Abstract: A method for face image recognition is disclosed. The method comprises generating one or more face region pairs of face images to be compared and recognized; forming a plurality of feature modes by exchanging the two face regions of each face region pair and horizontally flipping each face region of each face region pair; receiving, by one or more convolutional neural networks, the plurality of feature modes, each of which forms a plurality of input maps in the convolutional neural network; extracting, by the one or more convolutional neural networks, relational features from the input maps, which reflect identity similarities of the face images; and recognizing whether the compared face images belong to the same identity based on the extracted relational features of the face images. In addition, a system for face image recognition is also disclosed.

Abstract: A method and an apparatus for generating a facial feature verification model. The method includes acquiring N input facial images, performing feature extraction on the N input facial images, to obtain an original feature representation of each facial image, and forming a face sample library, for samples of each person with an independent identity, obtaining an intrinsic representation of each group of face samples in at least two groups of face samples, training a training sample set of the intrinsic representation, to obtain a Bayesian model of the intrinsic representation, and obtaining a facial feature verification model according to a preset model mapping relationship and the Bayesian model of the intrinsic representation. In the method and apparatus for generating a facial feature verification model in the embodiments of the present disclosure, complexity is low and a calculation amount is small.

Abstract: A video classification method and apparatus relate to the field of electronic and information technologies, so that precision of video classification can be improved. The method includes: segmenting a video in a sample video library according to a time sequence, to obtain a segmentation result, and generating a motion atom set; generating, by using the motion atom set and the segmentation result, a motion phrase set that can indicate a complex motion pattern, and generating a descriptive vector, based on the motion phrase set, of the video in the sample video library; and determining, by using the descriptive vector, a to-be-detected video whose category is the same as that of the video in the sample video library. The method is applicable to a scenario of video classification.

Abstract: The present disclosure relates to an image re-ranking method, which includes: performing image searching by using an initial keyword, obtaining, by calculation, an anchor concept set of a search result according to the search result corresponding to the initial keyword, obtaining, by calculation, a weight of a correlation between anchor concepts in the anchor concept set, and forming an anchor concept graph ACG by using the anchor concepts in the anchor concept set as vertexes and the weight of the correlation between anchor concepts as a weight of a side between the vertexes; acquiring a positive training sample by using the anchor concepts, and training a classifier by using the positive training sample; obtaining a concept projection vector by using the ACG and the classifier; calculating an ACG distance between images in the search result corresponding to the initial keyword; and ranking the images according to the ACG distance.

Abstract: Some implementations provide techniques and arrangements to address intrapersonal variations encountered during facial recognition. For example, some implementations transform at least a portion of an image from a first intrapersonal condition to a second intrapersonal condition to enable more accurate comparison with another image. Some implementations may determine a pose category of an input image and may modify at least a portion of the input image to a different pose category of another image for comparing the input image with the other image. Further, some implementations provide for compression of data representing at least a portion of the input image to decrease the dimensionality of the data.

Abstract: A method and an apparatus for generating a facial feature verification model. The method includes acquiring N input facial images, performing feature extraction on the N input facial images, to obtain an original feature representation of each facial image, and forming a face sample library, for samples of each person with an independent identity, obtaining an intrinsic representation of each group of face samples in at least two groups of face samples, training a training sample set of the intrinsic representation, to obtain a Bayesian model of the intrinsic representation, and obtaining a facial feature verification model according to a preset model mapping relationship and the Bayesian model of the intrinsic representation. In the method and apparatus for generating a facial feature verification model in the embodiments of the present disclosure, complexity is low and a calculation amount is small.

Abstract: Some implementations provide techniques and arrangements to address intrapersonal variations encountered during facial recognition. For example, some implementations employ an identity data set having a plurality of images representing different intrapersonal settings. A predictive model may associate one or more input images with one or more images in the identity data set. Some implementations may use an appearance-prediction approach to compare two images by predicting an appearance of at least one of the images under an intrapersonal setting of the other image. Further, some implementations may utilize a likelihood-prediction approach for comparing images that generates a classifier for an input image based on an association of an input image with the identity data set.

Abstract: Systems and methods of segmenting images are disclosed. The similarity of images in a set of images is compared. A group of images is selected from the set of images. The images in the group of images are selected based on compared similarities among the images. An informative image is selected from the group of images. User-defined semantic information of the informative image is received. The group of images is modeled as a graph. Each image in the group of images denotes a node in the graph. Edges of the graph denote a foreground or background relationship between images. One or more images in the group of images may be automatically segmented by propagating semantic information of the informative image to images in the group having a graph node corresponding to the informative image. Segmentation results can be refined according to user provided image semantics.

Abstract: Systems and methods are described for learning visual object cutout from a single example. In one implementation, an exemplary system determines the color context near each block in a model image to create an appearance model. The system also learns color sequences that occur across visual edges in the model image to create an edge profile model. The exemplary system then infers segmentation boundaries in unknown images based on the appearance model and edge profile model. In one implementation, the exemplary system minimizes the energy in a graph-cut model where the appearance model is used for data energy and the edge profile is used to modulate edges. The system is not limited to images with nearly identical foregrounds or backgrounds. Some variations in scale, rotation, and viewpoint are allowed.

