Snap Inc.

Yuncheng Li

Ning Xu

Ning Zhang

Zhou Ren

Zehao Xue

Yingying Wang

Enxu Yan

Tan Yu

Linjie Luo

Guohui Wang

Sumant Milind Hanumante

Xuecheng Nie

Liuhao Ge

Jianchao Yang

Samuel Edward Hare

Itamar Berger

Tony Mathew

Avihay Assouline

Jonathan Solichin

Travis Chen

Yiwei Ma

Xuan Huang

Harsh Agrawal

Ye Tao

Jung Hyun Kim

Tao Ning

Jonathan M Rodriguez, Ii

Linjie Yang

Zhengyuan Yang

Systems, methods, devices, computer readable instruction media, and other embodiments are described for automated image processing and insight presentation. One embodiment involves receiving a plurality of ephemeral content messages from a plurality of client devices, and processing the messages to identify content associated with at least a first content type. A set of analysis data associated with the first content type is then generated from the messages, and portions of the messages associated with the first content type are processed to generate a first content collection. The first content collection and the set of analysis data are then communicated to a client device configured for a display interface comprising the first content collection and a representation of at least a portion of the set of analysis data.

Automated image processing and insight presentation

Remote distribution of multiple neural network models to various client devices over a network can be implemented by identifying a native neural network and remotely converting the native neural network to a target neural network based on a given client device operating environment. The native neural network can be configured for execution using efficient parameters, and the target neural network can use less efficient but more precise parameters.

Remote distribution of neural networks

Systems, devices, media and methods are presented for a human pose tracking framework. The human pose tracking framework may identify a message with video frames, generate, using a composite convolutional neural network, joint data representing joint locations of a human depicted in the video frames, the generating of the joint data by the composite convolutional neural network done by a deep convolutional neural network operating on one portion of the video frames, a shallow convolutional neural network operating on a another portion of the video frames, and tracking the joint locations using a one-shot learner neural network that is trained to track the joint locations based on a concatenation of feature maps and a convolutional pose machine. The human pose tracking framework may store, the joint locations, and cause presentation of a rendition of the joint locations on a user interface of a client device.

Efficient human pose tracking in videos

Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for detecting a pose of a user. The program and method include receiving a monocular image that includes a depiction of a body of a user; detecting a plurality of skeletal joints of the body depicted in the monocular image; and determining a pose represented by the body depicted in the monocular image based on the detected plurality of skeletal joints of the body. A pose of an avatar is modified to match the pose represented by the body depicted in the monocular image by adjusting a set of skeletal joints of a rig of an avatar based on the detected plurality of skeletal joints of the body; and the avatar having the modified pose that matches the pose represented by the body depicted in the monocular image is generated for display.

Body pose estimation

Systems and methods are disclosed for capturing multiple sequences of views of a three-dimensional object using a plurality of virtual cameras. The systems and methods generate aligned sequences from the multiple sequences based on an arrangement of the plurality of virtual cameras in relation to the three-dimensional object. Using a convolutional network, the systems and methods classify the three-dimensional object based on the aligned sequences and identify the three-dimensional object using the classification.

Sequence-of-sequences model for 3D object recognition

Systems and methods herein describe using a neural network to identify a first set of joint location coordinates and a second set of joint location coordinates and identifying a three-dimensional hand pose based on both the first and second sets of joint location coordinates.

Hand pose estimation from stereo cameras

Systems, devices, media, and methods are presented for object detection and inserting graphical elements into an image stream in response to detecting the object. The systems and methods detect an object of interest in received frames of a video stream. The systems and methods identify a bounding box for the object of interest and estimate a three-dimensional position of the object of interest based on a scale of the object of interest. The systems and methods generate one or more graphical elements having a size based on the scale of the object of interest and a position based on the three-dimensional position estimated for the object of interest. The one or more graphical elements are generated within the video stream to form a modified video stream. The systems and methods cause presentation of the modified video stream including the object of interest and the one or more graphical elements.

Neural network-based image stream modification

Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for receiving a monocular image that includes a depiction of a hand and extracting features of the monocular image using a plurality of machine learning techniques. The program and method further include modeling, based on the extracted features, a pose of the hand depicted in the monocular image by adjusting skeletal joint positions of a three-dimensional (3D) hand mesh using a trained graph convolutional neural network (CNN); modeling, based on the extracted features, a shape of the hand in the monocular image by adjusting blend shape values of the 3D hand mesh representing surface features of the hand depicted in the monocular image using the trained graph CNN; and generating, for display, the 3D hand mesh adjusted to model the pose and shape of the hand depicted in the monocular image.

3D hand shape and pose estimation

Segmentation of an image into individual body parts is performed based on a trained model. The model is trained with a plurality of training images, each training image representing a corresponding training figure. The model is also trained with a corresponding plurality of segmentations of the training figures. Each segmentation is generated by positioning body parts between defined positions of joints of the represented figure. The body parts are represented by body part templates obtained from a template library, with the templates defining characteristics of body parts represented by the templates.

Weakly supervised semantic parsing

Aspects of the present disclosure involve a system comprising a storage medium storing a program and method for receiving a video comprising a plurality of video segments; selecting a target action sequence that includes a sequence of action phases; receiving features of each of the video segments; computing, based on the received features, for each of the plurality of video segments, a plurality of action phase confidence scores indicating a likelihood that a given video segment includes a given action phase of the sequence of action phases; identifying a set of consecutive video segments of the plurality of video segments that corresponds to the target action sequence, wherein video segments in the set of consecutive video segments are arranged according to the sequence of action phases; and generating a display of the video that includes the set of consecutive video segments and skips other video segments in the video.

Segment action detection

Growing community of inventors

Los Angeles, CA, United States of America

Yuncheng Li