Dong Wang

US Patent:

20110035259, Feb 10, 2011

Filed:

Aug 7, 2009

Appl. No.:

12/537429

Inventors:

Shirshanka Das - Santa Clara CA, US
Bhaskar Ghosh - Palo Alto CA, US
Dong Wang - Saratoga CA, US

Assignee:

Yahoo! Inc. - Sunnyvale CA

International Classification:

G06Q 10/00
G06Q 30/00

US Classification:

705 10

Abstract:

A modeling system to evaluate cost-based viability of a real-time, auction-based advertising system with third-party integration includes an exchange server configured to receive advertising bids, create bid requests to third-party entities based thereon, and select a winning bid from responses to the requests. A computer, coupled with the exchange server: computes a plurality of valid paths from publishers to and from the third-party entities through the exchange server; estimates server and network costs, including fixed hardware costs and variable operational costs, amortized over a predetermined period of time, based on a number of average queries per second (QPS) transmitted at different portions of the valid paths; compares current periodic fees paid by the third-party entities to the amortized costs, to determine cost-based system viability; and determines updates, if needed, to the periodic fees based on the plurality of costs to maintain cost-based system viability.

US Patent:

20220270364, Aug 25, 2022

Filed:

Feb 9, 2022

Appl. No.:

17/667758

Inventors:

- Palo Alto CA, US
Dong Wang - San Jose CA, US
Deepak Menghani - Mountain View CA, US
John Goddard - Mountain View CA, US
Ryan Tobin - Sacramento CA, US

International Classification:

G06V 20/40
G06K 9/62
G11B 27/34
G11B 27/36
G06F 16/74
G06F 16/783
G06F 16/2457
G06F 3/00
G06F 16/738

Abstract:

Described herein are systems and methods that search videos and other media content to identify items, objects, faces, or other entities within the media content. Detectors identify objects within media content by, for instance, detecting a predetermined set of visual features corresponding to the objects. Detectors configured to identify an object can be trained using a machine learned model (e.g., a convolutional neural network) as applied to a set of example media content items that include the object. The systems provide user interfaces that allow users to review search results, pinpoint relevant portions of media content items where the identified objects are determined to be present, review detector performance and retrain detectors, providing search result feedback, and/or reviewing video monitoring results and analytics.

US Patent:

20220261128, Aug 18, 2022

Filed:

May 7, 2022

Appl. No.:

17/739077

Inventors:

- Palo Alto CA, US
Dong Wang - San Jose CA, US
Deepak Menghani - Mountain View CA, US
John Goddard - Mountain View CA, US
Ryan Tobin - Sacramento CA, US

International Classification:

G06F 3/0484
G06V 20/40

Abstract:

Described herein are systems and methods that search videos and other media content to identify items, objects, faces, or other entities within the media content. Detectors identify objects within media content by, for instance, detecting a predetermined set of visual features corresponding to the objects. Detectors configured to identify an object can be trained using a machine learned model (e.g., a convolutional neural network) as applied to a set of example media content items that include the object. The systems provide user interfaces that allow users to review search results, pinpoint relevant portions of media content items where the identified objects are determined to be present, review detector performance and retrain detectors, providing search result feedback, and/or reviewing video monitoring results and analytics.

US Patent:

20210303863, Sep 30, 2021

Filed:

Jun 12, 2021

Appl. No.:

17/346202

Inventors:

- Palo Alto CA, US
Dong Wang - San Jose CA, US
Deepak Menghani - Mountain View CA, US
John Goddard - Mountain View CA, US
Ryan Tobin - Sacramento CA, US

International Classification:

G06K 9/00
G06K 9/62
G11B 27/34
G11B 27/36
G06F 16/74
G06F 16/783
G06F 16/2457
G06F 3/00
G06F 16/738

Abstract:

Described herein are systems and methods that search videos and other media content to identify items, objects, faces, or other entities within the media content. Detectors identify objects within media content by, for instance, detecting a predetermined set of visual features corresponding to the objects. Detectors configured to identify an object can be trained using a machine learned model (e.g., a convolutional neural network) as applied to a set of example media content items that include the object. The systems provide user interfaces that allow users to review search results, pinpoint relevant portions of media content items where the identified objects are determined to be present, review detector performance and retrain detectors, providing search result feedback, and/or reviewing video monitoring results and analytics.

