Qualcomm Incorporated

Qualcomm Technologies, Inc.

Other

Euvision Technologies B.v.

Cornelis Gerardus Maria Snoek

Amirhossein Habibian

Efstratios Gavves

Mihir Jain

Zhenyang Li

Arnold Wilhelmus Maria Smeulders

Tom Frederik Hugo Runia

Daniel Hendricus Franciscus Dijkman

Amir Ghodrati

Koen Erik Adriaan Van De Sande

Shuai Liao

Antonio Leonardo Rodriguez Lopez

Yue Hei Ng

Kirill Gavrilyuk

Victor Augusto Escorcia

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.

Video processing using a spectral decomposition layer

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.

Deep cross-correlation learning for object tracking

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.

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.

Decoupled motion models for object tracking

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.

Spatio-temporal action and actor localization

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.

Video action localization from proposal-attention

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.

Failure detection for a neural network object tracker

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.

Learning geometric differentials for matching 3D models to objects in a 2D image

A method of predicting action labels for a video stream includes receiving the video stream and calculating an optical flow of consecutive frames of the video stream. An attention map is generated from the current frame of the video stream and the calculated optical flow. An action label is predicted for the current frame based on the optical flow, a previous hidden state and the attention map.

Recurrent networks with motion-based attention for video understanding

A method of labeling media files includes connecting to at least one device on an ad hoc network and indexing media and corresponding labels in the ad hoc network. The method also includes comparing a computed feature representation of a seed media file with feature representations of other media files in the ad hoc network to create an ordered list. The method further includes determining whether a label corresponding to a media file on the ordered list matches the label of the seed media file and increasing a label frequency when the label corresponding to the media file on the ordered list matches the label of the seed media file.

Media label propagation in an ad hoc network

A method of processing data within a convolutional attention recurrent neural network (RNN) includes generating a current multi-dimensional attention map. The current multi-dimensional attention map indicates areas of interest in a first frame from a sequence of spatio-temporal data. The method further includes receiving a multi-dimensional feature map. The method also includes convolving the current multi-dimensional attention map and the multi-dimensional feature map to obtain a multi-dimensional hidden state and a next multi-dimensional attention map. The method identifies a class of interest in the first frame based on the multi-dimensional hidden state and training data.

Video analysis with convolutional attention recurrent neural networks

A method for automated categorization of human face images based on facial traits, said method comprising a facial trait extracting phase, comprising the steps of: providing a multitude of images comprising human faces, for each image sampling a multitude of points in said image to obtain point sample data, for each sampled point extracting visual features from said point sample data, for each image assigning said visual features to predefined codewords by applying a codebook transform, for each image extracting facial traits by applying a kernel-based learning method's prediction algorithm to said codewords to establish the probability that a facial trait from a predefined set of facial traits is present in said image, and extract said facial trait for said image if said probability is higher than a predefined threshold.

Growing community of inventors

Volendam, Netherlands

Cornelis Gerardus Maria Snoek