Other

Leland Stanford Junior University

Microsoft Technology Licensing, LLC

Google Inc.

Jia H Deng

Fei-Fei Li

Jonathan Krause

Alexander C Berg

Hartwig Adam

Yuan Hang Li

Michael Isard

Qifa Ke

Simon John Baker

Nan Ding

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying objects in images. One of the methods includes obtaining data identifying a plurality of object categories; obtaining relationship data for the plurality of object categories; determining a plurality of valid assignments from the relationship data; obtaining, for an image, a respective raw image score for each of the object categories, wherein the raw image score for each of the object categories represents an estimate of a likelihood that the image includes an image of an object that belongs to the object category; and generating a respective final score for each of the object categories from the raw image scores using the valid assignments, wherein the final score for each of the object categories represents the likelihood that the image includes an image of an object that belongs to the object category.

Identifying objects in images

As visual recognition scales up to ever larger numbers of categories, maintaining high accuracy is increasingly difficult. Embodiment of the present invention include methods for optimizing accuracy-specificity trade-offs in large scale recognition where object categories form a semantic hierarchy consisting of many levels of abstraction.

Method and system for optimizing accuracy-specificity trade-offs in large scale visual recognition

A PAR-type light bulb includes an LED lacking a phosphor coating, the LED covered by a lens having a phosphor coating, and a base comprising reverse threads.

LED PAR and R lamps

Image search results are obtained by providing weights to visual features to emphasize features corresponding to objects of interest while simultaneously deemphasizing irrelevant or inconsistent features that lead to poor search results. In order to minimize the impact of visual features that are unreliable or irrelevant with respect to the objects of interest in the image, context-dependent weights are provided to detect visual features such that those visual features pertaining to the objects of interest are more heavily weighted than those visual features that pertain to irrelevant or unreliable portions of the image. Visual features may be weighted for images in a searchable database. Training data may be obtained and used in weighting visual features in a query image and, alternatively, in searchable database images.

Image retrieval using discriminative visual features

A lighting apparatus includes a primary lighting source powered by from a facility A-C power source, and backup LED lighting source powered by batteries.

LED emergency light

A light bulb includes an A/C driven LED lacking a phosphor coating, the LED covered by a lens having a phosphor coating.

A/C LED bulb

A detachable ballast housing for use with fluorescent lights includes a ballast, a housing for the ballast, and electrical contacts for detachably mounting and dismounting to a lighting fixture without connecting or disconnecting power wires.

Detachable ballast housing

A lamp bar may include and/or involve multiple LED light sources linearly arranged along a length of the lamp bar.

Growing community of inventors

Diamond Bar, CA, United States of America

Jia H Deng