US Patent:

20210220489, Jul 22, 2021

Filed:

Jan 13, 2021

Appl. No.:

17/148377

Inventors:

- Stanford CA, US
Mark Schnitzer - Redwood City CA, US
Benjamin Grewe - Zurich, CH
Dong Wang - Palo Alto CA, US
Biafra Ahanonu - San Francisco CA, US
Gregory Corder - Philadelphia PA, US

International Classification:

A61K 49/00
A61K 9/00
C07K 16/28
C12N 15/113

Abstract:

An ensemble of neurons in the basolateral amygdala (BLA) has been identified that encodes nociceptive information across pain modalities, including pain evoked by noxious thermal and mechanical stimuli. Methods are provided for screening candidate agents for inhibition of neural activity of the BLA nociceptive ensemble. Screening assays further include determining the effectiveness of candidate agents in alleviating pain and reducing aversive pain avoidance behavior.

US Patent:

20210157845, May 27, 2021

Filed:

Nov 27, 2019

Appl. No.:

16/697948

Inventors:

- Seattle WA, US
Zhiheng HUANG - Santa Clara CA, US
Xiaofei MA - New York NY, US
Ramesh M. NALLAPATI - New Canaan CT, US
Krishnakumar RAJAGOPALAN - Edison NJ, US
Milan SAINI - West New York NJ, US
Sudipta SENGUPTA - Sammamish WA, US
Saurabh Kumar SINGH - Seattle WA, US
Dimitrios SOULIOS - Seattle WA, US
Ankit SULTANIA - Seattle WA, US
Dong WANG - New York NY, US
Zhiguo WANG - Great Neck NY, US
Bing XIANG - Mount Kisco NY, US
Peng XU - Sunnyvale CA, US
Yong YUAN - Mercer Island WA, US

International Classification:

G06F 16/901
G06F 16/903
G06F 16/2457
G06N 3/04

Abstract:

Techniques for searching documents are described. An exemplary method includes receiving a document search query; querying at least one index based upon the document search query to identify matching data; fetching the identified matched data; determining one or more of a top ranked passage and top ranked documents from the set of documents based upon one or more invocations of one or more machine learning models based at least on the fetched identified matched data and the document search query; and returning one or more of the top ranked passage and the proper subset of documents.

US Patent:

20200364263, Nov 19, 2020

Filed:

Aug 1, 2020

Appl. No.:

16/945805

Inventors:

- Palo Alto CA, US
Dong Wang - San Jose CA, US
Deepak Menghani - Mountain View CA, US
John Goddard - Palo Alto CA, US
Ryan Tobin - Sacramento CA, US

International Classification:

G06F 16/783
G11B 27/34
G06F 16/738
G06F 16/74
G06K 9/00
G06F 3/0484

Abstract:

Described herein are systems and methods that search videos and other media content to identify items, objects, faces, or other entities within the media content. Detectors identify objects within media content by, for instance, detecting a predetermined set of visual features corresponding to the objects. Detectors configured to identify an object can be trained using a machine learned model (e.g., a convolutional neural network) as applied to a set of example media content items that include the object. The systems provide user interfaces that allow users to review search results, pinpoint relevant portions of media content items where the identified objects are determined to be present, review detector performance and retrain detectors, providing search result feedback, and/or reviewing video monitoring results and analytics.

US Patent:

20200242364, Jul 30, 2020

Filed:

Apr 15, 2020

Appl. No.:

16/848843

Inventors:

- Palo Alto CA, US
Dong Wang - San Jose CA, US
Deepak Menghani - Mountain View CA, US
John Goddard - Mountain View CA, US
Ryan Tobin - Sacramento CA, US

International Classification:

G06K 9/00
G11B 27/36
G06F 16/74
G06F 3/00
G06F 16/2457
G06K 9/62
G11B 27/34
G06F 16/783

Abstract:

Described herein are systems and methods that search videos and other media content to identify items, objects, faces, or other entities within the media content. Detectors identify objects within media content by, for instance, detecting a predetermined set of visual features corresponding to the objects. Detectors configured to identify an object can be trained using a machine learned model (e.g., a convolutional neural network) as applied to a set of example media content items that include the object. The systems provide user interfaces that allow users to review search results, pinpoint relevant portions of media content items where the identified objects are determined to be present, review detector performance and retrain detectors, providing search result feedback, and/or reviewing video monitoring results and analytics.