Abstract: The invention relates to a method for training a machine learning model to identify a subject having at least one machine readable identifier providing a subject ID, said method comprising: providing a computer vision system with an image capturing system comprising at least one image capturing device, and a reader system comprising at least one reader for reading said at least one machine readable identifier; defining said machine learning model in said computer vision system; capturing a first image using said image capturing system, said first image showing said subject; reading said subject ID using said reader system when capturing said first image, and linking said subject ID with said first image, said linking providing said first image with a linked subject ID, providing a first annotated image; capturing at least one further image showing said subject, linking said linked subject ID to said at least one further image providing at least one further annotated image, and subjecting said first annotat

Abstract: A method is presented. The method includes receiving a first sequence of frames depicting a dynamic element. The method also includes decomposing each spatial position from multiple spatial positions in the first sequence of frames to a frequency domain. The method further includes determining a distribution of spectral power density over a range of frequencies of the multiple spatial positions. The method still further includes generating a first set of feature maps based on the determined distribution of spectral power density over the range of frequencies. The method still further includes estimating a first physical property of the dynamic element.

Abstract: The invention relates to a method for training a machine learning model to identify a subject having at least one machine readable identifier providing a subject ID, said method comprising: providing a computer vision system with an image capturing system comprising at least one image capturing device, and a reader system comprising at least one reader for reading said at least one machine readable identifier; defining said machine learning model in said computer vision system; capturing a first image using said image capturing system, said first image showing said subject; reading said subject ID using said reader system when capturing said first image, and linking said subject ID with said first image, said linking providing said first image with a linked subject ID, providing a first annotated image; capturing at least one further image showing said subject, linking said linked subject ID to said at least one further image providing at least one further annotated image, and subjecting said first annotat

Abstract: Certain aspects of the present disclosure provide techniques for training a first model based on a first labeled video dataset; generating a plurality of action-words based on output generated by the first model processing motion data in videos of an unlabeled video dataset; defining labels for the videos in the unlabeled video dataset based on the generated action-words; and training a second model based on the labels for the videos in the unlabeled video dataset.

Abstract: A method is presented. The method includes receiving a first sequence of frames depicting a dynamic element. The method also includes decomposing each spatial position from multiple spatial positions in the first sequence of frames to a frequency domain. The method further includes determining a distribution of spectral power density over a range of frequencies of the multiple spatial positions. The method still further includes generating a first set of feature maps based on the determined distribution of spectral power density over the range of frequencies. The method still further includes estimating a first physical property of the dynamic element.

Abstract: The invention relates to a method for training a machine learning model to identify a subject having at least one machine readable identifier providing a subject ID, said method comprising: providing a computer vision system with an image capturing system comprising at least one image capturing device, and a reader system comprising at least one reader for reading said at least one machine readable identifier; defining said machine learning model in said computer vision system; capturing a first image using said image capturing system, said first image showing said subject; reading said subject ID using said reader system when capturing said first image, and linking said subject ID with said first image, said linking providing said first image with a linked subject ID, providing a first annotated image; capturing at least one further image showing said subject, linking said linked subject ID to said at least one further image providing at least one further annotated image, and subjecting said first annotat

Abstract: An artificial neural network for learning to track a target across a sequence of frames includes a representation network configured to extract a target region representation from a first frame and a search region representation from a subsequent frame. The artificial neural network also includes a cross-correlation layer configured to convolve the extracted target region representation with the extracted search region representation to determine a cross-correlation map. The artificial neural network further includes a loss layer configured to compare the cross-correlation map with a ground truth cross-correlation map to determine a loss value and to back propagate the loss value into the artificial neural network to update filter weights of the artificial neural network.

Abstract: A method is presented. The method includes receiving a first sequence of frames. The method also includes decomposing each spatial position from multiple spatial positions in the first sequence of frames to a frequency domain. The method further includes determining a distribution of spectral power density over a range of frequencies of the multiple spatial positions. The method still further includes generating a first set of feature maps based on the determined distribution of spectral power density over the range of frequencies.

