Jie Li

7860870, Dec 28, 2010

May 31, 2007

11/755972

Narayanan Sadagopan - Fremont CA, US
Jie Li - Stanford CA, US

Yahoo! Inc. - Sunnyvale CA

G06F 17/30

707748, 707758

The present invention provides for the detection of abnormal user behavior for a query session of an electronic search engine. A query session is initiated upon receipt of a user search request that includes one or more search terms. The search engine, in accordance with known search technology, generates a search results page that includes various hyperlinks, including for example web content hyperlinks, page navigation hyperlinks and advertising hyperlinks. Tracking user activities generates the clickstream associated with the search results page. The present invention determines a probability score for the clickstream and then this score is normalized. A comparison of the normalized probability score with other normalized probability scores for similar query sessions determines of the normalcy of the query session.

8170838, May 1, 2012

Apr 27, 2009

12/430805

Silvio J. Rabello - Palo Alto CA, US
William A. McGahan - Spicewood TX, US
Jie Li - Milpitas CA, US

Nanometrics Incorporated - Milpitas CA

H03F 1/26
G06F 15/00

702189, 359237, 372 24, 600409, 702 27, 702127

The process of modeling a complex two-dimensional periodic structure is improved by selectively truncating the Fourier expansion used in the calculation of resulting scatter signature from the model. The Fourier expansion is selectively truncated by determining the contribution for each harmonic order in the Fourier transform of the permittivity function and retaining the harmonic orders with a contribution that is above a threshold. The Fourier space may be compressed so that only the selected harmonic orders are used, thereby reducing the required memory and calculation times. The compressed Fourier space may be used in a real-time analysis of a sample or to generate a library that is used in the analysis of a sample.

8525993, Sep 3, 2013

Jan 29, 2010

12/696974

Silvio J. Rabello - Palo Alto CA, US
William A. McGahan - Spicewood TX, US
Jie Li - Milpitas CA, US
Yongdong Liu - Cupertino CA, US

Nanometrics Incorporated - Milpitas CA

G01J 4/00

356368, 356369

Asymmetry metrology is performed using at least a portion of Mueller matrix elements, including, e. g. , the off-diagonal elements of the Mueller matrix. The Mueller matrix may be generated using, e. g. , a spectroscopic or angle resolved ellipsometer that may include a rotating compensator. The Mueller matrix is analyzed by fitting at least a portion of the elements to Mueller matrix elements calculated using a rigorous electromagnetic model of the sample or by fitting the off-diagonal elements to a calibrated linear response. The use of the Mueller matrix elements in the asymmetry measurement permits, e. g. , overlay analysis using in-chip devices thereby avoiding the need for special off-chip targets.

20220309695, Sep 29, 2022

Mar 25, 2021

17/212325

- Los Altos CA, US
Rares A. Ambrus - San Francisco CA, US
Adrien David Gaidon - Mountain View CA, US
Jie Li - Los Altos CA, US

G06T 7/571
G06T 15/20
G06T 15/40
G06T 3/00

Systems and methods described herein relate to training a machine-learning-based monocular depth estimator. One embodiment selects a virtual image in a virtual dataset, the virtual dataset including a plurality of computer-generated virtual images; generates, from the virtual image in accordance with virtual-camera intrinsics, a point cloud in three-dimensional space based on ground-truth depth information associated with the virtual image; reprojects the point cloud back to two-dimensional image space in accordance with real-world camera intrinsics to generate a transformed virtual image; and trains the machine-learning-based monocular depth estimator, at least in part, using the transformed virtual image.

20220300746, Sep 22, 2022

May 25, 2021

17/329922

- Los Altos CA, US
Rares A. Ambrus - San Francisco CA, US
Vitor Guizilini - Santa Clara CA, US
Jie Li - Los Altos CA, US
Adrien David Gaidon - Mountain View CA, US

G06K 9/00
G06K 9/62
G01S 17/931

Described are systems and methods for self-learned label refinement of a training set. In on example, a system includes a processor and a memory having a training set generation module that causes the processor to train a model using an image as an input to the model and 2D bounding based on 3D bounding boxes as ground truths, select a first subset from predicted 2D bounding boxes previously outputted by the model, retrain the model using the image as the input and the first subset as ground truths, select a second set of predicted 2D bounding boxes previously outputted by the model, and generate the training set by selecting the 3D bounding boxes from a master set of 3D bounding boxes that have corresponding 2D bounding boxes that form the second subset.

20220300768, Sep 22, 2022

Jun 25, 2021

17/358497

- Los Altos CA, US
Dennis Park - Fremont CA, US
Vitor Guizilini - Santa Clara CA, US
Jie Li - Los Altos CA, US
Adrien David Gaidon - Mountain View CA, US

G06K 9/62
G06T 7/11
G06T 7/50
G06K 9/00
G06K 9/46
G01S 17/89
G01S 17/42
G06N 3/08
G06N 3/04

System, methods, and other embodiments described herein relate to evaluating a perception network in relation to the accuracy of depth estimates and object detections. In one embodiment, a method includes segmenting range data associated with an image according to bounding boxes of objects identified in the image to produce masked data. The method includes comparing the masked data with corresponding depth estimates in the depth map according to an evaluation mask that correlates the depth estimates with the depth map. The method includes providing a metric that quantifies the comparing to assess a network that generated the depth map and the bounding boxes.

20220301202, Sep 22, 2022

May 28, 2021

17/333537

- Los Altos CA, US
Rares A. Ambrus - San Francisco CA, US
Vitor Guizilini - Santa Clara CA, US
Jie Li - Los Altos CA, US
Adrien David Gaidon - Mountain View CA, US

G06T 7/50
G06N 3/08

System, methods, and other embodiments described herein relate to performing depth estimation and object detection using a common network architecture. In one embodiment, a method includes generating, using a backbone of a combined network, a feature map at multiple scales from an input image. The method includes decoding, using a top-down pathway of the combined network, the feature map to provide features at the multiple scales. The method includes generating, using a head of the combined network, a depth map from the features for a scene depicted in the input image, and bounding boxes identifying objects in the input image.

20220301203, Sep 22, 2022

Jul 23, 2021

17/384121

- Los Altos CA, US
Dennis Park - Fremont CA, US
Vitor Guizilini - Santa Clara CA, US
Jie Li - Los Altos CA, US
Adrien David Gaidon - Mountain View CA, US

G06T 7/50
G06T 7/10
G06K 9/00
G06K 9/62
G06N 20/00

System, methods, and other embodiments described herein relate to a manner of training a depth prediction system using bounding boxes. In one embodiment, a method includes segmenting an image to mask areas beyond bounding boxes and identify unmasked areas within the bounding boxes. The method also includes training a depth model using depth losses from comparing weighted points associated with pixels of the image within the unmasked areas to ground-truth depth. The method also includes providing the depth model for object detection.