Abstract: Examples are disclosed that relate to generating expressive avatars using multi-modal three-dimensional face modeling and tracking. One example includes a computer system comprising a processor coupled to a storage system that stores instructions. Upon execution by the processor, the instructions cause the processor to receive initialization data describing an initial state of a facial model. The instructions further cause the processor to receive a plurality of multi-modal data signals. The instructions further cause the processor to perform a fitting process using the initialization data and the plurality of multi-modal data signals. The instructions further cause the processor to determine a set of parameters based on the fitting process, wherein the determined set of parameters describes an updated state of the facial model.

Abstract: Keypoints are predicted in an image. Predictions are generated for each of the keypoints of an image as a 2D random variable, normally distributed with location (x, y) and standard deviation sigma. A neural network is trained to maximize a log-likelihood that samples from each of the predicted keypoints equal a ground truth. The trained neural network is used to predict keypoints of an image without generating a heatmap.

Abstract: A method of object detection includes receiving a first image taken from a first perspective by a first camera and receiving a second image taken from a second perspective, different from the first perspective, by a second camera. Each pixel in the first image is offset relative to a corresponding pixel in the second image by a predetermined offset distance resulting in offset first and second images. A particular pixel of the offset first image depicts a same object locus as a corresponding pixel in the offset second image only if the object locus is at an expected object-detection distance from the first and second cameras. The method includes recognizing that a target object is imaged by the particular pixel of the offset first image and the corresponding pixel of the offset second image.

Abstract: Symbol recognition techniques may be applied to documents comprising various forms of content. Documents including both text and mathematical expressions may be problematic, as applying a recognizer that does not match the content may produce anomalous results. Instead, a parser may evaluate the document to classify respective regions as one of a text region or a mathematics region, based on the characteristics of each type of content. The recognizer corresponding to the content of each region may be applied to produce a composite document comprising both recognized text expressions and recognized mathematical expressions. Additional functionality may be presented based on the recognized content; e.g.

Abstract: Symbol recognition techniques may be applied to documents comprising various forms of content. Documents including both text and mathematical expressions may be problematic, as applying a recognizer that does not match the content may produce anomalous results. Instead, a parser may evaluate the document to classify respective regions as one of a text region or a mathematics region, based on the characteristics of each type of content. The recognizer corresponding to the content of each region may be applied to produce a composite document comprising both recognized text expressions and recognized mathematical expressions. Additional functionality may be presented based on the recognized content; e.g.

Abstract: A method of object detection includes receiving a first image taken from a first perspective by a first camera and receiving a second image taken from a second perspective, different from the first perspective, by a second camera. Each pixel in the first image is offset relative to a corresponding pixel in the second image by a predetermined offset distance resulting in offset first and second images. A particular pixel of the offset first image depicts a same object locus as a corresponding pixel in the offset second image only if the object locus is at an expected object-detection distance from the first and second cameras. The method includes recognizing that a target object is imaged by the particular pixel of the offset first image and the corresponding pixel of the offset second image.

Abstract: A method of object detection includes receiving a first image taken by a first stereo camera, receiving a second image taken by a second stereo camera, and offsetting the first image relative to the second image by an offset distance selected such that each corresponding pixel of offset first and second images depict a same object locus if the object locus is at an assumed distance from the first and second stereo cameras. The method further includes locating a target object in the offset first and second images.

Abstract: Image processing for productivity applications is provided. An image may be received by a computing device. The computing device may detect the edges comprising the received image and adjust the image based on a skew state of the detected edges. The computing device may then process the adjusted image to correct imbalances. The computing device may then assign an image classification to the processed image. The computing device may then adjust the processed image based on the assigned image classification.

Abstract: The technology described herein employs techniques for overlaying (superimposing) translated text on top of (over) scanned text in realtime. The technology recognizes text in an image and identifies a first language in which the text is written. The technology translates the text into a second language and generates an overlay in the second language. The overlay is then inserted into the display over the text in the image.

Abstract: The technology described herein employs techniques for overlaying (superimposing) translated text on top of (over) scanned text in realtime. The technology recognizes text in an image and identifies a first language in which the text is written. The technology translates the text into a second language and generates an overlay in the second language. The overlay is then inserted into the display over the text in the image.

