Peng Yung Mei Wang DeceasedAlameda, CA

2003016, Sep 4, 2003

Mar 4, 2002

10/091371

Peng Wang - Burlingame CA, US
Lin Lei - Melshan, CN

A61K035/78

424/725000

The present invention provides novel compositions and methods for lowering blood glucose levels, as well as manufacture processes for producing the compositions. Specifically, the present invention provides novel compositions that are extracts of the plant Prunella Linn and/or Rabdosis (Blume) Hasskarl containing enriched corosolic acid. Methods of isolating corosolic acid at high purity from these plants are also provided. These extracts and the purified corosolic acid can be used for lowering blood sugar levels and reducing accumulation of triglyeride in the treatment of diabetes, obesity and related conditions.

2012000, Jan 5, 2012

Apr 29, 2011

13/097497

Renbin Peng - San Jose CA, US
Peng Wang - Princeton NJ, US
Terrence Chen - Princeton NJ, US
Dorin Comaniciu - Princeton Junction NJ, US

Slemens Corporation - Iselin NJ

A61B 8/12

600424

Multiple candidates are optimized in medical device or feature tracking. Possible locations of medical devices or features for each of a plurality of different times are received. The possible locations of devices are modeled using a probability function. An iterative solution to obtain the maximum of the probability function determines the possible locations to be used as the locations of the medical devices or features for each time. Where two or more medical devices or features are provided with a geometric relationship, such as being connected by a detected guide wire, the probability function may account for the geometric relationship, such as a geodesic distance between the possible locations for the two medical devices.

2021039, Dec 16, 2021

Jun 12, 2020

16/980373

- Sunnyvale CA, US
- Beijing, CN
Peng WANG - Sunnyvale CA, US
Ruigang YANG - Beijing, CN

Baidu USA LLC - Sunnyvale CA
Baidu.com Times Technology (Beijing) Co., Ltd. - Beijing CA

G06T 13/40
G06K 9/00
G06K 9/62
G10L 25/57
G10L 15/26
G06N 3/04
G06N 3/08

Presented herein are novel embodiments for converting a given speech audio or text into a photo-realistic speaking video of a person with synchronized, realistic, and expressive body dynamics. In one or more embodiments, 3D skeleton movements are generated from the audio sequence using a recurrent neural network, and an output video is synthesized via a conditional generative adversarial network. To make movements realistic and expressive, the knowledge of an articulated 3D human skeleton and a learned dictionary of personal speech iconic gestures may be embedded into the generation process in both learning and testing pipelines. The former prevents the generation of unreasonable body distortion, while the later helps the model quickly learn meaningful body movement with a few videos. To produce photo-realistic and high-resolution video with motion details, a part-attention mechanism is inserted in the conditional GAN, where each detailed part is automatically zoomed in to have their own discriminators.

2020027, Aug 27, 2020

Feb 26, 2019

16/286484

- Sunnyvale CA, US
Peng WANG - Sunnyvale CA, US
Ruigang YANG - Beijing, CN

Baidu USA LLC - Sunnyvale CA

G06T 7/593
G06K 9/62

Presented are systems and methods for improving speed and quality of real-time per-pixel depth estimation of scene layouts from a single image by using a 3D end-to-end Convolutional Spatial Propagation Network (CSPN). An efficient linear propagation model performs propagation using a recurrent convolutional operation. The affinity among neighboring pixels may be learned through a deep convolutional neural network (CNN). The CSPN may be applied to two depth estimation tasks, given a single image: (1) to refine the depth output of existing methods, and (2) to convert sparse depth samples to a dense depth map, e.g., by embedding the depth samples within the propagation procedure. For stereo depth estimation, the 3D CPSN is applied to stereo matching by adding a diffusion dimension over discrete disparity space and feature scale space. This aids the recovered stereo depth to generate more details and to avoid error matching from noisy appearance caused by sunlight, shadow, and similar effects.

2019019, Jun 27, 2019

Dec 21, 2017

15/850404

- San Jose CA, US
Peng Wang - Dublin CA, US

Adobe Inc. - San Jose CA

G06F 17/30
G06F 11/14
G06F 9/54

Techniques for achieving consistency across data layers associated with multiple microservices. An always strictly consistent microservice coordination system provides immediate consistency for data stored across multiple microservices. A strictly successful eventually consistent multiple microservice coordination system provides eventual consistency for data stored across multiple microservices.

2018028, Oct 4, 2018

Jun 4, 2018

15/996833

- San Jose CA, US
Scott Cohen - Sunnyvale CA, US
Peng Wang - Los Angeles CA, US
Bryan Russell - San Francisco CA, US
Brian Price - Pleasant Grove UT, US
Jonathan Eisenmann - San Francisco CA, US

G06T 7/50

Techniques for planar region-guided estimates of 3D geometry of objects depicted in a single 2D image. The techniques estimate regions of an image that are part of planar regions (i.e., flat surfaces) and use those planar region estimates to estimate the 3D geometry of the objects in the image. The planar regions and resulting 3D geometry are estimated using only a single 2D image of the objects. Training data from images of other objects is used to train a CNN with a model that is then used to make planar region estimates using a single 2D image. The planar region estimates, in one example, are based on estimates of planarity (surface plane information) and estimates of edges (depth discontinuities and edges between surface planes) that are estimated using models trained using images of other scenes.

2018007, Mar 15, 2018

Sep 9, 2016

15/261749

- SAN JOSE CA, US
Scott COHEN - Sunnyvale CA, US
Peng WANG - Los Angeles CA, US
Bryan RUSSELL - San Francisco CA, US
Brian PRICE - San Jose CA, US
Jonathan EISENMANN - San Francisco CA, US

G06T 7/00

Techniques for planar region-guided estimates of 3D geometry of objects depicted in a single 2D image. The techniques estimate regions of an image that are part of planar regions (i.e., flat surfaces) and use those planar region estimates to estimate the 3D geometry of the objects in the image. The planar regions and resulting 3D geometry are estimated using only a single 2D image of the objects. Training data from images of other objects is used to train a CNN with a model that is then used to make planar region estimates using a single 2D image. The planar region estimates, in one example, are based on estimates of planarity (surface plane information) and estimates of edges (depth discontinuities and edges between surface planes) that are estimated using models trained using images of other scenes.

2016035, Dec 1, 2016

May 28, 2015

14/724660

- San Jose CA, US
Scott D. Cohen - Sunnyvale CA, US
Peng Wang - Los Angeles CA, US
Xiaohui Shen - San Jose CA, US
Brian L. Price - San Jose CA, US

G06T 7/00
G06K 9/66
H04N 13/02

Joint depth estimation and semantic labeling techniques usable for processing of a single image are described. In one or more implementations, global semantic and depth layouts are estimated of a scene of the image through machine learning by the one or more computing devices. Local semantic and depth layouts are also estimated for respective ones of a plurality of segments of the scene of the image through machine learning by the one or more computing devices. The estimated global semantic and depth layouts are merged with the local semantic and depth layouts by the one or more computing devices to semantically label and assign a depth value to individual pixels in the image.