Patent application number | Description | Published |
20100124377 | LINEAR SPATIAL PYRAMID MATCHING USING SPARSE CODING - Systems and methods are disclosed to classify an input image by determining a spatial-pyramid image representation based on sparse coding; determining a descriptor for each interest point in the input image; encoding the descriptor; and applying max pooling to form the spatial pyramid representation of images. | 05-20-2010 |
20130129199 | OBJECT-CENTRIC SPATIAL POOLING FOR IMAGE CLASSIFICATION - A method is provided for classifying an image. The method includes inferring location information of an object of interest in an input representation of the image. The method further includes determining foreground object features and background object features from the input representation of the image. The method additionally includes pooling the foreground object features separately from the background object features using the location information to form a new representation of the image. The new representation is different than the input representation of the image. The method also includes classifying the image based on the new representation of the image. | 05-23-2013 |
20130129202 | LARGE-SCALE STRONGLY SUPERVISED ENSEMBLE METRIC LEARNING - Systems and methods for metric learning include iteratively determining feature groups of images based on its derivative norm. Corresponding metrics of the feature groups are learned by gradient descent based on an expected loss. The corresponding metrics are combined to provide an intermediate metric matrix as a sparse representation of the images. A loss function of all metric parameters corresponding to features of the intermediate metric matrix are optimized, using a processor, to learn a final metric matrix. Eigenvalues of the final metric matrix are projected onto a simplex. | 05-23-2013 |
20130132402 | QUERY SPECIFIC FUSION FOR IMAGE RETRIEVAL - Systems and methods for image retrieval include constructing a plurality of graphs including a first graph for candidate images retrieved based upon holistic features of a query image and a second graph for candidate images retrieved based upon local features of the query image, wherein constructing includes weighting connected images based upon a Jaccard similarity coefficient. The plurality of graphs are fused to provide a fused graph. Candidate images of the fused graph are ranked, using a processor, to provide retrieval results of the query image. | 05-23-2013 |
20130156327 | Shape from Differential Motion with Unknown Reflectance - A computer implemented method for determining shape from differential motion with unknown reflectance includes deriving a general relation that relates spatial and temporal image derivatives to bidirectional reflectance distribution function BRDF derivatives, responsive to 3D points and relative camera poses from images and feature tracks of an object in motion under colocated and unknown directional light conditions, employing a rank deficiency in image sequences from the deriving for shape determinations, under predetermined multiple camera and lighting conditions, to eliminate BDRF terms; and recovering a surface depth for determining a shape of the object. | 06-20-2013 |
Patent application number | Description | Published |
20090141969 | Transfer Learning Methods and systems for Feed-Forward Visual Recognition Systems - A method and system for training a neural network of a visual recognition computer system, extracts at least one feature of an image or video frame with a feature extractor; approximates the at least one feature of the image or video frame with an auxiliary output provided in the neural network; and measures a feature difference between the extracted at least one feature of the image or video frame and the approximated at least one feature of the image or video frame with an auxiliary error calculator. A joint learner of the method and system adjusts at least one parameter of the neural network to minimize the measured feature difference. | 06-04-2009 |
20090299996 | RECOMMENDER SYSTEM WITH FAST MATRIX FACTORIZATION USING INFINITE DIMENSIONS - Systems and methods are disclosed for generating a recommendation by performing collaborative filtering using an infinite dimensional matrix factorization; generating one or more recommendations using the collaborative filtering; and displaying the recommendations to a user. | 12-03-2009 |
20110116708 | FAST IMAGE PARSING BY GRAPH ADAPTIVE DYNAMIC PROGRAMMING - Systems and methods are disclosed to perform image parsing on one or more images by identifying a set of similar regions from each image; assigning one or more region labels to each region and generating multiple hypotheses for region label assignment; and detecting class, location and boundary of each object in the image, wherein object classification, detection and segmentation are performed jointly during image parsing. | 05-19-2011 |
20110116711 | LOCALITY-CONSTRAINED LINEAR CODING SYSTEMS AND METHODS FOR IMAGE CLASSIFICATION - Systems and methods are disclosed for classifying an input image by detecting one or more feature points on the input image; extracting one or more descriptors from each feature point; applying a codebook to quantize each descriptor and generate code from each descriptor; applying spatial pyramid matching to generate histograms; and concatenating histograms from all sub-regions to generate a final representation of the image for classification. | 05-19-2011 |
