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.

Response prediction using collaborative filtering with hierarchies and side-information

Abstract: In online advertising, response prediction is the problem of estimating the probability that an advertisement is clicked when displayed on a content publisher's webpage In this paper, we show how response prediction can be viewed as a problem of matrix completion, and propose to solve it using matrix factorization techniques from collaborative filtering (CF) We point out the two crucial differences between standard CF problems and response prediction, namely the requirement of predicting probabilities rather than scores, and the issue of confidence in matrix entries We address these issues using a matrix factorization analogue of logistic regression, and by applying a principled confidence-weighting scheme to its objective We show how this factorization can be seamlessly combined with explicit features or side-information for pages and ads, which let us combine the benefits of both approaches Finally, we combat the extreme sparsity of response prediction data by incorporating hierarchical information about the pages and ads into our factorization model Experiments on three very large real-world datasets show that our model outperforms current state-of-the-art methods for response prediction

Nuts and Human Health Outcomes: A Systematic Review.

Abstract: There has been increasing interest in nuts and their outcome regarding human health. The consumption of nuts is frequently associated with reduction in risk factors for chronic diseases. Although nuts are high calorie foods, several studies have reported beneficial effects after nut consumption, due to fatty acid profiles, vegetable proteins, fibers, vitamins, minerals, carotenoids, and phytosterols with potential antioxidant action. However, the current findings about the benefits of nut consumption on human health have not yet been clearly discussed. This review highlights the effects of nut consumption on the context of human health.

TGIF: A New Dataset and Benchmark on Animated GIF Description

Abstract: With the recent popularity of animated GIFs on social media, there is need for ways to index them with rich meta-data. To advance research on animated GIF understanding, we collected a new dataset, Tumblr GIF (TGIF), with 100K animated GIFs from Tumblr and 120K natural language descriptions obtained via crowdsourcing. The motivation for this work is to develop a testbed for image sequence description systems, where the task is to generate natural language descriptions for animated GIFs or video clips. To ensure a high quality dataset, we developed a series of novel quality controls to validate free-form text input from crowd-workers. We show that there is unambiguous association between visual content and natural language descriptions in our dataset, making it an ideal benchmark for the visual content captioning task. We perform extensive statistical analyses to compare our dataset to existing image and video description datasets. Next, we provide baseline results on the animated GIF description task, using three representative techniques: nearest neighbor, statistical machine translation, and recurrent neural networks. Finally, we show that models fine-tuned from our animated GIF description dataset can be helpful for automatic movie description.

Link-Based Characterization and Detection of Web Spam

Abstract: We perform a statistical analysis of a large collection of Web pages, focusing on spam detection. We study several metrics such as degree correlations, number of neighbors, rank propagation through links, TrustRank and others to build several automatic web spam classiers. This paper presents a study of the performance of each of these classiers alone, as well as their combined performance. Using this approach we are able to detect 80.4% of the Web spam in our sample, with only 1.1% of false positives.

The influence of three-dimensional computed tomography images of the shoulder in preoperative planning for total shoulder arthroplasty.

Abstract: Background: Arthritic changes to glenoid morphology can be difficult to fully characterize on both plain radiographs and conventional two-dimensional computer tomography images. We tested the hypothesis that three-dimensional imaging of the shoulder would increase inter-rater agreement for assessing the extent and location of glenoid bone loss and also would improve surgical planning for total shoulder arthroplasty. Methods: Four shoulder surgeons independently and retrospectively reviewed the preoperative computed tomography scans of twenty-four arthritic shoulders. The blinded images were evaluated with conventional two-dimensional imaging software and then later with novel three-dimensional imaging software. Measurements and preoperative judgments were made for each shoulder with use of each imaging modality and then were compared. The glenoid measurements were glenoid version and bone loss. The judgments were the zone of maximum glenoid bone loss, glenoid implant fit within the glenoid vault, and how to surgically address abnormal glenoid version and bone loss. Agreement between observers was evaluated with use of intraclass correlation coefficients and the weighted kappa coefficient (κ), and we determined if surgical decisions changed with use of the three-dimensional data. Results: The average glenoid version (and standard deviation) measured −17° ± 2.2° on the two-dimensional images and −19° ± 2.4° on the three-dimensional images (p < 0.05). The average posterior glenoid bone loss measured 9 ± 2.3 mm on the two-dimensional images and 7 ± 2 mm on the three-dimensional images (p < 0.05). The average anterior bone loss measured 1 mm on both the two-dimensional and the three-dimensional images. However, the intraclass correlation coefficients for anterior bone loss increased significantly with use of the three-dimensional data (from 0.36 to 0.70; p < 0.05). Observers were more likely to locate mid-anterior glenoid bone loss on the basis of the three-dimensional data (p < 0.05). The use of three-dimensional data provided greater agreement among observers with regard to the zone of glenoid bone loss, glenoid prosthetic fit, and surgical decision-making. Also, when the judgment of implant fit changed, observers more often determined that it would violate the vault walls on the basis of the three-dimensional data (p < 0.05). Conclusions: The use of three-dimensional imaging can increase inter-rater agreement for the analysis of glenoid morphology and preoperative planning. Important considerations such as the extent and location of glenoid bone loss and the likelihood of implant fit were influenced by the three-dimensional data. Clinical Relevance: We believe that these data support the concept that three-dimensional imaging techniques applied to the shoulder provide further information that may be useful to the surgeon during the planning of total shoulder arthroplasty.