Naver Corporation

Xerox Corporation

Naver Labs Corporation

Conduent Business Machines Services, LLC

Jérome Revaud

Jon Almazan

Cesar De Souza

Philippe Weinzaepfel

Albert Gordo Soldevila

Diane Larlus-Larrondo

Rafael Sampaio De Rezende

Martin Humenberger

Yohann Cabon

A speed estimation system includes: a detection module configured to determine bounding boxes of an object moving on a surface in images, respectively, captured using a camera; a solver module configured to, based on the bounding boxes, determine a homography of the surface by solving an optimization problem, where the solver module is not trained; and a speed module configured to, using the homography, determine a speed that the object is moving on the surface.

Untrained systems and methods for vehicle speed estimation

A method of performing image retrieval includes: obtaining a query image; generating a global feature descriptor of the query image by inputting the query image into a convolutional neural network (CNN) and obtaining the global feature descriptor as an output of the CNN, where parameters of the CNN are learned during training of the CNN on a batch of training images using a listwise ranking loss function and optimizing a quantized mean average precision ranking evaluation metric; determining similarities between the query image and other images based on distances between the global feature descriptor of the query image and global feature descriptors of the other images, respectively; ranking the other images based on the similarities, respectively; and selecting a set of the other images based on the similarities between the query image and the other images.

Training a convolutional neural network for image retrieval with a listwise ranking loss function

A system for detecting and describing keypoints in images is described. A camera is configured to capture an image including a plurality of pixels. A fully convolutional network is configured to jointly and concurrently: generate descriptors for each of the pixels, respectively; generate reliability scores for each of the pixels, respectively; and generate repeatability scores for each of the pixels, respectively. A scoring module is configured to generate scores for the pixels, respectively, based on the reliability scores and the repeatability scores of the pixels, respectively. A keypoint list module is configured to: select X of the pixels having the X highest scores, where X is an integer greater than 1; and generate a keypoint list including: locations of the selected X pixels; and the descriptors of the selected X pixels.

Joint detection and description systems and methods

In a method for detecting an object in an input image, an input image vector representing the input image is generated by performing a regional maximum activations of convolutions (R-MAC) using a convolutional neural network (CNN) applied to the input image and using regions for the R-MAC defined by applying a region proposal network (RPN) to the output of the CNN applied to the input image. Likewise, a reference image vector representing a reference image depicting the object is generated by performing the R-MAC using the CNN applied to the reference image and using regions for the R MAC defined by applying the RPN to the output of the CNN applied to the reference image. A similarity metric between the input image vector and the reference image vector is computed, and the object is detected as present in the input image if the similarity metric satisfies a detection criterion.

Instance-level image retrieval with a region proposal network

A method, non-transitory computer readable medium and apparatus for detecting a window in a display are disclosed. For example, the method includes scanning pixels within each frame of a plurality of frames that is displayed via a sliding window, extracting one or more features from each pixel within the sliding window, applying a classification function to classify a subset of potential pixels comprising the each pixel within the sliding window as corner pixels based on the one or more features that match predefined features associated with the corner pixels and detecting the window based on the corner pixels and additional pixels within a boundary defined by the corner pixels.

Growing community of inventors

Meylan, France

Jérome Revaud