Abstract: Image processing for productivity applications is provided. An image may be received by a computing device. The computing device may detect the edges comprising the received image and adjust the image based on a skew state of the detected edges. The computing device may then process the adjusted image to correct imbalances. The computing device may then assign an image classification to the processed image. The computing device may then adjust the processed image based on the assigned image classification.

Abstract: Image processing for productivity applications is provided. An image may be received by a computing device. The computing device may detect the edges comprising the received image and adjust the image based on a skew state of the detected edges. The computing device may then process the adjusted image to correct imbalances. The computing device may then assign an image classification to the processed image. The computing device may then adjust the processed image based on the assigned image classification.

Abstract: Architecture that employs techniques for overlaying (superimposing) translated text on top of (over) scanned text in realtime translation to provide clear visual correlation between original text and translated text. Algorithms are provided that overlay text in cases of translated scanned text of language written in first direction to a language written in same direction, translate scanned text from a first language written in a first direction to a second language written in the opposite direction, and translated scanned text from a language written in a first direction to language written in a different direction.

Abstract: Architecture that enables optical character recognition (OCR) of text in video frames at the rate at which the frames are received. Additionally, conflation is performed on multiple text recognition results in the frame sequence. The architecture comprises an OCR text recognition engine and a tracker system; the tracker system establishes a common coordinate system in which OCR results from different frames may be compared and/or combined. From a set of sequential video frames, a keyframe is chosen from which the reference coordinate system is established. An estimated transformation from keyframe coordinates to subsequent video frames is computed using the tracker system. When text recognition is completed for any subsequent frame, the result coordinates can be related to the keyframe using the inverse transformation from the processed frame to the reference keyframe. The results can be rendered for viewing as the results are obtained.

Abstract: Architecture that employs techniques for overlaying (superimposing) translated text on top of (over) scanned text in realtime translation to provide clear visual correlation between original text and translated text. Algorithms are provided that overlay text in cases of translated scanned text of language written in first direction to a language written in same direction, translate scanned text from a first language written in a first direction to a second language written in the opposite direction, and translated scanned text from a language written in a first direction to language written in a different direction.

Abstract: Image processing for productivity applications is provided. An image may be received by a computing device. The computing device may detect the edges comprising the received image and adjust the image based on a skew state of the detected edges. The computing device may then process the adjusted image to correct imbalances. The computing device may then assign an image classification to the processed image. The computing device may then adjust the processed image based on the assigned image classification.

Abstract: A method of object detection includes receiving a first image taken by a first stereo camera, receiving a second image taken by a second stereo camera, and offsetting the first image relative to the second image by an offset distance selected such that each corresponding pixel of offset first and second images depict a same object locus if the object locus is at an assumed distance from the first and second stereo cameras. The method further includes locating a target object in the offset first and second images.

Abstract: Architecture that employs techniques for overlaying (superimposing) translated text on top of (over) scanned text in realtime translation to provide clear visual correlation between original text and translated text. Algorithms are provided that overlay text in cases of translated scanned text of language written in first direction to a language written in same direction, translate scanned text from a first language written in a first direction to a second language written in the opposite direction, and translated scanned text from a language written in a first direction to language written in a different direction.

Abstract: Freeform mathematical computations are described. In implementations, an input is recognized as a freeform selection of an area of a user interface output by a computing device. Text is identified that is associated with the area defined by the freeform selection and that includes one or more numbers. A mathematical computation is performed that involves the one or more numbers.

Abstract: Architecture that enables optical character recognition (OCR) of text in video frames at the rate at which the frames are received. Additionally, conflation is performed on multiple text recognition results in the frame sequence. The architecture comprises an OCR text recognition engine and a tracker system; the tracker system establishes a common coordinate system in which OCR results from different frames may be compared and/or combined. From a set of sequential video frames, a keyframe is chosen from which the reference coordinate system is established. An estimated transformation from keyframe coordinates to subsequent video frames is computed using the tracker system. When text recognition is completed for any subsequent frame, the result coordinates can be related to the keyframe using the inverse transformation from the processed frame to the reference keyframe. The results can be rendered for viewing as the results are obtained.