Yahoo!

About: Yahoo! is a company organization based out in London, United Kingdom. It is known for research contribution in the topics: Population & Web search query. The organization has 26749 authors who have published 29915 publications receiving 732583 citations. The organization is also known as: Yahoo! Inc. & Maudwen-Yahoo! Inc.

Multi-view Face Detection Using Deep Convolutional Neural Networks

Abstract: In this paper we consider the problem of multi-view face detection. While there has been significant research on this problem, current state-of-the-art approaches for this task require annotation of facial landmarks, e.g. TSM [25], or annotation of face poses [28, 22]. They also require training dozens of models to fully capture faces in all orientations, e.g. 22 models in HeadHunter method [22]. In this paper we propose Deep Dense Face Detector (DDFD), a method that does not require pose/landmark annotation and is able to detect faces in a wide range of orientations using a single model based on deep convolutional neural networks. The proposed method has minimal complexity; unlike other recent deep learning object detection methods [9], it does not require additional components such as segmentation, bounding-box regression, or SVM classifiers. Furthermore, we analyzed scores of the proposed face detector for faces in different orientations and found that 1) the proposed method is able to detect faces from different angles and can handle occlusion to some extent, 2) there seems to be a correlation between distribution of positive examples in the training set and scores of the proposed face detector. The latter suggests that the proposed method's performance can be further improved by using better sampling strategies and more sophisticated data augmentation techniques. Evaluations on popular face detection benchmark datasets show that our single-model face detector algorithm has similar or better performance compared to the previous methods, which are more complex and require annotations of either different poses or facial landmarks.

Link prediction and path analysis using Markov chains

Abstract: The enormous growth in the number of documents in the World Wide Web increases the need for improved link navigation and path analysis models. Link prediction and path analysis are important problems with a wide range of applications ranging from personalization to Web server request prediction. The sheer size of the World Wide Web coupled with the variation in users' navigation patterns makes this a very difficult sequence modelling problem. In this paper, the notion of probabilistic link prediction and path analysis using Markov chains is proposed and evaluated. Markov chains allow the system to dynamically model the URL access patterns that are observed in navigation logs based on the previous state. Furthermore, the Markov chain model can also be used in a generative mode to automatically obtain tours. The Markov transition matrix can be analysed further using eigenvector decomposition to obtain `personalized hubs/authorities'. The utility of the Markov chain approach is demonstrated in many domains: HTTP request prediction, system-driven adaptive Web navigation, tour generation, and detection of `personalized hubs/authorities' from user navigation profiles. The generality and power of Markov chains is a first step towards the application of powerful probabilistic models to Web path analysis and link prediction.

SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations between Pairs of Nominals

Abstract: SemEval-2 Task 8 focuses on Multi-way classification of semantic relations between pairs of nominals. The task was designed to compare different approaches to semantic relation classification and to provide a standard testbed for future research. This paper defines the task, describes the training and test data and the process of their creation, lists the participating systems (10 teams, 28 runs), and discusses their results.

Prospectively Gated Transverse Coronary CT Angiography versus Retrospectively Gated Helical Technique : Improved Image Quality and Reduced Radiation Dose

Abstract: Purpose: To retrospectively compare image quality, radiation dose, and blood vessel assessability for coronary artery computed tomographic (CT) angiograms obtained with a prospectively gated transverse (PGT) CT technique and a retrospectively gated helical (RGH) CT technique. Materials and Methods: This HIPAA-compliant study received a waiver for approval from the institutional review board, including one for informed consent. Coronary CT angiograms obtained with 64–detector row CT were retrospectively evaluated in 203 clinical patients. A routine RGH technique was evaluated in 82 consecutive patients (44 males, 38 females; mean age, 55.6 years). The PGT technique was then evaluated in 121 additional patients (71 males, 50 females; mean age, 56.7 years). All images were evaluated for image quality, estimated radiation dose, and coronary artery segment assessability. Differences in image quality score were evaluated by using a proportional odds logistic regression model, with main effects for three readers...

Scalable k-means++

Abstract: Over half a century old and showing no signs of aging, k-means remains one of the most popular data processing algorithms. As is well-known, a proper initialization of k-means is crucial for obtaining a good final solution. The recently proposed k-means++ initialization algorithm achieves this, obtaining an initial set of centers that is provably close to the optimum solution. A major downside of the k-means++ is its inherent sequential nature, which limits its applicability to massive data: one must make k passes over the data to find a good initial set of centers. In this work we show how to drastically reduce the number of passes needed to obtain, in parallel, a good initialization. This is unlike prevailing efforts on parallelizing k-means that have mostly focused on the post-initialization phases of k-means. We prove that our proposed initialization algorithm k-means|| obtains a nearly optimal solution after a logarithmic number of passes, and then show that in practice a constant number of passes suffices. Experimental evaluation on real-world large-scale data demonstrates that k-means|| outperforms k-means++ in both sequential and parallel settings.