Qualcomm Incorporated

Daniel Hendricus Franciscus Dijkman

Farhad Ghazvinian Zanjani

Simone Merlin

Ilia Karmanov

Fatih Murat Porikli

Brian Michael Buesker

Bibhu P Mohanty

Harshit Joshi

Vamsi Vegunta

Ishaque Ashar Kadampot

David Jonathan Julian

Venkata Sreekanta Reddy Annapureddy

Bence Major

Joseph Binamira Soriaga

Stephen Jay Shellhammer

Jamie Menjay Lin

Max Welling

Amirhossein Habibian

Regan Blythe Towal

Cornelis Gerardus Maria Snoek

Arash Behboodi

Raamkumar Balamurthi

Koen Erik Adriaan Van De Sande

Nojun Kwak

Amir Jalalirad

Antonio Leonardo Rodriguez Lopez

Yue Hei Ng

Rui Liang

Davide Belli

Hanno Ackermann

Shubhankar Mange Borse

Aspects presented herein may enable a passive positioning system, which may be a network entity or node, to be trained to identify multiple moving objects based on using training data for a single object. In one aspect, a network entity receives first RF channel data recorded by a set of devices for a coverage area during a first time period. The network entity trains an ML model based on the set of devices and the first RF channel data. The network entity receives second RF channel data recorded by the set of devices at a second time instance that is outside of the first time period. The network entity computes a number of moving objects in the coverage area at the second time instance based on the second RF channel data using the ML model.

Zero-shot deep learning for multi-target RF positioning

Certain aspects of the present disclosure provide techniques and apparatus for biometric authentication using an anti-spoofing protection model refined using online data. The method generally includes receiving a biometric data input for a user. Features for the received biometric data input are extracted through a first machine learning model. It is determined, using the extracted features for the received biometric data input and a second machine learning model, whether the received biometric data input for the user is authentic or inauthentic. It is determined whether to add the extracted features for the received biometric data input, labeled with an indication of whether the received biometric data input is authentic or inauthentic, to a finetuning data set. The second machine learning model is adjusted based on the finetuning data set.

Adaptive personalization for anti-spoofing protection in biometric authentication systems

Systems and techniques are provided for unsupervised scene-decompositional normalizing flows. An example process can include obtaining a scene-decompositional model having a normalizing flow neural network architecture. The process can include determining, based on processing data depicting multiple targets in a scene using the scene-decompositional model, a distribution of scene data as a mixture of flows from one or more background components and one or more foreground components. The process can further include identifying, based on processing the distribution of scene data using the scene-decompositional model, a target associated with the one or more foreground components and included in the data depicting the multiple targets in the scene.

Unsupervised object-oriented decompositional normalizing flow

Aspects described herein provide a method of performing guided training of a neural network model, including: receiving supplementary domain feature data; providing the supplementary domain feature data to a fully connected layer of a neural network model; receiving from the fully connected layer supplementary domain feature scaling data; providing the supplementary domain feature scaling data to an activation function; receiving from the activation function supplementary domain feature weight data; receiving a set of feature maps from a first convolution layer of the neural network model; fusing the supplementary domain feature weight data with the set of feature maps to form fused feature maps; and providing the fused feature maps to a second convolution layer of the neural network model.

Guided training of machine learning models with convolution layer feature data fusion

Disclosed are systems, methods, and non-transitory media for performing passive radio frequency (RF) location detection operations. In some aspects, RF data, such as RF signals including channel state information (CSI), can be received from a wireless device. The RF data can be provided to a self-supervised machine-learning architecture that is configured to perform object location estimation.

Self-supervised passive positioning using wireless data

Disclosed are systems, methods, and non-transitory media for performing passive radio frequency (RF) location detection operations. In some aspects, RF data, such as RF signals including channel state information (CSI), can be received from a wireless device. The RF data can be provided to a self-supervised machine-learning architecture that is configured to perform three-dimensional (3D) object location estimation.

Disclosed are systems, methods, and non-transitory media for performing radio frequency sensing detection operations. For instance, radio frequency data can be received that is associated with at least one wireless device. The radio frequency data can be based on radio frequency signals reflected from a first object and received by the at least one wireless device. Training label data can also be obtained (e.g., from a labeling device, from the at least one wireless device, etc.). The training label data can be based at least in part on the first object and input data (e.g., received by the labeling device, the at least one wireless device, etc.). A sensing model can be generated based on the radio frequency data and the training label data.

Passive positioning with radio frequency sensing labels

Certain aspects of the present disclosure provide techniques for object positioning using mixture density networks, comprising: receiving radio frequency (RF) signal data collected in a physical space; generating a feature vector encoding the RF signal data by processing the RF signal data using a first neural network; processing the feature vector using a first mixture model to generate a first encoding tensor indicating a set of moving objects in the physical space, a first location tensor indicating a location of each of the moving objects in the physical space, and a first uncertainty tensor indicating uncertainty of the locations of each of the moving objects in the physical space; and outputting at least one location from the first location tensor.

Multi-object positioning using mixture density networks

Disclosed are systems, methods, and non-transitory media for sensing radio frequency signals. For instance, radio frequency data can be received by an apparatus and from at least one wireless device in an environment. Based on the radio frequency data received from the at least one wireless device, the apparatus can determine sensing coverage of the at least one wireless device. The apparatus can further provide the determined sensing coverage and a position of at least one device to a user device.

Passive positioning with radio frequency sensing

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

Context-based priors are utilized in machine learning networks (e.g., neural networks) for detecting objects in images. The likely locations of objects are estimated based on context labels. A machine learning network identifies a context label of an entire image. Based on the context label, the network selects a set of likely regions for detecting objects of interest in the image.

Context-based priors for object detection in images

A method of training for image classification includes labelling a crop from an image including an object of interest. The crop may be labelled with an indication of whether the object of interest is framed, partially framed or not present in the crop. The method may also include assigning a fully framed class to the labelled crop, including the object of interest, if the object of interest is framed. A labelled crop may be assigned a partially framed class if the object of interest is partially framed. A background class may be assigned to a labelled crop if the object of interest is not present in the crop.

Methods for object localization and image classification

Compressing a machine learning network, such as a neural network, includes replacing one layer in the neural network with compressed layers to produce the compressed network. The compressed network may be fine-tuned by updating weight values in the compressed layer(s).

Growing community of inventors

Haarlem, Netherlands

Daniel Hendricus Franciscus Dijkman