Abstract: Improvements are provided to effectively assess a user's face and head pose such that a computer or like device can track the user's attention towards a display device(s). Then the region of the display or graphical user interface that the user is turned towards can be automatically selected without requiring the user to provide further inputs. A frontal face detector is applied to detect the user's frontal face and then key facial points such as left/right eye center, left/right mouth corner, nose tip, etc., are detected by component detectors. The system then tracks the user's head by an image tracker and determines yaw, tilt and roll angle and other pose information of the user's head through a coarse to fine process according to key facial points and/or confidence outputs by pose estimator.

Abstract: Improvements are provided to effectively assess a user's face and head pose such that a computer or like device can track the user's attention towards a display device(s). Then the region of the display or graphical user interface that the user is turned towards can be automatically selected without requiring the user to provide further inputs. A frontal face detector is applied to detect the user's frontal face and then key facial points such as left/right eye center, left/right mouth corner, nose tip, etc., are detected by component detectors. The system then tracks the user's head by an image tracker and determines yaw, tilt and roll angle and other pose information of the user's head through a coarse to fine process according to key facial points and/or confidence outputs by pose estimator.

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.

Abstract: A method and system for generating a detector to detect a dominant color of an image is provided. A dominant color system trains a detector to classify colors as being dominant colors of images. The dominant color system trains the detector using a collection of training images. To train the detector, the dominant color system first identifies candidate dominant colors of the training images. The dominant color system then extracts features of the candidate dominant colors. The dominant color system also inputs an indication of dominance of each of the candidate dominant colors. The dominant color system then trains a detector to detect the dominant color of images using the extracted features and indications of dominance of the candidate dominant colors as training data.

Abstract: Probabilistic retrospective event detection is described. In one aspect, event parameters are initialized to identify a number of events from a corpus of documents. Using a generative model, documents are determined to be associated with an event to detect representative events from the identified number of events.

Abstract: A method and system for generating clusters of images for a search result of an image query is provided. When an original image query is received, the search system identifies text associated with the original image query by submitting the original image query to a search engine. The search system identifies phrases from the text of the web page containing the search result. The search system uses each of the identified phrases as an image query and submits the image queries to an image search engine. The search system considers the image search result for each image query to represent a cluster of related images. The search system then presents the clusters of images as the images of the image search result of the original image query.

Abstract: Face detection techniques are provided that use a multiple-stage face detection algorithm. An exemplary three-stage algorithm includes a first stage that applies linear-filtering to enhance detection performance by removing many non-face-like portions within an image, a second stage that uses a boosting chain that is adopted to combine boosting classifiers within a hierarchy “chain” structure, and a third stage that performs post-filtering using image pre-processing, SVM-filtering and color-filtering to refine the final face detection prediction. In certain further implementations, the face detection techniques include a two-level hierarchy in-plane pose estimator to provide a rapid multi-view face detector that further improves the accuracy and robustness of face detection.

Abstract: A method and system for classifying an image as a photograph or a graphic based on a ranked prevalent color histogram feature or a ranked region size feature is provided. The prevalent color histogram feature contains counts of the colors that are most prevalent in the image sorted in descending order. The region size feature contains counts of the largest regions of the image sorted in descending order. The classification system then classifies the image based on the ranked prevalent color histogram feature and/or the ranked region size feature using a previously trained classifier.

Abstract: A duplicate image detection system generates an image table that maps hash codes of images to their corresponding images. The image table may group images according to their group identifiers generated from the most significant elements of the hash codes based on significance of the elements in representing an image. The image table thus segregates images by their group identifiers. To detect a duplicate image of a target image, the detection system generates a target hash code for the target image. The detection system then identifies the group of the target image based on the group identifier of the target hash code. After identifying the group identifier, the detection system searches the corresponding group table to identify hash codes that have values that are similar to the target hash code. The detection system then selects the images associated with those similar hash codes as being duplicates of the target image.

Abstract: Techniques for identifying copied images based on an original image are described. The identifying copied image is based on creating unique and identifiable features that in turn are used to generate multiple histograms. The histograms are generated by patches of the image, where the patches are created by equally dividing the image. The combined patch histograms are representative of the image.

Abstract: Statistical approaches to large-scale image annotation are described. Generally, the annotation technique includes compiling visual features and textual information from a number of images, hashing the images visual features, and clustering the images based on their hash values. An example system builds statistical language models from the clustered images and annotates the image by applying one of the statistical language models.

Abstract: Systems and methods for learning-based automatic commercial content detection are described. In one aspect, the systems and methods include a training component and an analyzing component. The training component trains a commercial content classification model using a kernel support vector machine. The analyzing component analyzes program data such as video and audio data using the commercial content classification model and one or more of single-side left neighborhood(s) and right neighborhood(s) of program data segments. Based on this analysis, each of the program data segments are classified as being commercial or non-commercial segments.

Abstract: Systems and methods for clustering Web queries are described. In one aspect, one or more of a same document and a plurality of similar documents selected by a user in response to a plurality of queries is identified. Responsive to this identification, a query cluster is generated. The cleric the query cluster indicates that the queries are similar independent of whether individual ones of the queries comprise similar composition with respect to other ones of the queries.

Abstract: Methods and apparatuses are provided for detecting blur within digital images using Cepstrum analysis blur detection techniques that are able to detect motion blur and/or out-of-focus blur.

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: 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: 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: 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: 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.

Abstract: Improvements are provided to effectively assess a user's face and head pose such that a computer or like device can track the user's attention towards a display device(s). Then the region of the display or graphical user interface that the user is turned towards can be automatically selected without requiring the user to provide further inputs. A frontal face detector is applied to detect the user's frontal face and then key facial points such as left/right eye center, left/right mouth corner, nose tip, etc., are detected by component detectors. The system then tracks the user's head by an image tracker and determines yaw, tilt and roll angle and other pose information of the user's head through a coarse to fine process according to key facial points and/or confidence outputs by pose estimator.