Intel Corporation

Samsung Sdi Co., Inc.

Samsung Electronics Co., Ltd.

Tahoe Research, Ltd.

Minje Park

Tae-Hoon Kim

Myung-Ho Ju

Yangzhou Du

Wenlong Li

Xiaofeng Tong

Jihyeon Kate Yi

Yikai Fang

Qiang Eric Li

Yeongjae Cheon

Qiang Li

Xiaolu Shen

Hyungsoo Lee

Sumin Lee

Lidan Zhang

Kanghee Lee

Mijong Kim

Seongho Jeon

Wooju Ryu

Byungseok Roh

Hongmo Je

Jinwook Lee

Taesup Kim

Jinhyon Lee

Jaemyung Lee

Byoungsun Lee

Koichi Takei

Gyusung Kim

Hyunjoon Lee

Ken Ogata

Jeong-Ju Cho

Jongki Lee

Jiwoon Lee

Sean Pyo

Eunyoung Goh

Kiyoung Jeong

Jongho Jeon

Songki Choi

Boogeon Yoon

Olivier Duchenne

Seok-Yong Byun

Jihyeon Yi

Sangyup Lee

Kye-Hyeon Kim

Sanghoon Hong

Avatar animation systems disclosed herein provide high quality, real-time avatar animation that is based on the varying countenance of a human face. In some example embodiments, the real-time provision of high quality avatar animation is enabled, at least in part, by a multi-frame regressor that is configured to map information descriptive of facial expressions depicted in two or more images to information descriptive of a single avatar blend shape. The two or more images may be temporally sequential images. This multi-frame regressor implements a machine learning component that generates the high quality avatar animation from information descriptive of a subject's face and/or information descriptive of avatar animation frames previously generated by the multi-frame regressor. The machine learning component may be trained using a set of training images that depict human facial expressions and avatar animation authored by professional animators to reflect facial expressions depicted in the set of training images.

Avatar animation system

Systems, apparatuses and methods may provide for technology that generates, by a full inference path of a neural network, a first detection result associated with one or more objects in a first video frame. The technology may also generate, by a partial inference path of the neural network, a second detection result based on the first detection result, wherein the second detection result corresponds to a second video frame that is subsequent to the first video frame.

Partial inference path technology in general object detection networks for efficient video processing

Examples of systems and methods for augmented facial animation are generally described herein. A method for mapping facial expressions to an alternative avatar expression may include capturing a series of images of a face, and detecting a sequence of facial expressions of the face from the series of images. The method may include determining an alternative avatar expression mapped to the sequence of facial expressions, and animating an avatar using the alternative avatar expression.

Augmented facial animation

An example computer-vision system to convert images includes an image converter () to convert a near infrared light first image () to form a visible light image (), and to update a coefficient of the image converter () based on a difference (), an object recognizer () to recognize an object () in the first visible light image (), and an object recognition analyzer () to determine the difference () between the object () recognized in the first visible light image () and an object () associated with the near infrared light image ().

Methods and apparatus to convert images for computer-vision systems

A secondary particle-type electrode active material including: at least one pore; and a shell surrounding the at least one pore, wherein the shell includes a first layer and a second layer, the first layer including a first carbonaceous material, and the second layer including a composite and disposed on the first layer, wherein the composite includes a silicon material and a second carbonaceous material. Also, an electrode and a secondary battery include the electrode active material.

Electrode active material, electrode and secondary battery including the same, and method of preparing the electrode active material

Avatar animation systems disclosed herein provide high quality, real-time avatar animation that is based on the varying countenance of a human face. In some example embodiments, the real-time provision of high quality avatar animation is enabled at least in part, by a multi-frame regressor that is configured to map information descriptive of facial expressions depicted in two or more images to information descriptive of a single avatar blend shape. The two or more images may be temporally sequential images. This multi-frame regressor implements a machine learning component that generates the high quality avatar animation from information descriptive of a subject's face and/or information descriptive of avatar animation frames previously generated by the multi-frame regressor. The machine learning component may be trained using a set of training images that depict human facial expressions and avatar animation authored by professional animators to reflect facial expressions depicted in the set of training images.

