Abstract: Methods and systems for managing an image collection. Metadata associated with a captured image includes data identifying each human in the captured image. A linkage score may be generated, representing a relationship between first and second identified humans in the captured image. Records in an image collection database are updated to include the generated linkage score. The linkage information may be used to render a graphical user interface (GUI) for navigating the image collection.

Abstract: System and method for classifying data objects occurring in an unstructured dataset, comprising: extracting feature vectors from the unstructured dataset, each feature vector representing an occurrence of a data object in the unstructured dataset; classifying the feature vectors into feature vector sets that each correspond to a respective object class from a plurality of object classes; for each feature vector set: performing multiple iterations of a clustering operation, each iteration including clustering feature vectors from the feature vector set into clusters of similar feature vectors and identifying outlier feature vectors, wherein for at least one iteration after a first iteration of the clustering operation, outlier feature vectors identified in a previous iteration are excluded from the clustering operation; and outputting a key cluster for the feature vector set from a final iteration of the multiple iterations, the key cluster including a greater number of similar feature vectors than any of the

Abstract: Methods and devices for generating a slow motion video segment are described. A first set of video frames captures a video view at a first resolution and at a first frame rate. A second set of video frames captures the video view at a second lower resolution, and at a second frame rate that is greater for at least a portion of the second set. At least two high resolution frames are identified in the first set for generating the slow motion video segment. One or more low resolution frames are identified in the second set corresponding to an inter-frame time period between the identified high resolution frames. The slow motion video segment is generated by generating at least one high resolution frame corresponding to the inter-frame time period using interpolation based on the identified high resolution frames and the identified low resolution frames.

Abstract: Methods and systems for updating the weights of a set of convolution kernels of a convolutional layer of a neural network are described. A set of convolution kernels having attention-infused weights is generated by using an attention mechanism based on characteristics of the weights. For example, a set of location-based attention multipliers is applied to weights in the set of convolution kernels, a magnitude-based attention function is applied to the weights in the set of convolution kernels, or both. An output activation map is generated using the set of convolution kernels with attention-infused weights. A loss for the neural network is computed, and the gradient is back propagated to update the attention-infused weights of the convolution kernels.

Abstract: A method and system for displaying data content associated with a video, comprising: receiving video data for a video at the user equipment; playing the video in a user interface rendered on a display device of the user equipment; pausing the video at a selected frame; accessing, based on the selected frame, content data associated with the selected frame; and displaying information about the content data associated with the selected frame in the user interface.

Abstract: Methods and systems for video segmentation and scene recognition are described. A video having a plurality of frames and a subtitle file associated with the video are received. Segmentation is performed on the video to generate a first set video frames comprising one or more video frames based on a frame-by-frame comparison of features in the frames of the video. Each video frame in the first includes a frame indicator which indicates at least a first start frame of the video frame. The subtitle file associated with the video is parsed to generate one or more subtitle segments based on a start and an end time of each dialogue in the subtitle file. A second set of video frames comprising one or more second video frames are generated based on the video frames of the first set of video frames and the e or more subtitle segments.

Abstract: Methods and systems for video segmentation and scene recognition are described. A video having a plurality of frames and a subtitle file associated with the video are received. Segmentation is performed on the video to generate a first set video frames comprising one or more video frames based on a frame-by-frame comparison of features in the frames of the video. Each video frame in the first includes a frame indicator which indicates at least a first start frame of the video frame. The subtitle file associated with the video is parsed to generate one or more subtitle segments based on a start and an end time of each dialogue in the subtitle file. A second set of video frames comprising one or more second video frames are generated based on the video frames of the first set of video frames and the e or more subtitle segments.

Abstract: By adding a side network to a face recognition network, output of early convolution blocks may be used to determine relative bounding box values. The relative bounding box values may be used to refine existing boundary box value with an eye on improving the generation, by the face recognition network, of embedding vectors.

Abstract: Methods and systems for processing an image are described. A saliency map is generated from the image. The saliency map indicates one or more salient portions of the image that have saliency values satisfying a saliency criterion. A scene graph is generated for at least the one or more salient portions. The scene graph represents a plurality of objects detected in the image. The scene graph further represents one or more relationships between each respective object pairs. One or more dataset entries associated with the image are generated. Each of the one or more relationships for each of the one or more object pairs is indicated by a respective dataset entry. The one or more dataset entries are stored in a first dataset.

Abstract: An adaptive action recognizer for video that performs multiscale spatiotemporal decomposition of video to generate lower complexity video. The adaptive action recognizer has a number of processing pathways, one for each level of video complexity with each processing pathway having a different computational cost. The adaptive action recognizer applies a decision making scheme that encourages using low average computational costs while retaining high accuracy.

