A non-transitory processor-readable medium includes code to cause a processor to receive
aerial data having a plurality of points arranged in a pattern. An indication associated with …

A face recognition neural network generates small dimensional facial feature vectors for
faces in received images. A multi-task learning classifier network receives generated vectors …

A method for fine-grained object recognition in a robotic system is disclosed that includes
obtaining an image of an object from an imaging device. Based on the image, a deep …

Some embodiments provide a method for training a machine-trained (MT) network that
processes images using multiple network parameters. The method propagates a triplet of …

Primary Examiner—Vu Le Assistant Examiner—Samah A Beg (74) Attorney, Agent, or Firm—
Schmeiser, Olsen & Watts, LLP; Dan Johnson (57) ABSTRACT A method and system for …

Detection of synthetic content in portrait videos, eg, deep fakes, is achieved. Detectors
blindly utilizing deep learning are not effective in catching fake content, as generative …

The present disclosure includes methods and systems for identifying and manipulating a
segment of a three-dimensional digital model based on soft classification of the three …

Methods and systems for embedding a network in a latent space include generating a
representation of an input network graph in the latent space using an autoencoder model …

A method includes acquiring a plurality of pictures of a single item to be classified placed on
a checkout counter, the plurality of pictures corresponding to a plurality of shooting angles …

Provided are an apparatus and a method of multi-stage image recognition. For the multi-
stage image recognition, categorized object data is received from a first deep neural …