Techniques related to automatic perspective control of images using vanishing points are discussed. Such techniques may include determining a perspective control vanishing point associated with the image based on lines detected within the image, rotating the image based on the perspective control vanishing point to generate an aligned image, and warping the aligned image based on aligning two lines of the detected lines that meet at the perspective control vanishing point.

Automatic perspective control using vanishing points

A complex for anode active material, the complex including: a conductive framework having a spherical skein shape; and metal particles dispersed in the conductive framework. Also an anode including the complex, a lithium secondary battery including the anode, and a method of preparing the complex.

Complex for anode active material, anode including the complex, lithium secondary battery including the anode, and method of preparing the complex

Technologies for multi-scale object detection include a computing device including a multi-layer convolution network and a multi-scale region proposal network (RPN). The multi-layer convolution network generates a convolution map based on an input image. The multi-scale RPN includes multiple RPN layers, each with a different receptive field size. Each RPN layer generates region proposals based on the convolution map. The computing device may include a multi-scale object classifier that includes multiple region of interest (ROI) pooling layers and multiple associated fully connected (FC) layers. Each ROI pooling layer has a different output size, and each FC layer may be trained for an object scale based on the output size of the associated ROI pooling layer. Each ROI pooling layer may generate pooled ROIs based on the region proposals and each FC layer may generate object classification vectors based on the pooled ROIs. Other embodiments are described and claimed.

Technologies for improved object detection accuracy with multi-scale representation and training

A lithium secondary battery includes a thick-film negative electrode having a current density of about 4.0 mA/cmto about 7.0 mA/cmand a low-viscosity electrolytic solution having a viscosity of about 3 cP or less. Since the electrolytic solution includes a propionate-based ester compound, impregnation of the electrolytic solution in electronic devices having a thick-film negative electrode and lifespan characteristics of the devices may be improved.

Lithium secondary battery

Techniques are provided for facial recognition using decoy-based matching of facial image features. An example method may include comparing extracted facial features of an input image, provided for recognition, to facial features of each of one or more images in a gallery of known faces, to select a closest gallery image. The method may also include calculating a first distance between the input image and the selected gallery image. The method may further include comparing the facial features of the input image to facial features of each of one or more images in a set of decoy faces, to select a closest decoy image and calculating a second distance between the input image and the selected decoy image. The method may further include recognizing a match between the input image and the selected gallery image based on a comparison of the first distance and the second distance.

Decoy-based matching system for facial recognition

Apparatuses, methods and storage medium associated with creating an avatar video are disclosed herein. In embodiments, the apparatus may one or more facial expression engines, an animation-rendering engine, and a video generator. The one or more facial expression engines may be configured to receive video, voice and/or text inputs, and, in response, generate a plurality of animation messages having facial expression parameters that depict facial expressions for a plurality of avatars based at least in part on the video, voice and/or text inputs received. The animation-rendering engine may be configured to receive the one or more animation messages, and drive a plurality of avatar models, to animate and render the plurality of avatars with the facial expression depicted. The video generator may be configured to capture the animation and rendering of the plurality of avatars, to generate a video. Other embodiments may be described and/or claimed.

Facial expression based avatar rendering in video animation and method

According to a method for providing a notification on a face recognition environment of the present disclosure, the method includes obtaining an input image that is input in a preview state, comparing feature information for a face included in the input image with feature information for a plurality of reference images of people stored in a predetermined database to determine, in real-time, whether the input image satisfies a predetermined effective condition for photographing. The predetermined effective condition for photographing is information regarding a condition necessary for recognizing the face included in the input image at a higher accuracy level than a predetermined accuracy level. The method further includes providing a user with a predetermined feedback for photographing guidance that corresponds to whether the predetermined effective condition for photographing is satisfied. According to the method, a condition of a face image detected for face recognition is checked, and if there is an unsuitable element in recognizing the face, it is notified to a user such that an obstruction environment hindering the face recognition by the user is removed, for enhancing a success rate of the face recognition.

Method, apparatus for providing a notification on a face recognition environment, and computer-readable recording medium for executing the method

Growing community of inventors

Seongnam, South Korea

Minje Park