Abstract: By adding a side network to a face recognition network, output of early convolution blocks may be used to determine relative bounding box values. The relative bounding box values may be used to refine existing boundary box value with an eye on improving the generation, by the face recognition network, of embedding vectors.

Abstract: System and method for classifying data objects occurring in an unstructured dataset, comprising: extracting feature vectors from the unstructured dataset, each feature vector representing an occurrence of a data object in the unstructured dataset; classifying the feature vectors into feature vector sets that each correspond to a respective object class from a plurality of object classes; for each feature vector set: performing multiple iterations of a clustering operation, each iteration including clustering feature vectors from the feature vector set into clusters of similar feature vectors and identifying outlier feature vectors, wherein for at least one iteration after a first iteration of the clustering operation, outlier feature vectors identified in a previous iteration are excluded from the clustering operation; and outputting a key cluster for the feature vector set from a final iteration of the multiple iterations, the key cluster including a greater number of similar feature vectors than any of the

Abstract: A method and system for displaying data content associated with a video, comprising: receiving video data for a video at the user equipment; playing the video in a user interface rendered on a display device of the user equipment; pausing the video at a selected frame; accessing, based on the selected frame, content data associated with the selected frame; and displaying information about the content data associated with the selected frame in the user interface.

Abstract: Systems and methods for learning a high-level visual vocabulary generate inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, map the visual words to a vector space based on the inter-visual word relationships, and generate high-level visual words in the vector space.

Abstract: Systems, devices, and methods for generating an image representation obtain a set of low-level features from an image; generate a high-dimensional generative representation of the low-level features; generate a lower-dimensional representation of the low-level features based on the high-dimensional generative representation of the low-level features; generate classifier scores based on classifiers and on one or more of the high-dimensional generative representation and the lower-dimensional representation, wherein each classifier uses the one or more of the high-dimensional generative representation and the lower-dimensional representation as an input, and wherein each classifier is associated with a respective label; and generate a combined representation for the image based on the classifier scores and the lower-dimensional representation.

Abstract: Systems and methods for generating visual words define initial inter-visual word relationships between a plurality of visual words; define visual word-image relationships between the plurality of visual words and a plurality of images; define inter-image relationships between the plurality of images; generate revised inter-visual word relationships in a vector space based on the initial inter-visual word relationships, the inter-image relationships, and the visual word-image relationships; and generate higher-level visual words in the vector space based on the revised inter-visual word relationships.

Abstract: Systems, devices, and methods for generating attribute scores obtain a plurality of object images; generate a respective first attribute score of a first attribute for each object image in the plurality of object images based on the object images; calculate a respective pairwise object-similarity measure for pairs of object images in the plurality of object images; and refine the first attribute score of an object image in the plurality of object images based at least in part on the attribute scores of other object images in the plurality of object images and on the object-similarity measures of the pairs of object images in the plurality of object images.

Abstract: Systems, devices, and methods for generating an image representation obtain a set of low-level features from an image; generate a high-dimensional generative representation of the low-level features; generate a lower-dimensional representation of the low-level features based on the high-dimensional generative representation of the low-level features; generate classifier scores based on classifiers and on one or more of the high-dimensional generative representation and the lower-dimensional representation, wherein each classifier uses the one or more of the high-dimensional generative representation and the lower-dimensional representation as an input, and wherein each classifier is associated with a respective label; and generate a combined representation for the image based on the classifier scores and the lower-dimensional representation.

Abstract: Systems, devices, and methods for generating hierarchical subspace maps obtain a training set of images, wherein the images in the training set of images are each associated with at least one category in a plurality of categories; organize the images in the training set of images into a category hierarchy based on the training set of images and on the plurality of categories, wherein the category hierarchy identifies each of the categories in the plurality of categories as at least one of a parent category and child category; and generate a subspace map for each parent category based on images associated with respective child categories of the parent category, thereby generating a plurality of subspace maps.

Abstract: Systems and methods for generating a visual vocabulary build a plurality of visual words via unsupervised learning on set of features of a given type; decompose one or more visual words to a collection of lower-dimensional buckets; generate labeled image representations based on the collection of lower dimensional buckets and labeled images, wherein labels associated with an image are associated with a respective representation of the image; and iteratively select a sub-collection of buckets from the collection of lower-dimensional buckets based on the labeled image representations, wherein bucket selection during any iteration after an initial iteration is based at least in part on feedback from previously selected buckets.