Microsoft Technology Licensing, LLC

Intel Corporation

Marvell International Limited

Marvell D.s.p.c. Ltd.

Eyal Krupka

Kfir Karmon

Igor Kviatkovsky

Igor Abramovski

Adi Diamant

Xiong Xiao

Shixiong Zhang

Ido Leichter

Yoni Smolin

Aviv Hurvitz

Daniel Freedman

Karen Master Ben-Dor

Moshe David

Aharon Bar-Hillel

Ilya Gurvich

Xuedong D Huang

Nir Nice

Wei Xiong

Amit Kumar Agarwal

Lijuan Qin

Raz Halaly

Lingfeng Wu

Yuval Tzairi

Yagil Engel

Alon Vinnikov

Yevgeny Shapiro

Jinyu Li

Jason Matthew Cahill

Cha Zhang

Tommer Leyvand

Rotem Avivi

Ron Jack Karidi

Mirko Schmidt

Timothy R O'Connor

Tim Keosababian

Aharon Bar Hillel

Qingfen Lin

Ofer Dekel

Arash Ghanaie-sichanie

Noam Bloom

Uri Levanon

Shelly Horowitz

In a system including a processor and memory, the memory includes instructions that, when executed by the processor, cause the processor to control the system to perform receiving a video stream capturing objects; identifying, based on the received video stream, object areas corresponding to the objects, respectively; tracking the object areas in the received video stream; generating, based on the tracking of the object areas, visual data sets at a plurality of times, wherein each visual data set is generated at a different time and includes visual data representing each object area; determining a priority of each visual data in each visual data set; selecting, based on the determined priority of each visual data, a group of the visual data to be transmitted to a remote system; and transmitting, to the remote system, the selected group of the visual data.

Object data generation for remote image processing

A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.

Computerized intelligent assistant for conferences

Computer implemented method for detecting a hand gesture of a user, comprising:

Detection of hand gestures using gesture language discrete values

A user's collection of images may be analyzed to identify people's faces within the images, then create clusters of similar faces, where each of the clusters may represent a person. The clusters may be ranked in order of size to determine a relative importance of the associated person to the user. The ranking may be used in many social networking applications to filter and present content that may be of interest to the user. In one use scenario, the clusters may be used to identify images from a second user's image collection, where the identified images may be pertinent or interesting to the first user. The ranking may also be a function of user interactions with the images, as well as other input not related to the images. The ranking may be incrementally updated when new images are added to the user's collection.

Ranking clusters based on facial image analysis

Examples are disclosed that relate to voice identification enrollment. One example provides a method of voice identification enrollment comprising, during a meeting in which two or more human speakers speak at different times, determining whether one or more conditions of a protocol for sampling meeting audio used to establish human speaker voiceprints are satisfied, and in response to determining that the one or more conditions are satisfied, selecting a sample of meeting audio according to the protocol, the sample representing an utterance made by one of the human speakers. The method further comprises establishing, based at least on the sample, a voiceprint of the human speaker.

Voice identification enrollment

Multi-modal speech localization is achieved using image data captured by one or more cameras, and audio data captured by a microphone array. Audio data captured by each microphone of the array is transformed to obtain a frequency domain representation that is discretized in a plurality of frequency intervals. Image data captured by each camera is used to determine a positioning of each human face. Input data is provided to a previously-trained, audio source localization classifier, including: the frequency domain representation of the audio data captured by each microphone, and the positioning of each human face captured by each camera in which the positioning of each human face represents a candidate audio source. An identified audio source is indicated by the classifier based on the input data that is estimated to be the human face from which the audio data originated.

Multi-modal speech localization

A speaker recognition system includes a previously-trained joint neural network. An enrollment machine of the speaker recognition system is configured to operate the previously-trained joint neural network to enroll a new speaker based on audiovisual data featuring the newly enrolled speaker. A recognition machine of the speaker recognition system is configured to operate the previously-trained joint neural network to recognize a previously-enrolled speaker based on audiovisual data featuring the previously-enrolled speaker.

Joint neural network for speaker recognition

A gesture recognition method comprises receiving at a processor from a sensor a sequence of captured signal frames for extracting hand pose information for a hand and using at least one trained predictor executed on the processor to extract hand pose information from the received signal frames. For at least one defined gesture, defined as a time sequence comprising hand poses, with each of the hand poses defined as a conjunction or disjunction of qualitative propositions relating to interest points on the hand, truth values are computed for the qualitative propositions using the hand pose information extracted from the received signal frames, and execution of the gesture is tracked, by using the truth values to determine which of the hand poses in the time sequence have already been executed and which of the hand poses in the time sequence is expected next.

Gesture recognition

A computer implemented method of training an image classifier, comprising: receiving training images data labeled according to image classes; selecting reference points of the images; and constructing a set of voting convolutional tables and binary features on a patch surrounding each reference point by performing, for each calculation stage: creating a voting table by: creating first candidate binary features; calculating a global loss reduction for each first candidate binary feature; selecting one first candidate binary feature having minimal global loss reduction; and repeating to select stage-size binary features; and performing a tree split using the voting table by: creating second candidate binary features; calculating a combined loss reduction for each stage-split size group of the second candidate binary features; selecting one of the groups having a maximal combined loss reduction; and creating a child-directing table using the selected binary features.

Structure and training for image classification

A system for creating hand gestures representations, comprising an interface for interacting with a user, a storage storing a plurality of discrete pose values and discrete motion values, a memory storing a gesture visual builder code, one or more processors coupled to the interface, storage and memory to execute the gesture visual builder code allowing the user to create hand gesture. The gesture visual builder code comprising code instructions to present the user with a GUI which displays a hierarchical menu driven interface, code instructions to receive iteratively user instructions from the user using the hierarchical menu driven interface, for creating a logical sequence of hand gesture by defining one or more hand pose features records and hand motion features records and code instructions to generate a code segment defining the one or more hand pose/motion features records through the discrete pose/motion values respectively.

Gestures visual builder tool

Ranking based on facial image analysis

Depth map correction using lookup tables is described. In an example depth maps may be generated that measure a depth to an object using differences in phase between light transmitted from a camera which illuminates the object and light received at the camera which has been reflected from the object. In various embodiments depth maps may be subject to errors caused by received light undergoing multiple reflections before being received by the camera. In an example a correction for an estimated depth of an object may be computed and stored in a lookup table which maps the amplitude and phase of the received light to a depth correction. In an example the amplitudes and frequencies of each modulation frequency may be to access lookup table which stores corrections for the depth of an object and which allows an accurate depth map to be obtained.

Depth map correction using lookup tables

Hand gesture detection electrical device for detecting hand gestures, comprising an IC electronically integrating:

Electrical device for hand gestures detection

Growing community of inventors

Shimshit, Israel

Eyal Krupka