Bin K Zhu

US Patent:

8315964, Nov 20, 2012

Filed:

Oct 27, 2008

Appl. No.:

12/258991

Inventors:

Shipeng Li - Palo Alto CA, US
Yang Yang - Hefei, CN
Bin Benjamin Zhu - Edina MN, US
Rui Guo - Beijing, CN
Linjun Yang - Beijing, CN

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06N 5/00

US Classification:

706 46, 706 45

Abstract:

Technologies for a human computation framework suitable for answering common sense questions that are difficult for computers to answer but easy for humans to answer. The technologies support solving general common sense problems without a priori knowledge of the problems; support for determining whether an answer is from a bot or human so as to screen out spurious answers from bots; support for distilling answers collected from human users to ensure high quality solutions to the questions asked; and support for preventing malicious elements in or out of the system from attacking other system elements or contaminating the solutions produced by the system, and preventing users from being compensated without contributing answers.

US Patent:

20130060726, Mar 7, 2013

Filed:

Nov 1, 2012

Appl. No.:

13/666814

Inventors:

Shipeng Li - Palo Alto CA, US
Yang Yang - Hefei, CN
Bin Benjamin Zhu - Edina MN, US
Rui Guo - Beijing, CN
Linjun Yang - Beijing, CN

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06N 5/02

US Classification:

706 46

Abstract:

Technologies for a human computation framework suitable for answering common sense questions that are difficult for computers to answer but easy for humans to answer. The technologies support solving general common sense problems without a priori knowledge of the problems; support for determining whether an answer is from a bot or human so as to screen out spurious answers from bots; support for distilling answers collected from human users to ensure high quality solutions to the questions asked; and support for preventing malicious elements in or out of the system from attacking other system elements or contaminating the solutions produced by the system, and preventing users from being compensated without contributing answers.

US Patent:

20220417496, Dec 29, 2022

Filed:

Jun 25, 2021

Appl. No.:

17/358797

Inventors:

- Palo Alto CA, US
Xiang Li - Saratoga CA, US
Bin Zhu - San Jose CA, US
Shan Liu - San Jose CA, US

Assignee:

Tencent America LLC - Palo Alto CA

International Classification:

H04N 19/105
H04N 19/159
H04N 19/70
H04N 19/176

Abstract:

Aspects of the disclosure include methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. An apparatus includes processing circuitry that decodes prediction information of a current block in a coded video bitstream. The prediction information comprises at least one reference picture index used in low delay inter bi-prediction for the current block. Each of the at least one reference picture index has a same value. The processing circuitry determines a first reference picture in a first reference picture list and a second reference picture in a second reference picture list based on the at least one reference picture index. The current block is coded using the low delay inter bi-prediction. The first reference picture list is identical to the second reference picture list. The first reference picture is identical to the second reference picture. The processing circuitry reconstructs the current block based on the first and second reference pictures.

US Patent:

20220312039, Sep 29, 2022

Filed:

Oct 12, 2021

Appl. No.:

17/499700

Inventors:

- Palo Alto CA, US
Xiang LI - Saratoga CA, US
Bin ZHU - Palo Alto CA, US
Soo-Chul HAN - Palo Alto CA, US
Shan LIU - San Jose CA, US

Assignee:

TENCENT AMERICA LLC - Palo Alto CA

International Classification:

H04N 19/70
H04N 19/46
H04N 19/169
H04N 19/174

Abstract:

A method of video processing by a video processor includes receiving a first syntax element in a coded video bitstream. The first syntax element can be a high level syntax element and indicate whether a height of each of a plurality of pictures in a video sequence of the coded video bitstream is equal to or larger than a width of the respective picture in the video sequence of the coded video bitstream. The pictures in the video sequence of the coded video can be processed in an orientation that is determined according to the first syntax element indicating whether the height of each of the pluralty of pictures in the video sequence of the coded video is guaranteed to be equal to or larger than the width of the respective picture in the video sequence.

US Patent:

20220224948, Jul 14, 2022

Filed:

Mar 29, 2022

Appl. No.:

17/707901

Inventors:

- Palo Alto CA, US
Bin ZHU - San Jose CA, US
Xiaozhong XU - State College PA, US
Xiang LI - Saratoga CA, US
Shan LIU - San Jose CA, US

Assignee:

TENCENT AMERICA LLC - Palo Alto CA

International Classification:

H04N 19/96
H04N 19/176
H04N 19/174
H04N 19/436

Abstract:

Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes receiving circuitry and processing circuitry. The processing circuitry receives coded information of a block that is encoded in a palette based coding mode. The block is a beginning of a predefined coding region that includes one or more coding tree units (CTUs). The processing circuitry further determines a palette for the block independently of palette information of one or more previously decoded blocks of the palette based coding mode, and decodes pixels of the block based on the coded information of the block and the determined palette for the block.

US Patent:

20210044836, Feb 11, 2021

Filed:

Jul 28, 2020

Appl. No.:

16/940842

Inventors:

- Palo Alto CA, US
Bin ZHU - San Jose CA, US
Xiaozhong XU - State College PA, US
Xiang LI - Saratoga CA, US
Shan LIU - San Jose CA, US

Assignee:

Tencent America LLC - Palo Alto CA

International Classification:

H04N 19/96
H04N 19/436
H04N 19/174
H04N 19/176

Abstract:

Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes receiving circuitry and processing circuitry. The processing circuitry receives coded information of a block that is encoded in a palette based coding mode. The block is a beginning of a predefined coding region that includes one or more coding tree units (CTUs). The processing circuitry further determines a palette for the block independently of palette information of one or more previously decoded blocks of the palette based coding mode, and decodes pixels of the block based on the coded information of the block and the determined palette for the block.

US Patent:

20190132591, May 2, 2019

Filed:

Oct 26, 2017

Appl. No.:

15/794938

Inventors:

- Santa Clara CA, US
Bin Zhu - San Jose CA, US
Sang-Hee Lee - San Jose CA, US
Qing Li - El Dorado Hills CA, US

International Classification:

H04N 19/124
H04N 19/167
H04N 19/59
H04N 19/184
G06N 3/10
G06N 3/04

Abstract:

Techniques related to quantization parameter estimation for video coding are discussed. Such techniques may include generating features using a picture of input video received for encoding and applying a neural network to a feature vector including the features, a target bitrate, and a resolution of the picture to generate an estimated quantization parameter for encoding the picture.