Abstract: The invention relates to a method for training a machine learning model to identify a subject having at least one machine readable identifier providing a subject ID, said method comprising: providing a computer vision system with an image capturing system comprising at least one image capturing device, and a reader system comprising at least one reader for reading said at least one machine readable identifier; defining said machine learning model in said computer vision system; capturing a first image using said image capturing system, said first image showing said subject; reading said subject ID using said reader system when capturing said first image, and linking said subject ID with said first image, said linking providing said first image with a linked subject ID, providing a first annotated image; capturing at least one further image showing said subject, linking said linked subject ID to said at least one further image providing at least one further annotated image, and subjecting said first annotat

Abstract: A visual tracker may track an object by identifying the object in a frame, and the visual tracker by identify the object in the frame within a search region. The search region may be provided by a motion modeling system that independently models the motion of the object and models the motion of the camera. For example, an object motion model of the motion modeling system may first model the motion of the object, assuming the camera is not in motion, in order to identify the expected position of the object. A camera motion model of the motion modeling system may then update the expected position of the object, obtained from the object motion model, based on the motion of the camera.

Abstract: A method of pixel-wise localization of an actor and an action in a sequence of frames includes receiving a natural language query describing the action and the actor. The method also includes receiving the sequence of frames. The method further includes localizing the action and the actor in the sequence of frames based on the natural language query.

Abstract: A method is presented. The method includes receiving a first sequence of frames. The method also includes decomposing each spatial position from multiple spatial positions in the first sequence of frames to a frequency domain. The method further includes determining a distribution of spectral power density over a range of frequencies of the multiple spatial positions. The method still further includes generating a first set of feature maps based on the determined distribution of spectral power density over the range of frequencies.

Abstract: A method for processing a sequence of frames includes receiving a sequence of frames and multiple action proposals for the sequence of frames. The method also includes generating a representation of the sequence of frames and pooling the representation around each of the action proposals. The method further includes classifying the action proposals based on the pooled representations and controlling a device based on the classifying.

Abstract: A method of detecting failure of an object tracking network with a failure detection network includes receiving an activation from an intermediate layer of the object tracking network and classifying the activation as a failure or success. The method also includes determining whether to initiate a recovery mode of the object tracking network or to remain in a tracking mode of the object tracking network, based on the classifying.

Abstract: A method aligns, with an artificial neural network, a three-dimensional (3D) model to an object in a 2D image. The method includes detecting, with an object detector, the object from the 2D image. The method also includes estimating a geodesic distance value between the object and multiple discretized poses of the 3D model. The method further includes selecting a discretized pose of the multiple discretized poses corresponding to a smallest geodesic distance value. The method still further includes propagating pose parameters of the selected discretized pose of the 3D model to the object.

Abstract: A method for labeling a spherical target includes receiving an input including a representation of an object. The method also includes estimating unconstrained coordinates corresponding to the object. The method further includes estimating coordinates on a sphere by applying a spherical exponential activation function to the unconstrained coordinates. The method also associates the input with a set of values corresponding to a spherical target based on the estimated coordinates on the sphere.

Abstract: A visual tracker may track an object by identifying the object in a frame, and the visual tracker by identify the object in the frame within a search region. The search region may be provided by a motion modeling system that independently models the motion of the object and models the motion of the camera. For example, an object motion model of the motion modeling system may first model the motion of the object, assuming the camera is not in motion, in order to identify the expected position of the object. A camera motion model of the motion modeling system may then update the expected position of the object, obtained from the object motion model, based on the motion of the camera.

Abstract: A method of detecting failure of an object tracking network with a failure detection network includes receiving an activation from an intermediate layer of the object tracking network and classifying the activation as a failure or success. The method also includes determining whether to initiate a recovery mode of the object tracking network or to remain in a tracking mode of the object tracking network, based on the classifying.

Abstract: A method of pixel-wise localization of an actor and an action in a sequence of frames includes receiving a natural language query describing the action and the actor. The method also includes receiving the sequence of frames. The method further includes localizing the action and the actor in the sequence of frames based on the natural language query.

Abstract: A method for processing a sequence of frames includes receiving a sequence of frames and multiple action proposals for the sequence of frames. The method also includes generating a representation of the sequence of frames and pooling the representation around each of the action proposals. The method further includes classifying the action proposals based on the pooled representations and controlling a device based on the classifying.