Intel Corporation

Technology, Patents and Licensing, Inc.

Fuji Xerox Co., Ltd.

Rpx Corporation

Rainer Wolfgang Lienhart

Charles Anthony Eldering

Igor V Kozintsev

Richard König

Christine Lienhart

Minerva M Yeung

Dmitry N Budnikov

Igor V Chikalov

Vikas C Raykar

Axel Wernicke

Sergey A Egorychev

Jochen Maydt

Lynn D Wilcox

Yen-Kuang Chen

Boon-Lock Yeo

Lyndon Kennedy

Matthew J Holliman

Matthew L Lee

Luhong Liang

Moritz Werner Amadeus Einfalt

Alexander J Hartmann

Alexander Kuranov

A computer-implemented method of assessing whether a patent has a condition is provided, including generating a facial landmark on a received input video to define points associated with a region of interest on a face of the patient, defining a period of talking based respective positions of the defined points, during the period of talking, measuring pause frequency, repetitive pattern, and vocabulary variety, without determining or applying semantic information associated with the talking, to generate an aggregate score, and based on the aggregate score, generating a prediction of the patient having the condition associated with the aggregate score.

System and method for detection of cognitive and speech impairment based on temporal visual facial feature

A method and system for detection of video segments in compressed digital video streams is presented. The compressed digital video stream is examine to determine synchronization points, and the compressed video signal is analyzed following detection of the synchronization points to create video fingerprints that are subsequently compared against a library of stored fingerprints.

Advertisement detection

Video entity recognition in compressed digital video streams

A method and system for detecting automatic ad detection is presented in which video streams are modified such that features cannot be automatically recognized or statistical parameters and fingerprints derived from the video stream cannot be matched against fingerprints of known video segments in a database.

Video stream modification to defeat detection

A television signal substitution system that replaces known video segments such as advertisements with selected replacement advertisements. Fingerprint data of known advertisements can be stored in a fingerprint database. When new fingerprint data is available, the fingerprint data can be automatically or manually transmitted to subscribers. Various techniques can be used to identify advertisements based on the fingerprint data.

Video detection and insertion

In general, in one aspect, the disclosure describes a method for detecting a known video entity within a video stream. The method includes receiving a video stream and continually creating statistical parameterized representations for windows of the video stream. The statistical parameterized representation windows are continually compared to windows of a plurality of fingerprints. Each of the plurality of fingerprints includes associated statistical parameterized representations of a known video entity. A known video entity in the video stream is detected when a particular fingerprint of the plurality of fingerprints has at least a threshold level of similarity with the video stream.

Detecting known video entities utilizing fingerprints

According to one embodiment of the present invention, a novel apparatus is disclosed. The apparatus includes an analog to digital converter to receive a predefined synchronization signal and a receiver clock; and an interpolation module coupled to the analog to digital converter to receive an output of the analog to digital converter and to continuously estimate and adapt current delay and skew estimates to synchronize a signal.

Universal adaptive synchronization scheme for distributed audio-video capture on heterogeneous computing platforms

According to one embodiment of the present invention, a novel method and system are disclosed. In one embodiment, a first node records a first node local time of receiving a wirelessly transmitted packet, the first node local time recorded with a monotonically increasing clock of the first node. The first node wirelessly transmits the recorded local time to at least a second node. The second node records a second node local time of receiving the wirelessly transmitted packet and records the first node local time of receiving the wirelessly transmitted packet. The second node updates a second node timing model to synchronize with the first node, the updating based on the second node local time of receiving the wirelessly transmitted packet and the first node local time of receiving the wirelessly transmitted packet. In one embodiment, the method and system further include synchronizing sample numbers of a multimedia stream on the second node with the timing model of the second node, the timing model of the second node having been synchronized with the first node.

Method and system for synchronizing platform clocks in a distributed wireless platform

A system and method for adaptation of time synchronization of a plurality of multimedia streams is presented. In one embodiment, multimedia data is captured, via a plurality of multimedia platforms. A first synchronization signal is received by each of the plurality of multimedia platforms. The first synchronization signal is used to generate a first common clock reference among the plurality of multimedia platforms. Captured multimedia data is synchronized according to the first common clock reference. A second synchronization signal is received by each of the plurality of multimedia platforms. The second synchronization signal is used generate a transitional common clock reference among the plurality of multimedia platforms. The second synchronization signal is also used to generate a second common clock reference among the plurality of multimedia platforms.

Apparatus and method for adaptation of time synchronization of a plurality of multimedia streams

A tree classifier may include a number of stages. Some stages may include monolithic classifiers, and other stages may be split into two or more classifiers.

Detector tree of boosted classifiers for real-time object detection and tracking

Growing community of inventors

Santa Clara, CA, United States of America

Rainer Wolfgang Lienhart