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.

Scalable logo recognition in real-world images

Abstract: In this paper we propose a highly effective and scalable framework for recognizing logos in images. At the core of our approach lays a method for encoding and indexing the relative spatial layout of local features detected in the logo images. Based on the analysis of the local features and the composition of basic spatial structures, such as edges and triangles, we can derive a quantized representation of the regions in the logos and minimize the false positive detections. Furthermore, we propose a cascaded index for scalable multi-class recognition of logos.For the evaluation of our system, we have constructed and released a logo recognition benchmark which consists of manually labeled logo images, complemented with non-logo images, all posted on Flickr. The dataset consists of a training, validation, and test set with 32 logo-classes. We thoroughly evaluate our system with this benchmark and show that our approach effectively recognizes different logo classes with high precision.

Visual diversification of image search results

Abstract: Due to the reliance on the textual information associated with an image, image search engines on the Web lack the discriminative power to deliver visually diverse search results. The textual descriptions are key to retrieve relevant results for a given user query, but at the same time provide little information about the rich image content.In this paper we investigate three methods for visual diversification of image search results. The methods deploy lightweight clustering techniques in combination with a dynamic weighting function of the visual features, to best capture the discriminative aspects of the resulting set of images that is retrieved. A representative image is selected from each cluster, which together form a diverse result set.Based on a performance evaluation we find that the outcome of the methods closely resembles human perception of diversity, which was established in an extensive clustering experiment carried out by human assessors.

Memristor-Based Multilayer Neural Networks With Online Gradient Descent Training

Abstract: Learning in multilayer neural networks (MNNs) relies on continuous updating of large matrices of synaptic weights by local rules. Such locality can be exploited for massive parallelism when implementing MNNs in hardware. However, these update rules require a multiply and accumulate operation for each synaptic weight, which is challenging to implement compactly using CMOS. In this paper, a method for performing these update operations simultaneously (incremental outer products) using memristor-based arrays is proposed. The method is based on the fact that, approximately, given a voltage pulse, the conductivity of a memristor will increment proportionally to the pulse duration multiplied by the pulse magnitude if the increment is sufficiently small. The proposed method uses a synaptic circuit composed of a small number of components per synapse: one memristor and two CMOS transistors. This circuit is expected to consume between 2% and 8% of the area and static power of previous CMOS-only hardware alternatives. Such a circuit can compactly implement hardware MNNs trainable by scalable algorithms based on online gradient descent (e.g., backpropagation). The utility and robustness of the proposed memristor-based circuit are demonstrated on standard supervised learning tasks.

Why We Twitter: An Analysis of a Microblogging Community

Abstract: Microblogging is a new form of communication in which users describe their current status in short posts distributed by instant messages, mobile phones, email or the Web. We present our observations of the microblogging phenomena by studying the topological and geographical properties of the social network in Twitter, one of the most popular microblogging systems. We find that people use microblogging primarily to talk about their daily activities and to seek or share information. We present a taxonomy characterizing the the underlying intentions users have in making microblogging posts. By aggregating the apparent intentions of users in implicit communities extracted from the data, we show that users with similar intentions connect with each other.

Techniques for input recogniton and completion

Abstract: Methods and apparatus are described by which one or more input words may be predicted based on partial input from a user using a predictive model that employs contextual metadata which characterizes the user in a multi-dimensional space in which the dimensions are defined by one or more of a spatial aspect, a temporal aspect, a social aspect, or a topical aspect.