Abstract: The present invention discloses a system and method for synthesizing a portrait sketch from a photo. The method includes: dividing the photo into a set of photo patches; determining first matching information between each of the photo patches and training photo patches pre-divided from a set of training photos; determining second matching information between each of the photo patches and training sketch patches pre-divided from a set of training sketches; determining a shape prior for the portrait sketch to be synthesized; determining a set of matched training sketch patches for each of the photo patches based on the first and the second matching information and the shape prior; and synthesizing the portrait sketch from the determined matched training sketch patches.

Abstract: Some implementations provide techniques and arrangements to address intrapersonal variations encountered during facial recognition. For example, some implementations employ an identity data set having a plurality of images representing different intrapersonal settings. A predictive model may associate one or more input images with one or more images in the identity data set. Some implementations may use an appearance-prediction approach to compare two images by predicting an appearance of at least one of the images under an intrapersonal setting of the other image. Further, some implementations may utilize a likelihood-prediction approach for comparing images that generates a classifier for an input image based on an association of an input image with the identity data set.

Abstract: Some implementations provide techniques and arrangements to address intrapersonal variations encountered during facial recognition. For example, some implementations transform at least a portion of an image from a first intrapersonal condition to a second intrapersonal condition to enable more accurate comparison with another image. Some implementations may determine a pose category of an input image and may modify at least a portion of the input image to a different pose category of another image for comparing the input image with the other image. Further, some implementations provide for compression of data representing at least a portion of the input image to decrease the dimensionality of the data.

Abstract: The handling of occlusions in stereo imaging is disclosed. In one implementation, an association between a discontinuity in one stereo image and an occlusion in a second stereo image is utilized. In such an implementation, the first and second stereo images are segmented. A mapping of a discontinuity within the second stereo image is used to form at least part of a boundary of an occlusion in the first stereo image. The mapped discontinuity is found at a boundary between two segments in the second stereo image, and once mapped, divides a segment in the first stereo image into two patches. An energy calculation is made in an iterative manner, alternating with changes to a solution with the disparities and occlusions of the patches. Upon minimization, disparities and occlusions at the patch and pixel level are available.

Abstract: Systems and methods for video completion by motion field transfer are described. In one aspect, a spatio-temporal target patch of an input video data sequence is filled in or replaced by motion field transfer from a spatio-temporal source patch of the input video data sequence. Color is propagated to corresponding portions of the spatio-temporal target patch by treating the transferred motion information as directed edges. These motion field transfer and color propagation operations result in a video completed spatio-temporal target patch. The systems and methods present the video data sequence, which now includes the video completed spatio-temporal target patch, to user for viewing.

Abstract: This disclosure describes an integrated framework for class-unsupervised object segmentation. The class-unsupervised object segmentation occurs by integrating top-down constraints and bottom-up constraints on object shapes using an algorithm in an integrated manner. The algorithm describes a relationship among object parts and superpixels. This process forms object shapes with object parts and oversegments pixel images into the superpixels, with the algorithm in conjunction with the constraints. This disclosure describes computing a mask map from a hybrid graph, segmenting the image into a foreground object and a background, and displaying the foreground object from the background.

Abstract: An exemplary method for extracting discriminant feature of samples includes providing data for samples in a multidimensional space; based on the data, computing local similarities for the samples; mapping the local similarities to weights; based on the mapping, formulating an inter-class scatter matrix and an intra-class scatter matrix; and based on the matrices, maximizing the ratio of inter-class scatter to intra-class scatter for the samples to provide discriminate features of the samples. Such a method may be used for classifying samples, recognizing patterns, or other tasks. Various other methods, devices, system, etc., are also disclosed.

Abstract: A system performs user intention modeling for interactive image retrieval. In one implementation, the system uses a three stage iterative technique to retrieve images from a database without using any image tags or text descriptors. First, the user submits a query image and the system models the user's search intention and configures a customized search to retrieve relevant images. Then, the system extends a user interface for the user to designate visual features across the retrieved images. The designated visual features refine the intention model and reconfigure the search to retrieve images that match the remodeled intention. Third, the system extends another user interface through which the user can give natural feedback about the retrieved images. The three stages can be iterated to quickly assemble a set of images that accurately fulfills the user's search intention.

Abstract: An interactive photo annotation method uses clustering based on facial similarities to improve annotation experience. The method uses a face recognition algorithm to extract facial features of a photo album and cluster the photos into multiple face groups based on facial similarity. The method annotates a face group collectively using annotations, such as name identifiers, in one operation. The method further allows merging and splitting of face groups. Special graphical user interfaces, such as displays in a group view area and a thumbnail area and drag-and-drop features, are used to further improve the annotation experience.

Abstract: Systems and methods of segmenting images are disclosed. The similarity of images in a set of images is compared. A group of images is selected from the set of images. The images in the group of images are selected based on compared similarities among the images. An informative image is selected from the group of images. User-defined semantic information of the informative image is received. The group of images is modeled as a graph. Each image in the group of images denotes a node in the graph. Edges of the graph denote a foreground or background relationship between images. One or more images in the group of images may be automatically segmented by propagating semantic information of the informative image to images in the group having a graph node corresponding to the informative image. Segmentation results can be refined according to user provided image semantics.

Abstract: Systems and methods are described for robust online face tracking. In one implementation, a system derives multiple resolutions of each video frame of a video sequence portraying movement of a visual object. The system tracks movement of the visual object in a low resolution as input for tracking the visual object in a higher resolution. The system can greatly reduce jitter while maintaining an ability to reliably track fast-moving visual objects.