Intel Corporation

Other

Lntel Corporation

Carl S Marshall

Adam T Lake

Selvakumar Panneer

Glen J Anderson

Giuseppe Beppe Raffa

Meng Shi

Ravishankar Iyer

Prasoonkumar Surti

Jill MacDonald Boyce

Varghese George

Scott R Janus

Deepak Shashidhar Vembar

Karthik Veeramani

John W Sherry

Jeffrey R Jackson

Marc S Blackstein

Satyam Srivastava

Vallabhajosyula S Somayazulu

Hugues Labbe

Mike MacPherson

Michael D Rosenzweig

Sangita R Sharma

Srenivas Varadarajan

Nilesh K Jain

Sherine Abdelhak

Zhijun Lei

Ankur Agrawal

Zhengmin Li

Saurabh Tangri

Jason Plumb

Ilke Demir

Darrel K Palke

Mark J Harris

Oleg Pogorelik

John H Feit

Bradford H Needham

Daniel Pohl

Venkat R Gokulrangan

Michael Mesnier

Soethiha Soe

Daniel D Johnston

Zack Waters

Daniel S Lake

Jose K Sia, Jr

Oliver A Heim

Andrea E Johnson

Mrutunjayya Mrutunjayya

Daniel P Horowitz

Dawn Nafus

Heather Patterson

Steven Gans

Rajesh Poornachandran

Alex Nayshtut

Omesh Tickoo

Julio Cesar Zamora Esquivel

Rajeev K Nalawadi

Lama Nachman

David Gomez Gutierrez

Lenitra M Durham

Rameshkumar G Illikkal

Rafael De La Guardia Gonzalez

David Arditti Ilitzky

Peter Munguia

Georg Stemmer

Jose I Parra Vilchis

Leobardo E Campos Macias

Rodrigo Aldana Lopez

Christopher J Cormack

Rebecca Chierichetti

Anthony G Lamarca

Abhay A Dharmadhikari

Ram R Rao

Fan Chen

Brandon Gavino

Sejun Kim

Doye Chukwuyem Emelue

Vinay Nooji

Suresh Rangarajulu

Rosa June Thanasophon

Shi Meng

Michael S Rosenzweig

Michael S MacPherson

Honnesh Rohmetra

Alexandra Warlen

Selvakumar Paneer

Mark J Abel

An apparatus to facilitate deepfake detection models utilizing subject-specific libraries is disclosed. The apparatus includes one or more processors to store a plurality of deepfake detection models corresponding to a plurality of subjects of interest; receive a query to identify whether data pertaining to a target subject of interest is a deepfake, the target subject of interest comprised in the plurality of subjects of interest and associated with a subject identifier (ID); identify a deepfake detection model corresponding to the subject ID; extract features for deepfake detection from the data; input the extracted features to the identified deepfake detection model corresponding to the subject ID; and responsive to an output of the deepfake detection model exceeding a determined deepfake threshold, generate a notification, in response to the query, indicating a possible deepfake attack corresponding to the target subject of interest.

Deepfake detection models utilizing subject-specific libraries

An apparatus to facilitate an authenticator-integrated generative adversarial network (GAN) for secure deepfake generation is disclosed. The apparatus includes one or more processors to: generate, by a generative neural network, samples based on feedback received from a discriminator neural network and from an authenticator neural network, the generative neural network aiming to trick the discriminator neural network to identify the generated samples as real content samples; digest, by the authenticator neural network, the real content samples, the generated samples from the generative neural network, and an authentication code; embed, by the authenticator neural network, the authentication code into the generated samples from the generative neural network by contributing to a generator loss provided to the generative neural network; generate, by the generative neural network, content comprising the embedded authentication code; and verify, by the authenticator neural network, the content based on the embedded authentication code.

Authenticator-integrated generative adversarial network (GAN) for secure deepfake generation

An apparatus to facilitate inferred object shading is disclosed. The apparatus comprises one or more processors to receive rasterized pixel data and hierarchical data associated with one or more objects and perform an inferred shading operation on the rasterized pixel data, including using one or more trained neural networks to perform texture and lighting on the rasterized pixel data to generate a pixel output, wherein the one or more trained neural networks uses the hierarchical data to learn a three-dimensional (3D) geometry, latent space and representation of the one or more objects.

Inferred shading mechanism

An apparatus to facilitate video motion smoothing is disclosed. The apparatus comprises one or more processors including a graphics processor, the one or more processors including circuitry configured to receive a video stream, decode the video stream to generate a motion vector map and a plurality of video image frames, analyze the motion vector map to detect a plurality of candidate frames, wherein the plurality of candidate frames comprise a period of discontinuous motion in the plurality of video image frames and the plurality of candidate frames are determined based on a classification generated via a convolutional neural network (CNN), generate, via a generative adversarial network (GAN), one or more synthetic frames based on the plurality of candidate frames, insert the one or more synthetic frames between the plurality of candidate frames to generate up-sampled video frames and transmit the up-sampled video frames for display.

Video smoothing mechanism

One embodiment provides a graphics processor comprising a block of execution resources, a cache memory, a cache memory prefetcher, and circuitry including a programmable neural network unit, the programmable neural network unit comprising a network hardware block including circuitry to perform neural network operations and activation operations for a layer of a neural network, the programmable neural network unit addressable by cores within the block of graphics cores and the neural network hardware block configured to perform operations associated with a neural network configured to determine a prefetch pattern for the cache memory prefetcher.

