People with social anxiety disorder avoid others, and the symptoms vary from person to person. We use unsupervised machine learning and the data collected from smartphone, called digital phenotype, to investigate the heterogeneity of social anxiety disorder. Here, we identified three subgroups of social anxiety disorder using digital phenotype. Symptom severity scores as well as app usage, call usage, phone usage, movement pattern and ambient light differed significantly across subgroups. Our findings provide insights into the behavioral traits collected through smartphone of social anxiety disorder-related subgroups.

A classic approach toward zero-shot learning (ZSL) is to map the input domain to a set of semantically meaningful attributes that could be used later on to classify unseen classes of data (e.g. visual data). In this paper, we propose to learn a visual feature dictionary that has semantically meaningful atoms. Such a dictionary is learned via joint dictionary learning for the visual domain and the attribute domain, while enforcing the same sparse coding for both dictionaries. Our novel attribute aware formulation provides an algorithmic solution to the domain shift/hubness problem in ZSL. Upon learning the joint dictionaries, images from unseen classes can be mapped into the attribute space by finding the attribute aware joint sparse representation using solely the visual data. We demonstrate that our approach provides superior or comparable performance to that of the state of the art on benchmark datasets.

We propose a general framework for unsupervised domain adaptation, which allows deep neural networks trained on a source domain to be tested on a different target domain without requiring any training annotations in the target domain. This is achieved by adding extra networks and losses that help regularize the features extracted by the backbone encoder network. To this end we propose the novel use of the recently proposed unpaired image-to-image translation framework to constrain the features extracted by the encoder network. Specifically, we require that the features extracted are able to reconstruct the images in both domains. In addition we require that the distribution of features extracted from images in the two domains are indistinguishable. Many recent works can be seen as specific cases of our general framework. We apply our method for domain adaptation between MNIST, USPS, and SVHN datasets, and Amazon, Webcam and DSLR Office datasets in classification tasks, and also between GTA5 and Cityscapes datasets for a segmentation task. We demonstrate state of the art performance on each of these datasets.

Zero-shot learning has tremendous application value in complex computer vision tasks, e.g. image classification, localization, image captioning, etc., for its capability of transferring knowledge from seen data to unseen data. Many recent proposed methods have shown that the formulation of a compatibility function and its generalization are crucial for the success of a zero-shot learning model. In this paper, we formulate a softmax-based compatibility function, and more importantly, propose a regularized empirical risk minimization objective to optimize the function parameter which leads to a better model generalization. In comparison to eight baseline models on four benchmark datasets, our model achieved the highest average ranking. Our model was effective even when the training set size was small and significantly outperforming an alternative state-of-the-art model in generalized zero-shot recognition tasks.

We address zero-shot learning using a new manifold alignment framework based on a localized multi-scale transform on graphs. Our inference approach includes a smoothness criterion for a function mapping nodes on a graph (visual representation) onto a linear space (semantic representation), which we optimize using multi-scale graph wavelets. The robustness of the ensuing scheme allows us to operate with automatically generated semantic annotations, resulting in an algorithm that is entirely free of manual supervision, and yet improves the state-of-the-art as measured on benchmark datasets.

The U.S. Defense Advanced Research Projects Agency's (DARPA) Neovision2 program aims to develop artificial vision systems based on the design principles employed by mammalian vision systems. Three such algorithms are briefly described in this paper. These neuromorphic-vision systems' performance in detecting objects in video was measured using a set of annotated clips. This paper describes the results of these evaluations including the data domains, metrics, methodologies, performance over a range of operating points and a comparison with computer vision based baseline algorithms.

The Contextual Visual Dataspace (CVD) is a real-time representation of an automotive environment that combines automated 3D modeling and semantic labeling of a scene with dynamic object detection using infrastructure cameras. Our automotive active safety concept uses CVD to detect and track dynamic objects of interest, geo-register them into the semantically labeled 3D world space, analyze the paths of vehicles and pedestrians, infer intent and therefore make more accurate predictions of potential collisions, and finally give alerts to drivers and pedestrians and provide them with real-time situational awareness. The CVD system was demonstrated in a blind curve collision warning scenario.

We present a new fast algorithm for background modeling and subtraction. Sample background values at each pixel are quantized into codebooks which represent a compressed form of background model for a long image sequence. This allows us to capture structural background variation due to periodic-like motion over a long period of time under limited memory. Our method can handle scenes containing moving backgrounds or illumination variations (shadows and highlights), and it achieves robust detection for compressed videos. We compared our method with other multimode modeling techniques.

An objective no-reference measure is presented to assess line-structure image/video quality. It was designed to measure image/video quality for video surveillance applications, especially for background modeling and foreground object detection. The proposed measure using local statistics reflects image degradation well in terms of noise and blur. The experimental results on a background subtraction algorithm validate the usefulness of the proposed measure, by showing its correlation with the algorithm's performance.