Abstract: The present invention relates to an anti-loose socket and a pull-out locking mechanism thereof, wherein inside the anti-loose socket, there are a pull-out locking mechanism composed of a bevelled sleeve (15) and two cylinders (16) arranged in a symmetrical manner at two sides within the bevelled sleeve; an inside longitudinal section of the bevelled sleeve has a cone angle in an umbrella shape, the middle portion of the bevelled sleeve allows a plug pin (61) to pass through; the cylinder is mounted on a floating block (14) movable up and down, and can move up and down along the inside conical surface of the bevelled sleeve by the floating block.

Abstract: A dual cross-media relevance model (DCMRM) is used for automatic image annotation. In contrast to the traditional relevance models which calculate the joint probability of words and images over a training image database, the DCMRM model estimates the joint probability by calculating the expectation over words in a predefined lexicon. The DCMRM model may be advantageous because a predefined lexicon potentially has better behavior than a training image database. The DCMRM model also takes advantage of content-based techniques and image search techniques to define the word-to-image and word-to-word relations involved in image annotation. Both relations can be estimated by using image search techniques on the web data as well as available training data.

Abstract: Automated rich presentation of a semantic topic is described. In one aspect, respective portions of multimodal information corresponding to a semantic topic are evaluated to locate events associated with the semantic topic. The probability that a document belongs to an event is determined based on document inclusion of one or more of persons, times, locations, and keywords, and document distribution along a timeline associated with the event. For each event, one or more documents objectively determined to be substantially representative of the event are identified. One or more other types of media (e.g., video, images, etc.) related to the event are then extracted from the multimodal information. The representative documents and the other media are for presentation to a user in a storyboard.

Abstract: Word correlations are estimated using a content-based method, which uses visual features of image representations of the words. The image representations of the subject words may be generated by retrieving images from data sources (such as the Internet) using image search with the subject words as query words. One aspect of the techniques is based on calculating the visual distance or visual similarity between the sets of retrieved images corresponding to each query word. The other is based on calculating the visual consistence among the set of the retrieved images corresponding to a conjunctive query word. The combination of the content-based method and a text-based method may produce even better result.

Abstract: Sketch and tagging based image search may include receiving a sketch query input and identifying an object in a desired image. The object or objects of the sketch query may be tagged with a text, and searching performed based on the objects. Certain implementations include indexing patches of the images, where the patches represent the objects. Relevant images can be returned based on the index of the patches.

Abstract: Described herein is a technology that facilitates efficient large-scale similarity-based retrieval. In several embodiments documents, images, and/or other multimedia files are compactly represented and efficiently indexed to enable robust search using a long-query in a large-scale corpus. As described herein, these techniques include performing decomposition of a file, e.g., a document or document-like representation. The techniques use dimension reduction to obtain three parts, topic-related words (major semantics), document specific words (minor semantics), and background words, representing the major semantics in a feature vector and the minor semantics as keywords. Using the techniques described, file vectors are matched in a topic model and the results ranked based on the keywords.

Abstract: Tools and techniques for learning to rank local interest points from images using a data-driven scale-invariant feature transform (SIFT) approach termed “Rank-SIFT” are described herein. Rank-SIFT provides a flexible framework to select stable local interest points using supervised learning. A Rank-SIFT application detects interest points, learns differential features, and implements ranking model training in the Gaussian scale space (GSS). In various implementations a stability score is calculated for ranking the local interest points by extracting features from the GSS and characterizing the local interest points based on the features being extracted from the GSS across images containing the same visual objects.

Abstract: Systems and methods for bipartite graph reinforcement modeling to annotate web images are described. In one aspect the systems and methods implement bipartite graph reinforcement modeling operations to identify a set of annotations that are relevant to a Web image. The systems and methods annotate the Web image with the identified annotations. The systems and methods then index the annotated Web image. Responsive to receiving an image search query from a user, wherein the image search query comprises information relevant to at least a subset of the identified annotations, the image search engine service presents the annotated Web image to the user.

Abstract: Tools and techniques for identifying visual contextual synonyms are described herein. The described operations use visual words having similar contextual distributions as contextual synonyms to identify and describe visual objects that share semantic meaning. The contextual distribution of a visual word is described using the statistics of co-occurrence and spatial information averaged over image patches that share the visual word. In various implementations, the techniques are employed to construct a visual contextual synonym dictionary for a large visual vocabulary. In various implementations, the visual contextual synonym dictionary narrows the semantic gap for large-scale visual search.