Graphics architecture including a neural network pipeline

One embodiment provides a method comprising, at a runtime library executed by a processor of a data processing system, receiving an input frame having objects to be stylized via a style transfer network associated with the runtime library, wherein the style transfer network is a neural network model trained to apply one or more visual styles to an input frame, performing instance segmentation on the input frame to generate one or more instance masks to identify one or more objects to be stylized, generating one or more stylized frames for each style to transfer to the input frame, and merging, via the one or more instance masks, stylized objects from one or more stylized frames with un-stylized content from the input frame to generate an output frame with per-instance stylization.

Real-time temporally consistent object segmented style transfer in media and gaming

An apparatus to facilitate generator exploitation for deepfake detection is disclosed. The apparatus includes one or more processors to: alter a generative neural network of a deepfake generator with one or more modifications for deepfake detection; train the generative neural network having the one or more modifications and a discriminative neural network of the deepfake generator, wherein training the generative neural network and the discriminative neural network to facilitate the generative neural network to generate deepfake content comprising the one or more modifications; and communicate identification of the one or more modifications to a deepfake detector to cause the deepfake detector to identify deepfake content generated by the deepfake generator that comprises at least one of the one or more modifications.

Generator exploitation for deepfake detection

Technologies for computing context replay include a computing device having a persistent memory and a volatile memory. The computing device creates multiple snapshots that are each indicative of a user's computing context at a corresponding sync point. The snapshots may include metadata created in response to system events, memory snapshots stored in a virtual machine, and/or video data corresponding to the computing context. At least a part of the snapshots are stored in the persistent memory. The computing device presents a timeline user interface based on the snapshots. The timeline includes multiple elements that are associated with corresponding sync points. The timeline elements may visually indicate a salience value that has been determined for each corresponding sync point. In response to a user selection of a sync point, the computing device activates a computing context corresponding to the snapshot for the selected sync point. Other embodiments are described and claimed.

Technologies for computing context replay with visual searching

Various embodiments for dynamically generating an advertisement in a video stream are disclosed. In one embodiment, video stream content associated with a video stream for a user device is received. Video analytics data is obtained for the video stream content, which indicates a scene recognized in the video stream content. An advertisement to be generated and inserted into the video stream content is then selected based on the scene recognized in the video stream content, and an advertisement template for generating the selected advertisement is obtained. Video advertisement content corresponding to the advertisement is then generated based on the advertisement template and the video analytics data. The video advertisement content is then inserted into the video stream content, and the modified video stream content is transmitted to the user device.

On-demand generation and personalization of video content

Apparatuses, methods, and storage medium associated with a browser for prioritized display of videos and/or photographs are disclosed herein. In embodiments, an apparatus may include one or more processors, devices, and/or circuitry to operate a browser to present a plurality of photos and/or videos for viewing. A subset of the plurality of the photos and/or videos may be selected based on the results of an analysis of sensor data collected by a plurality of wearable sensors. The subset of the plurality of the photos and/or videos may be prioritized over other photos and/or videos from the plurality of the photos and/or videos in terms of presentation space allocated for presentation.

Prioritization for presentation of media based on sensor data collected by wearable sensor devices

One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.

The systems and methods disclosed herein provide determination of an orientation of a feature towards a reference target. As a non-limiting example, a system consistent with the present disclosure may include a processor, a memory, and a single camera affixed to the ceiling of a room occupied by a person. The system may analyze images from the camera to identify any objects in the room and their locations. Once the system has identified an object and its location, the system may prompt the person to look directly at the object. The camera may then record an image of the user looking at the object. The processor may analyze the image to determine the location of the user's head and, combined with the known location of the object and the known location of the camera, determine the direction that the user is facing. This direction may be treated as a reference value, or 'ground truth.' The captured image may be associated with the direction, and the combination may be used as training input into an application.

System for determining anatomical feature orientation

An apparatus and method for scheduling threads on local and remote processing resources. For example, one embodiment of an apparatus comprises: a local graphics processor to execute threads of an application; graphics processor virtualization circuitry and/or logic to generate a virtualized representation of a local processor; a scheduler to identify a first subset of the threads for execution on a local graphics processor and a second subset of the threads for execution on a virtualized representation of a local processor; the scheduler to schedule the first subset of threads on the local graphics processor and the second subset of the threads by transmitting the threads or a representation thereof to Cloud-based processing resources associated with the virtualized representation of the local processor; and the local graphics processor to combine first results of executing the first subset of threads on the local graphics processor with second results of executing the second subset of threads on the Cloud-based processing resources to render an image frame.

Apparatus and method for real time graphics processing using local and cloud-based graphics processing resources

Embodiments are directed to neural network processing for multi-object three-dimensional (3D) modeling. An embodiment of a computer-readable storage medium includes executable computer program instructions for obtaining data from multiple cameras, the data including multiple images, and generating a 3D model for 3D imaging based at least in part on the data from the cameras, wherein generating the 3D model includes one or more of performing processing with a first neural network to determine temporal direction based at least in part on motion of one or more objects identified in an image of the multiple images or performing processing with a second neural network to determine semantic content information for an image of the multiple images.

Neural network processing for multi-object 3D modeling

Growing community of inventors

Portland, OR, United States of America

Carl S Marshall