Jiang X Wang

US Patent:

20220414425, Dec 29, 2022

Filed:

Aug 19, 2022

Appl. No.:

17/821076

Inventors:

- Mountain View CA, US
Xiaojie Jin - Palo Alto CA, US
Joshua Foster Slocum - San Francisco CA, US
Shengyang Dai - Mountain View CA, US
Jiang Wang - Mountain View CA, US

Assignee:

Google LLC - Mountain View CA

International Classification:

G06N 3/04
G06N 20/00
G06F 16/901

Abstract:

Methods, and systems, including computer programs encoded on computer storage media for neural network architecture search. A method includes defining a neural network computational cell, the computational cell including a directed graph of nodes representing respective neural network latent representations and edges representing respective operations that transform a respective neural network latent representation; replacing each operation that transforms a respective neural network latent representation with a respective linear combination of candidate operations, where each candidate operation in a respective linear combination has a respective mixing weight that is parameterized by one or more computational cell hyper parameters; iteratively adjusting values of the computational cell hyper parameters and weights to optimize a validation loss function subject to computational resource constraints; and generating a neural network for performing a machine learning task using the defined computational cell and the adjusted values of the computational cell hyper parameters and weights.

US Patent:

20220309549, Sep 29, 2022

Filed:

Mar 1, 2022

Appl. No.:

17/653097

Inventors:

- Mountain View CA, US
Jiang Wang - Santa Clara CA, US
Shengyang Dai - Dublin CA, US

Assignee:

Google LLC - Mountain View CA

International Classification:

G06Q 30/04
G06V 30/412
G06V 30/414

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for converting unstructured documents to structured key-value pairs. In one aspect, a method includes: providing an image of a document to a detection model, wherein: the detection model is configured to process the image to generate an output that defines one or more bounding boxes generated for the image; and each bounding box generated for the image is predicted to enclose a key-value pair including key textual data and value textual data, wherein the key textual data defines a label that characterizes the value textual data; and for each of the one or more bounding boxes generated for the image: identifying textual data enclosed by the bounding box using an optical character recognition technique; and determining whether the textual data enclosed by the bounding box defines a key-value pair.

US Patent:

20220254137, Aug 11, 2022

Filed:

Aug 5, 2019

Appl. No.:

17/622462

Inventors:

Jilin TU - Mountain View CA, US
Jiang WANG - Mountain View CA, US
Huizhong CHEN - Mountain View CA, US
Xiangxin ZHU - Mountain View CA, US
Shengyang DAI - Mountain View CA, US
- Mountain View CA, US

International Classification:

G06V 10/50
G06V 10/778
G06V 10/75

Abstract:

A computing system for detecting objects in an image can perform operations including generating an image pyramid that includes a first level corresponding with the image at a first resolution and a second level corresponding with the image at a second resolution. The operations can include tiling the first level and the second level by dividing the first level into a first plurality of tiles and the second level into a second plurality of tiles; inputting the first plurality of tiles and the second plurality of tiles into a machine-learned object detection model; receiving, as an output of the machine-learned object detection model, object detection data that includes bounding boxes respectively defined with respect to individual ones of the first plurality of tiles and the second plurality of tiles; and generating image object detection output by mapping the object detection data onto an image space of the image.

US Patent:

20210096637, Apr 1, 2021

Filed:

Mar 30, 2020

Appl. No.:

16/834783

Inventors:

- Cupertino CA, US
Jiang Wang - San Jose CA, US

International Classification:

G06F 3/01

Abstract:

Systems, methods, and computer-readable media for detecting blow events with an electronic device and for switching between different modes of an electronic device based on detected blow events are provided.

US Patent:

20210056378, Feb 25, 2021

Filed:

Aug 23, 2019

Appl. No.:

16/549715

Inventors:

- Mountain View CA, US
Xiaojie Jin - Palo Alto CA, US
Joshua Foster Slocum - San Francisco CA, US
Shengyang Dai - Dublin CA, US
Jiang Wang - Santa Clara CA, US

International Classification:

G06N 3/04
G06N 20/00
G06F 16/901

Abstract:

Methods, and systems, including computer programs encoded on computer storage media for neural network architecture search. A method includes defining a neural network computational cell, the computational cell including a directed graph of nodes representing respective neural network latent representations and edges representing respective operations that transform a respective neural network latent representation; replacing each operation that transforms a respective neural network latent representation with a respective linear combination of candidate operations, where each candidate operation in a respective linear combination has a respective mixing weight that is parameterized by one or more computational cell hyper parameters; iteratively adjusting values of the computational cell hyper parameters and weights to optimize a validation loss function subject to computational resource constraints; and generating a neural network for performing a machine learning task using the defined computational cell and the adjusted values of the computational cell hyper parameters and weights.

US Patent:

20200273078, Aug 27, 2020

Filed:

Feb 27, 2020

Appl. No.:

16/802864

Inventors:

- Mountain View CA, US
Jiang Wang - Santa Clara CA, US
Shengyang Dai - Dublin CA, US

International Classification:

G06Q 30/04
G06N 3/08
G06K 9/00

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for converting unstructured documents to structured key-value pairs. In one aspect, a method comprises: providing an image of a document to a detection model, wherein: the detection model is configured to process the image to generate an output that defines one or more bounding boxes generated for the image; and each bounding box generated for the image is predicted to enclose a key-value pair comprising key textual data and value textual data, wherein the key textual data defines a label that characterizes the value textual data; and for each of the one or more bounding boxes generated for the image: identifying textual data enclosed by the bounding box using an optical character recognition technique; and determining whether the textual data enclosed by the bounding box defines a key-value pair.

US Patent:

20190370633, Dec 5, 2019

Filed:

Aug 19, 2019

Appl. No.:

16/544772

Inventors:

- Sunnyvale CA, US
Wei Xu - Saratoga CA, US
Yi Yang - SAN JOSE CA, US
Jiang Wang - Santa Clara CA, US
Zhiheng Huang - Sunnyvale CA, US

Assignee:

BAIDU USA LLC - Sunnyvale CA

International Classification:

G06N 3/04

Abstract:

Presented herein are embodiments of a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions. In embodiments, it directly models the probability distribution of generating a word given a previous word or words and an image, and image captions are generated according to this distribution. In embodiments, the model comprises two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. In embodiments, these two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of an embodiment of model was validated on four benchmark datasets, and it outperformed the state-of-the-art methods. In embodiments, the m-RNN model may also be applied to retrieval tasks for retrieving images or captions.

US Patent:

20190279030, Sep 12, 2019

Filed:

May 22, 2019

Appl. No.:

16/420154

Inventors:

- Mountain View CA, US
Jiang Wang - Mountain View CA, US
Charles J. Rosenberg - Mountain View CA, US

International Classification:

G06K 9/62
G06F 16/583
G06F 16/51
G06N 20/00
G06K 9/66
G06N 3/04

Abstract:

Methods, systems, and apparatus, for determining fine-grained image similarity. In one aspect, a method includes training an image embedding function on image triplets by selecting image triplets of first, second and third images; generating, by the image embedding function, a first, second and third representations of the features of the first, second and third images; determining, based on the first representation of features and the second representation of features, a first similarity measure for the first image to the second image; determining, based on the first representation of features and the third representation of features, a second similarity measure for the the first image to the third image; determining, based on the first and second similarity measures, a performance measure of the image embedding function for the image triplet; and adjusting the parameter weights of the image embedding function based on the performance measures for the image triplets.