Abstract: Local features of retrieved images are identified and for each image, an ordered bag-of-features is created that describes the features of the image. Spatial relationships between features of an image are captured in histogram descriptors created from linear or circular projections. Using the histogram descriptors, ordered bags-of-features describing the features of the images are developed. Calibrating the ordered bags-of-features to account for spatial variance leads to spatial bags-of-features.

Abstract: A method and system for determining dominance of the media elements of display pages is provided. The dominance system provides a scoring mechanism for scoring the dominance of media elements of display pages based on features of each media element of the display page. To generate the scores for the media elements of the display page, the dominance system first identifies the media elements and then identifies the features of the media elements. The dominance system then scores the identified media elements using the provided scoring mechanism and the identified features.

Abstract: An object search system generates a hierarchical clustering of objects of a collection based on similarity of the objects. The object search system generates a separate hierarchical clustering of objects for multiple features of the objects. To identify objects similar to a target object, the object search system first generates a feature vector for the target object. For each feature of the feature vector, the object search system uses the hierarchical clustering of objects to identify the cluster of objects that is most “feature similar” to that feature of the target object. The object search system indicates the similarity of each candidate object based on the features for which the candidate object is similar.

Abstract: A method and system for generating a search request from a multimodal query that includes a query image and query text is provided. The multimodal query system identifies images of a collection that are textually related to the query image based on similarity between words associated with each image and the query text. The multimodal query system then selects those images of the identified images that are visually related to the query image. The multimodal query system may formulate a search request based on keywords of web pages that contain the selected images and submit that search request to a search engine service.

Abstract: Sketch and tagging based image search may include receiving a sketch query input and identifying an object in a desired image. The object or objects of the sketch query may be tagged with a text, and searching performed based on the objects. Certain implementations include indexing patches of the images, where the patches represent the objects. Relevant images can be returned based on the index of the patches.

Abstract: Sketch-based image search may include receiving a query curve as a sketch query input and identifying a first plurality of oriented points based on the query curve. The first plurality of oriented points may be used to locate at least one image having a curve that includes a second plurality of oriented points that match at least some of the first plurality of oriented points Implementations also include indexing a plurality of images by identifying at least one curve in each image and generating an index comprising a plurality of oriented points as index entries. The index entries are associated with the plurality of images based on corresponding oriented points in the identified curves in the images.

Abstract: Systems and methods for visual language modeling for image classification are described. In one aspect the systems and methods model training images corresponding to multiple image categories as matrices of visual words. Visual language models are generated from the matrices. In view of a given image, for example, provided by a user or from the Web, the systems and methods determine an image category corresponding to the given image. This image categorization is accomplished by maximizing the posterior probability of visual words associated with the given image over the visual language models. The image category, or a result corresponding to the image category, is presented to the user.

Abstract: A method and system for generating a search request from a multimodal query that includes a query image and query text is provided. The multimodal query system identifies images of a collection that are textually related to the query image based on similarity between words associated with each image and the query text. The multimodal query system then selects those images of the identified images that are visually related to the query image. The multimodal query system may formulate a search request based on keywords of web pages that contain the selected images and submit that search request to a search engine service.

Abstract: A method and system for determining dominance of the media elements of display pages is provided. The dominance system provides a scoring mechanism for scoring the dominance of media elements of display pages based on features of each media element of the display page. To generate the scores for the media elements of the display page, the dominance system first identifies the media elements and then identifies the features of the media elements. The dominance system then scores the identified media elements using the provided scoring mechanism and the identified features.

Abstract: A method and system for propagating the relevance of labeled documents to a query to unlabeled documents is provided. The propagation system provides training data that includes queries, documents labeled with their relevance to the queries, and unlabeled documents. The propagation system then calculates the similarity between pairs of documents in the training data. The propagation system then propagates the relevance of the labeled documents to similar, but unlabeled, documents. The propagation system may iteratively propagate labels of the documents until the labels converge on a solution. The training data with the propagated relevances can then be used to train a ranking function.

Abstract: An advertisement image classification system trains a binary classifier to classify images as advertisement images or non-advertisement images and then uses the binary classifier to classify images of web pages as advertisement images or non-advertisement images. During a training phase, the classification system generates training data of feature vectors representing the images and labels indicating whether an image is an advertisement image or a non-advertisement image. The classification system trains a binary classifier to classify images using training data. During a classification phase, the classification system inputs a web page with an image and generates a feature vector for the image. The classification system then applies the trained binary classifier to the feature vector to generate a score indicating whether the image is an advertisement image or a non-advertisement image.