Xin Yu, 52620 Iris Ave UNIT 305, Sunnyvale, CA 94086

2012014, Jun 7, 2012

Dec 7, 2010

12/962627

Jianwen Wang - San Jose CA, US
Runfang Zhou - Sunnyvale CA, US
Xin Yu - Palo Alto CA, US
Zhaowei Jiang - Palo Alto CA, US
Howard Cooperstein - Santa Clara CA, US
Andy Sze-Chai Chan - Fremont CA, US
Pierre Aoun - Los Altos CA, US
Aparna Thyagarajan - Fremont CA, US

Microsoft Corporation - Redmond WA

H04H 60/33

725 13

A technology is described for ranking content using user feedback. A method can include presenting a content entry to a plurality of users to enable viewing of the content entry. Positive and negative ratings can be captured about the content entry from the plurality of users. A relative deviation value can be calculated using the positive ratings and negative ratings for the content entry to form a raw rating score using a processor. Another operation can be scaling the raw rating score via a power function to form a controversial rating score using a processor. The content entry may then be displayed in a ranked order with other content entries based on the controversial rating score.

2021024, Aug 12, 2021

Jun 13, 2019

15/733778

- Erlangen, DE
Ahmet Tuysuzoglu - Jersey City NJ, US
Bin Lou - Princeton NJ, US
Bibo Shi - Monmouth Junction NJ, US
Nicolas Von Roden - St Gallen, CH
Kareem Abdelrahman - Giza, EG
Berthold Kiefer - Erlangen, DE
Robert Grimm - Nürnberg, DE
Heinrich von Busch - Uttenreuth, DE
Mamadou Diallo - Plainsboro NJ, US
Tongbai Meng - Ellicott City MD, US
Dorin Comaniciu - Princeton Junction NJ, US
David Jean Winkel - Basel, CH
Xin Yu - Nashville TN, US

G06T 7/00
G06K 9/62
G06N 20/00
G06T 7/11

Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.

2021003, Feb 4, 2021

Oct 19, 2020

17/074366

- Shenzhen, CN
Xin Yu - Santa Clara CA, US

G06Q 30/02

According to one aspect of the present disclosure, there is provided a method, by an advertiser directory service, that includes: receiving search criteria comprising one or more searching keywords, a performance threshold, and media information; identifying a category node in a tree structure according to the searching keywords and the performance threshold, the category node comprising a plurality of advertiser nodes; selecting a subset of the advertiser nodes according to the media information and the performance threshold; and recommending a publisher bid on the subset of the advertiser nodes.

2019013, May 2, 2019

Oct 26, 2017

15/795193

- Plano TX, US
Xin YU - Santa Clara CA, US

Futurewei Technologies, Inc. - Plano TX

H04N 21/858
H04N 21/44
H04N 21/84

Embodiments provide methods and devices for providing object information associated with a media program. Embodiments include identifying an object of interest in an image of a frame of the media program; inserting an indicator into the image of the frame to identify the object of interest; generating a video clip associated with the identified object based on a portion of the media program; constructing an information page containing information regarding the object of interest, wherein the information page comprises a window for displaying the video clip; and transmitting the information page, including the video clip, to the user device.