immersive systems, predict user performance and interaction, and offer theoretical insights about sensemaking from the perspective of embodied and distributed cognition.Low-cost virtual-reality (VR) head-mounted displays (HMDs) with the integration of smartphones have brought the immersive VR to the masses, and increased the ubiquity of VR. However, these systems are often limited by their poor interactivity. In this paper, we present GestOnHMD, a gesture-based interaction technique and a gesture-classification pipeline that leverages the stereo microphones in a commodity smartphone to detect the tapping and the scratching gestures on the front, the left, and the right surfaces on a mobile VR headset. Taking the Google Cardboard as our focused headset, we first conducted a gesture-elicitation study to generate 150 user-defined gestures with 50 on each surface. We then selected 15, 9, and 9 gestures for the front, the left, and the right surfaces respectively based on user preferences and signal detectability. We constructed a data set containing the acoustic signals of 18 users performing these on-surface gestures, and trained the deep-learning classification pipeline for gesture detection and recognition. Lastly, with the real-time demonstration of GestOnHMD, we conducted a series of online participatory-design sessions to collect a set of user-defined gesture-referent mappings that could potentially benefit from GestOnHMD.Hands are the most important tool to interact with virtual environments, and they should be available to perform the most critical tasks. For example, a surgeon in VR should keep his/her hands on the instruments and be able to do secondary tasks without performing a disruptive event to the operative task. In this common scenario, one can observe that hands are not available for interaction. The goal of this systematic review is to survey the literature and identify which hands-free interfaces are used, the performed interaction tasks, what metrics are used for interface evaluation, and the results of such evaluations. From 79 studies that met the eligibility criteria, the voice is the most studied interface, followed by the eye and head gaze. Some novel interfaces were brain interfaces and face expressions. System control and selection represent most of the interaction tasks studied and most studies evaluate interfaces for usability. Despite the best interface depending on the task and study, the voice was found to be versatile and showed good results amongst the studies. More research is recommended to improve the practical use of the interfaces and to evaluate the interfaces more formally.Cartoon is a common form of art in our daily life and automatic generation of cartoon images from photos is highly desirable. However, state-of-the-art single-style methods can only generate one style of cartoon images from photos and existing multi-style image style transfer methods still struggle to produce high-quality cartoon images due to their highly simplified and abstract nature. In this paper, we propose a novel multi-style generative adversarial network (GAN) architecture, called MS-CartoonGAN, which can transform photos into multiple cartoon styles. We develop a multi-domain architecture, where the generator consists of a shared encoder and multiple decoders for different cartoon styles, along with multiple discriminators for individual styles. By observing that cartoon images drawn by different artists have their unique styles while sharing some common characteristics, our shared network architecture exploits the common characteristics of cartoon styles, achieving better cartoonization and being more efficient than single-style cartoonization. We show that our multi-domain architecture can theoretically guarantee to output desired multiple cartoon styles. Through extensive experiments including a user study, we demonstrate the superiority of the proposed method, outperforming state-of-the-art single-style and multi-style image style transfer methods.The increased availability of quantitative historical datasets has provided new research opportunities for multiple disciplines in social science. In this paper, we work closely with the constructors of a new dataset, CGED-Q (China Government Employee Database-Qing), that records the career trajectories of over 340,000 government officials in the Qing bureaucracy in China from 1760 to 1912. We use these data to study career mobility from a historical perspective and understand social mobility and inequality. MAPK inhibitor However, existing statistical approaches are inadequate for analyzing career mobility in this historical dataset with its fine-grained attributes and long time span, since they are mostly hypothesis-driven and require substantial effort. We propose CareerLens, an interactive visual analytics system for assisting experts in exploring, understanding, and reasoning from historical career data. With CareerLens, experts examine mobility patterns in three levels-of-detail, namely, the macro-level providing a summary of overall mobility, the meso-level extracting latent group mobility patterns, and the micro-level revealing social relationships of individuals. We demonstrate the effectiveness and usability of CareerLens through two case studies and receive encouraging feedback from follow-up interviews with domain experts.This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images. A key challenge for this novel view synthesis arises from the reconstruction process, when the views from different input images may not be consistent due to obstruction in the light path. We overcome this by jointly modeling the epipolar property and occlusion in designing a convolutional neural network. We start by defining and computing the aperture disparity map, which approximates the parallax and measures the pixel-wise shift between two views. While this relates to free-space rendering and can fail near the object boundaries, we further develop a warping confidence map to address pixel occlusion in these challenging regions. The proposed method is evaluated on diverse real-world and synthetic light field scenes, and it shows better performance over several state-of-the-art techniques.Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salient instance segmentation (SIS) that predicts a class-agnostic mask for each detected salient instance. To better use the rich feature hierarchies in deep networks and enhance the side predictions, we propose the regularized dense connections, which attentively promote informative features and suppress non-informative ones from all feature pyramids. A novel multi-level RoIAlign based decoder is introduced to adaptively aggregate multi-level features for better mask predictions. Such strategies can be well-encapsulated into the Mask R-CNN pipeline. Extensive experiments on popular benchmarks demonstrate that our design significantly outperforms existing state-of-the-art competitors by 6.3% (58.6% vs. 52.3%) in terms of the AP metric. The code is available at https//github.com/yuhuan-wu/RDPNet.Domain Adaption tasks have recently attracted substantial attention in computer vision as they improve the transferability of deep network models from a source to a target domain with different characteristics. A large body of state-of-the-art domain-adaptation methods was developed for image classification purposes, which may be inadequate for segmentation tasks. We propose to adapt segmentation networks with a constrained formulation, which embeds domain-invariant prior knowledge about the segmentation regions. Such knowledge may take the form of anatomical information, for instance, structure size or shape, which can be known a priori or learned from the source samples via an auxiliary task. Our general formulation imposes inequality constraints on the network predictions of unlabeled or weakly labeled target samples, thereby matching implicitly the prediction statistics of the target and source domains, with permitted uncertainty of prior knowledge. Furthermore, our inequality constraints easily integrate weak annotations of the target data, such as image-level tags. We address the ensuing constrained optimization problem with differentiable penalties, fully suited for conventional stochastic gradient descent approaches. Unlike common two-step adversarial training, our formulation is based on a single segmentation network, which simplifies adaptation, while improving training quality. Comparison with state-of-the-art adaptation methods reveals considerably better performance of our model on two challenging tasks. Particularly, it consistently yields a performance gain of 1-4% Dice across architectures and datasets. Our results also show robustness to imprecision in the prior knowledge. The versatility of our novel approach can be readily used in various segmentation problems, with code available publicly.While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, a recent trend in AutoML is to focus on neural architecture search. In this paper, we introduce Auto-PyTorch, which brings the best of these two worlds together by jointly and robustly optimizing the architecture of networks and the training hyperparameters to enable fully automated deep learning (AutoDL). Auto-PyTorch achieves state-of-the-art performance on several tabular benchmarks by combining multi-fidelity optimization with portfolio construction for warmstarting and ensembling of deep neural networks (DNNs) and common baselines for tabular data. To thoroughly study our assumptions on how to design such an AutoDL system, we additionally introduce a new benchmark on learning curves for DNNs, dubbed LCBench, and run extensive ablation studies of the full Auto-PyTorch on typical AutoML benchmarks, eventually showing that Auto-PyTorch performs better than several state-of-the-art competitors on average.
Read More: https://www.selleckchem.com/products/BIX-02189.html