Xerox Corporation

José Antonio Rodriguez Serrano

Florent C Perronnin

Adrien Gaidon

Gloria Zen

Usman Tariq

A method includes adapting the universal generative model of local descriptors to a first camera to obtain a first camera-dependent generative model. The same universal generative model is also adapted to a second camera to obtain a second camera-dependent generative model. From a first image captured by the first camera, a first image-level descriptor is extracted, using the first camera-dependent generative model. From a second image captured by the second camera, a second image-level descriptor is extracted using the second camera-dependent generative model. A similarity is computed between the first image-level descriptor and the second image-level descriptor. Information is output, based on the computed similarity. The adaptation allows differences between the image-level descriptors to be shifted towards deviations in image content, rather than the imaging conditions.

Adapted vocabularies for matching image signatures with fisher vectors

A system and method enable generating a specific object detector for a category of interest. The method includes identifying seed objects in frames of a video sequence with a pre-trained generic detector for the category. An appearance model is iteratively learned for each of the seed objects using other frames in which the seed object is identified. The appearance models are learned jointly to optimize a loss function which accounts for the loss of incorrectly labeling sub-images and a regularization term which measures a distance between the appearance models. The loss of incorrectly labeling sub-images is determined using a motion model which predicts the location of the seed object in the subsequent frames so that sub-images outside the location that the current appearance model contribute to the loss. The specific object detector is then generated by aggregating the optimized appearance models.

Self-learning object detectors for unlabeled videos using multi-task learning

A system and method are provided for segmenting an image. The method includes computing an image signature for an input image. One or more similar images are identified from a first set of images, based on the image signature of the input image and image signatures of images in the first set of images. The similar image or images are used to define a cropped region of the input image and a second image signature is computed, this time for the cropped region. One or more similar images are identified from a second set of images, based on the cropped image signature and the image signatures of images in the second set of images. The input image is segmented based on a segmentation map of at least one of the similar images identified in the second set of images.

Growing community of inventors

Grenoble, France

José Antonio Rodriguez Serrano