20110182469 | 3D CONVOLUTIONAL NEURAL NETWORKS FOR AUTOMATIC HUMAN ACTION RECOGNITION - Systems and methods are disclosed to recognize human action from one or more video frames by performing | 07-28-2011 |
20110222724 | SYSTEMS AND METHODS FOR DETERMINING PERSONAL CHARACTERISTICS - Systems and methods are disclosed for determining personal characteristics from images by generating a baseline gender model and an age estimation model using one or more convolutional neural networks (CNNs); capturing correspondences of faces by face tracking, and applying incremental learning to the CNNs and enforcing correspondence constraint such that CNN outputs are consistent and stable for one person. | 09-15-2011 |
20110229045 | METHOD AND SYSTEM FOR IMAGE CLASSIFICATION - Methods and systems are disclosed for image classification coding an image by nonlinearly mapping an image descriptor to form a high-dimensional sparse vector; spatially pooling each local region to form an image-level feature vector using a probability kernel incorporating a similarity metric of local descriptors; and classifying the image. | 09-22-2011 |
20110274314 | REAL-TIME CLOTHING RECOGNITION IN SURVEILLANCE VIDEOS - Systems and methods are disclosed to recognize clothing from videos by detecting and tracking a human; performing face alignment and occlusal detection; and performing age and gender estimation, skin area extraction, and clothing segmentation to a linear support vector machine (SVM) to recognize clothing worn by the human. | 11-10-2011 |
20110299789 | SYSTEMS AND METHODS FOR DETERMINING IMAGE REPRESENTATIONS AT A PIXEL LEVEL - Systems and methods process an image having a plurality of pixels includes an image sensor to capture an image; a first-layer to encode local patches on an image region; and a second layer to jointly encode patches from the same image region. | 12-08-2011 |
20120221572 | CONTEXTUAL WEIGHTING AND EFFICIENT RE-RANKING FOR VOCABULARY TREE BASED IMAGE RETRIEVAL - Systems and methods are disclosed to search for a query image, by detecting local invariant features and local descriptors; retrieving best matching images by quantizing the local descriptors with a vocabulary tree; and reordering retrieved images with results from the vocabulary tree quantization. | 08-30-2012 |
20120243789 | FAST IMAGE CLASSIFICATION BY VOCABULARY TREE BASED IMAGE RETRIEVAL - Systems and methods are disclosed to categorize images by detecting local features for each image; applying a tree structure to index local features in the images; and extracting a rank list of candidate images with category tags based on a tree indexing structure to estimate a label of a query image. | 09-27-2012 |
20120308122 | FAST METHODS OF LEARNING DISTANCE METRIC FOR CLASSIFICATION AND RETRIEVAL - A nearest-neighbor-based distance metric learning process includes applying an exponential-based loss function to provide a smooth objective; and determining an objective and a gradient of both hinge-based and exponential-based loss function in a quadratic time of the number of instances using a computer. | 12-06-2012 |
Patent application number | Description | Published |
20120025896 | POWER SUPPLY SELECTOR AND POWER SUPPLY SELECTION METHOD - In the field of electronic technologies, a power supply selector and a power supply selection method are provided. The power supply selector includes: a first selection module, configured to select a power supply from multiple candidate power supplies; a control module, coupled to the first selection module, and configured to use the power supply selected by the first selection module as a power supply, and compare voltages of the multiple candidate power supplies to generate a control signal of each candidate power supply; and a second selection module, coupled to the control module, and configured to select a power supply for output in the multiple candidate power supplies under the control of the control signal of each candidate power supply. The technical solution is used to select a power supply from multiple candidate power supplies. | 02-02-2012 |
20120030494 | POWER SUPPLY SELECTOR AND POWER SUPPLY SELECTION METHOD - In the field of electronic technologies, a power supply selector and a power supply selection method are provided. The power supply selector includes: a first selection module, configured to select a power supply from multiple candidate power supplies; a control module, coupled to the first selection module, and configured to use the power supply selected by the first selection module as a power supply, and compare voltages of the multiple candidate power supplies to generate a control signal of each candidate power supply; and a second selection module, coupled to the control module, and configured to select a power supply for output in the multiple candidate power supplies under the control of the control signal of each candidate power supply. The technical solution is used to select a power supply from multiple candidate power supplies. | 02-02-2012 |