Ams Sensors Singapore Pte. Ltd.

Jd.com American Technologies Corporation

Beijing Jingdong Shangke Information Technology Co., Ltd.

Beijing Wodong Tianjun Information Technology Co., Ltd.

Chi Zhang

Florin Cutu

Xiaochuan Fan

Guanghan Ning

Yun Xiao

Hui Zhou

Alireza Yasan

Yong Yang

Di Wu

Hendrik Volkerink

Xin Liu

Qingan Yan

Yuze Zhang

Rong Yuan

Wanyan Zheng

Shiliang Diao

Lingfei Wu

Xincheng Wang

Yue Shang

Ping Liu

Yunjiang Jiang

Xueying Zhang

Xiaofan Zhang

Jui-Hsin Lai

Chenyou Fan

A method for recommending a product, includes: providing product information having a product description, a main image, and a plurality of alternate images; for each alternate image: performing saliency segmentation to obtain a segment and a background, defining a segment bounding box enclosing the segment, extracting image feature from the segment bounding box, extracting textual feature from the product description, extracting main image feature from the main image, matching the image feature of the segment bounding box to the textual feature and the main image feature, and determining the alternate image as a qualified alternate image if the image feature of the segment bounding box matches the textual feature and the main image feature; and when a number of the qualified alternate image equals to or is greater than a threshold number, recommending the product to customers.

System and method for validating product photography

A computer-implemented method for searching a product corresponding to a query from a customer. The method includes: embedding the query to obtain a query embedding; retrieving product information having a product text and a product image; embedding the product text to obtain a product text embedding, embedding the product image to obtain a product image embedding, and combining the product text embedding and the product image embedding to obtain a product embedding, where the product image embedding has a same format as the product text embedding; subjecting the query embedding and the product embedding to a transformer to determine whether the query and the product are relevant; and providing the product as a search result of the query when the query and the product are relevant.

System and method for product search by embedding visual representation into text sequences

A system and a method for time series forecasting. The method includes: providing input feature vectors corresponding to a plurality of future time steps; performing bi-directional long-short term memory network (BiLSTM) on the input feature vectors to obtain hidden outputs corresponding to the plurality of future time steps; for each future time step: performing temporal convolution on the hidden outputs using a plurality of temporal scales to obtain context features at the plurality of temporal scales, and summating the context features at the plurality of temporal scales using a plurality of weights to obtain multi-scale context features; and converting the multi-scale context features to obtain the time series forecasting corresponding to the future time steps.

System and method for multi-horizon time series forecasting with dynamic temporal context learning

A method, a device, and a non-transitory computer readable medium for item recommendation based on visual elements. The method includes: determining, by one or more processors, visual elements from an item image of an item; generating, by the one or more processors, an element descriptor for the item based on at least a part of the visual elements; and calculating, by the one or more processors, a compatibility value between the element descriptor and one or more other element descriptors for one or more other items.

Device and method for item recommendation based on visual elements

A method for virtual fitting, includes providing a customer avatar and a garment model of a selected garment; registering the garment model to the customer avatar to obtain a dressed garment; capturing a motion image of the customer; performing simulation to the customer avatar and the dressed garment based on the motion image; rendering the simulated customer avatar-garment; and displaying the rendered avatar-garment on a displaying device. Rigging is performed to the dressed garment to obtain rigged garment, and cloth simulation is performed to the dressed garment model to obtain simulated cloth. Each vertex of the simulated cloth has a distance to nearest body mesh vertices on the simulated customer avatar, and the simulated garment is the rigged garment when the distance is less than 0 or the distance is greater than a threshold distance. Air mesh between the avatar and the garment is used for collision detection.

System and method for virtual fitting

A method, a device and a non-transitory computer readable medium for tracking poses of multiple objects. The method includes detecting, by a processor, objects from each of a plurality of consecutive frames in a video sequence; estimating, by the processor, a pose of each of the objects within each of the plurality of consecutive frames; and tracking, by the processor, the poses of each of the objects across the plurality of consecutive frames.

Device and method of tracking poses of multiple objects based on single-object pose estimator

Presenting a merged, fused three-dimensional point cloud includes acquiring multiple sets of images of a scene from different vantage points, each set of images including respective stereo matched images and a color image. For each respective set of images, a disparity map based on the plurality of stereo images is obtained, data from the color image is fused onto the disparity map so as to generate a fused disparity map, and a three-dimensional fused point cloud is created from the fused disparity map. The respective three-dimensional fused point clouds is merged together so as to obtain a merged, fused three-dimensional point cloud. The techniques can be advantageous even under the constraints of sparseness and low-depth resolution, and are suitable, in some cases, for real-time or near real-time applications in which computing time needs to be reduced.

Generating a merged, fused three-dimensional point cloud based on captured images of a scene

A brightness image of a scene is converted into a corresponding frequency domain image and it is determined whether a threshold condition is satisfied for each of one or more regions of interest in the frequency domain image, the threshold condition being that the number of frequencies in the region of interest is at least as high as a threshold value. The results of the determination can be used to facilitate selection of an appropriate block matching algorithm for deriving disparity or other distance data and/or to control adjustment of an illumination source that generates structured light for the scene.

Three-dimensional imaging using frequency domain-based processing

The present disclosure describes projecting a structured light pattern onto a surface and detecting and responding to interactions with the same. A method includes-acquiring an image based on light reflected from a vicinity of the projection surface, and identifying regions of the acquired image that correspond to a feature that is within a specified distance of the projection surface by identifying regions of the acquired image for which intensity data differs relative to other regions of the acquired image and which fit a specified homographic relationship with respect to corresponding regions of a reference image.

Projecting a structured light pattern onto a surface and detecting and responding to interactions with the same

The present disclosure describes projecting a structured light pattern projected onto a surface and detecting and responding to interactions with the same. The techniques described here can, in some cases, facilitate recognizing that an object such as a user's hand is adjacent the plane of a projection surface and can distinguish the object from the projection surface itself. Movement of the object then can be interpreted, for example, as a specified type of gesture that can trigger a specified type of operation to occur.

Growing community of inventors

Fremont, CA, United States of America

Chi Zhang