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.

Learning Complexity-Aware Cascades for Deep Pedestrian Detection

Abstract: The design of complexity-aware cascaded detectors, combining features of very different complexities, is considered. A new cascade design procedure is introduced, by formulating cascade learning as the Lagrangian optimization of a risk that accounts for both accuracy and complexity. A boosting algorithm, denoted as complexity aware cascade training (CompACT), is then derived to solve this optimization. CompACT cascades are shown to seek an optimal trade-off between accuracy and complexity by pushing features of higher complexity to the later cascade stages, where only a few difficult candidate patches remain to be classified. This enables the use of features of vastly different complexities in a single detector. In result, the feature pool can be expanded to features previously impractical for cascade design, such as the responses of a deep convolutional neural network (CNN). This is demonstrated through the design of a pedestrian detector with a pool of features whose complexities span orders of magnitude. The resulting cascade generalizes the combination of a CNN with an object proposal mechanism: rather than a pre-processing stage, CompACT cascades seamlessly integrate CNNs in their stages. This enables state of the art performance on the Caltech and KITTI datasets, at fairly fast speeds.

User augmented reality for camera-enabled mobile devices

Abstract: Apparatus and methods are described for providing a user augmented reality (UAR) service for a camera-enabled mobile device, so that a user of such mobile device can use the mobile device to obtain meta data regarding one or more images/video that are captured with such device. The meta data is interactive and allows the user to obtain additional information or specific types of information, such as information that will aid the user in making a decision regarding the identified objects or selectable action options that can be used to initiate actions with respect to the identified objects.

Name disambiguation in author citations using a K-way spectral clustering method

Abstract: An author may have multiple names and multiple authors may share the same name simply due to name abbreviations, identical names, or name misspellings in publications or bibliographies (citations). This can produce name ambiguity which can affect the performance of document retrieval, web search, and database integration, and may cause improper attribution of credit. Proposed here is an unsupervised learning approach using K-way spectral clustering that disambiguates authors in citations. The approach utilizes three types of citation attributes: co-author names, paper titles, and publication venue titles. The approach is illustrated with 16 name datasets with citations collected from the DBLP database bibliography and author home pages and shows that name disambiguation can be achieved using these citation attributes

Multimedia sharing in social networks for mobile devices

Abstract: A mobile device, system, and method are directed towards sharing multimedia information on a mobile device based at least in part on vitality information and other social networking information. Multimedia information may be received and/or synchronized on the mobile device based on a relationship between vitality information of members of a social network. The relationship may comprise a common membership in a group, a common multimedia usage behavior, a geographical proximity of members of the social network, a degree of separation of members of the social network, a common search behavior, or the like. Multimedia information captured on the mobile device may be manually and/or automatically annotated and shared with members of the social network. The multimedia information may be displayed in an integrated live view in conjunction with other social networking information.

Respiratory Action of the Intercostal Muscles

Abstract: The mechanical advantages of the external and internal intercostals depend partly on the orientation of the muscle but mostly on interspace number and the position of the muscle within each interspace. Thus the external intercostals in the dorsal portion of the rostral interspaces have a large inspiratory mechanical advantage, but this advantage decreases ventrally and caudally such that in the ventral portion of the caudal interspaces, it is reversed into an expiratory mechanical advantage. The internal interosseous intercostals in the caudal interspaces also have a large expiratory mechanical advantage, but this advantage decreases cranially and, for the upper interspaces, ventrally as well. The intercartilaginous portion of the internal intercostals (the so-called parasternal intercostals), therefore, has an inspiratory mechanical advantage, whereas the triangularis sterni has a large expiratory mechanical advantage. These rostrocaudal gradients result from the nonuniform coupling between rib displacement and lung expansion, and the dorsoventral gradients result from the three-dimensional configuration of the rib cage. Such topographic differences in mechanical advantage imply that the functions of the muscles during breathing are largely determined by the topographic distributions of neural drive. The distributions of inspiratory and expiratory activity among the muscles are strikingly similar to the distributions of inspiratory and expiratory mechanical advantages, respectively. As a result, the external intercostals and the parasternal intercostals have an inspiratory function during breathing, whereas the internal interosseous intercostals and the triangularis sterni have an expiratory function.