Kai Living Yu

US Patent:

7788264, Aug 31, 2010

Filed:

Oct 10, 2007

Appl. No.:

11/869899

Inventors:

Kai Yu - Cupertino CA, US
Yun Chi - Santa Clara CA, US
Yihong Gong - Saratoga CA, US

Assignee:

NEC Laboratories America, Inc. - Princeton NJ

International Classification:

G06F 17/30

US Classification:

707739, 706 20

Abstract:

Systems and methods for classifying documents each having zero or more links thereto include generating a link matrix; generating a document term matrix; and jointly factorizing the document term matrix and the link matrix.

US Patent:

7870083, Jan 11, 2011

Filed:

Oct 10, 2007

Appl. No.:

11/869886

Inventors:

Kai Yu - Cupertino CA, US
Yihong Gong - Saratoga CA, US

Assignee:

NEC Laboratories America, Inc. - Princeton NJ

International Classification:

G06F 15/18
G06F 15/00

US Classification:

706 12, 705 10, 702 85

Abstract:

Systems and methods are disclosed to predict one or more missing elements from a partially-observed matrix by receiving one or more user item ratings; generating a model parameterized by matrices U, S, V; applying the model to display an item based on one or more predicted missing elements; and applying the model at run-time and determining USV.

US Patent:

8131732, Mar 6, 2012

Filed:

Dec 9, 2008

Appl. No.:

12/331346

Inventors:

Kai Yu - Santa Clara CA, US
Yihong Gong - Saratoga CA, US

Assignee:

NEC Laboratories America, Inc. - Princeton NJ

International Classification:

G06F 7/00
G06F 17/30

US Classification:

707748

Abstract:

A system is disclosed with a collaborative filtering engine to predict an active user's ratings/interests/preferences on a set of new products/items. The predictions are based on an analysis the database containing the historical data of many users' ratings/interests/preferences on a large set of products/items.

US Patent:

8233711, Jul 31, 2012

Filed:

Jun 24, 2010

Appl. No.:

12/822424

Inventors:

Jinjun Wang - San Jose CA, US
Fengjun Lv - San Jose CA, US
Kai Yu - Santa Clara CA, US

Assignee:

NEC Laboratories America, Inc. - Princeton NJ

International Classification:

G06K 9/00

US Classification:

382168, 382224

Abstract:

Systems and methods are disclosed for classifying an input image by detecting one or more feature points on the input image; extracting one or more descriptors from each feature point; applying a codebook to quantize each descriptor and generate code from each descriptor; applying spatial pyramid matching to generate histograms; and concatenating histograms from all sub-regions to generate a final representation of the image for classification.

US Patent:

8345962, Jan 1, 2013

Filed:

Nov 25, 2008

Appl. No.:

12/277504

Inventors:

Kai Yu - Santa Clara CA, US
Wei Xu - Los Gatos CA, US
Yihong Gong - Saratoga CA, US

Assignee:

NEC Laboratories America, Inc. - Princeton NJ

International Classification:

G06K 9/62

US Classification:

382157, 382156, 382158

Abstract:

A method and system for training a neural network of a visual recognition computer system, extracts at least one feature of an image or video frame with a feature extractor; approximates the at least one feature of the image or video frame with an auxiliary output provided in the neural network; and measures a feature difference between the extracted at least one feature of the image or video frame and the approximated at least one feature of the image or video frame with an auxiliary error calculator. A joint learner of the method and system adjusts at least one parameter of the neural network to minimize the measured feature difference.

US Patent:

8374442, Feb 12, 2013

Filed:

May 20, 2009

Appl. No.:

12/469073

Inventors:

Kai Yu - San Jose CA, US
Jianchao Yang - Santa Clara CA, US
Yihong Gong - Saratoga CA, US

Assignee:

NEC Laboratories America, Inc. - Princeton NJ

International Classification:

G06K 9/62
G06K 9/46
G06K 9/48

US Classification:

382224, 382190, 382241

Abstract:

Systems and methods are disclosed to classify an input image by determining a spatial-pyramid image representation based on sparse coding; determining a descriptor for each interest point in the input image; encoding the descriptor; and applying max pooling to form the spatial pyramid representation of images.

US Patent:

8379920, Feb 19, 2013

Filed:

Jan 5, 2011

Appl. No.:

12/985003

Inventors:

Ming Yang - Cupertino CA, US
Kai Yu - Santa Clara CA, US

Assignee:

NEC Laboratories America, Inc. - Princeton NJ

International Classification:

G06K 9/00
G06K 9/34
G06K 9/46

US Classification:

382103, 382115, 382164, 382171, 382173, 382190

Abstract:

Systems and methods are disclosed to recognize clothing from videos by detecting and tracking a human; performing face alignment and occlusal detection; and performing age and gender estimation, skin area extraction, and clothing segmentation to a linear support vector machine (SVM) to recognize clothing worn by the human.

US Patent:

8447119, May 21, 2013

Filed:

Jun 18, 2010

Appl. No.:

12/818156

Inventors:

Kai Yu - Santa Clara CA, US

Assignee:

NEC Laboratories America, Inc. - Princeton NJ

International Classification:

G06K 9/62

US Classification:

382224

Abstract:

Methods and systems are disclosed for image classification coding an image by nonlinearly mapping an image descriptor to form a high-dimensional sparse vector; spatially pooling each local region to form an image-level feature vector using a probability kernel incorporating a similarity metric of local descriptors; and classifying the image.