Hewlett-packard Development Company, L.p.

Agilent Technologies, Inc.

Jds Uniphase Corporation

Keysight Technologies, Inc.

Jerry J Liu

Georgia Koutrika

Glen L Purdy, Jr

Lei Liu

Jian Fan

Glenn R Engel

Shanchan Wu

Yuhong Xiong

Thomas M Snyder

Steven J Simske

Suk Hwan Lim

Lance A Tatman

Samson J Liu

Ping Luo

Eamonn O'Brien-Strain

Clayton Atkins

Yang Lei

Parag Mulendra Joshi

Rares Vernica

Tong Zhang

Peter G Hwang

Qian Lin

Niranjan Damera-Venkata

John C Eidson

Jogesh Warrior

Nina Bhatti

Jefferson B Burch

Sam Liu

Jian-Ming Jin

Hui-Man Hou

Seungyon Lee

Sheng-Wen Yang

Li-Mei Jiao

Jeff Burch

Li-Wei Zheng

Mutsuya Ii

Glen R Engel

Bruce Hamilson

John Cavanaugh

Ruiting Shao

Cong-Lei Yao

Terence C Ngai

Hector A Lopez

A deep learning method employs a neural network having three sub-nets to classify and retrieve the most similar 3D model of an object, given a rough 3D model or scanned images. The most similar 3D model is present in a database and can be retrieved to use directly or as a reference to redesign the 3D model. The three sub-nets of the neural network include one dealing with object images and the other two dealing with voxel representations. Majority vote is used instead of view pooling to classify the object. A feature map and a list of top N most similar well-designed 3D models are also provided.

Three-dimensional shape classification and retrieval using convolutional neural networks and majority vote

Examples associated with reading difficulty level based resource recommendation are disclosed. One example may involve instructions stored on a computer readable medium. The instructions, when executed on a computer, may cause the computer to obtain a set of candidate resources related to a source document. The candidate resources may be obtained based on content extracted from the source document. The instructions may also cause the computer to identify reading difficulty levels of members of the set of candidate resources. The instructions may also cause the computer to recommend a selected candidate resource to a user. The selected candidate resource may be recommended based on subject matter similarity between the selected candidate resource and the source document. The selected candidate resource may also be recommended based on reading difficulty level similarity between the selected candidate resource and the source document.

Reading difficulty level based resource recommendation

A method of recognizing an object includes comparing a three-dimensional point cloud of the object to a three-dimensional candidate from a dataset to determine a first confidence score, and comparing color metrics of a two-dimensional image of the object to a two-dimensional candidate from the dataset to determine a second confidence score. The point cloud includes a color appearance calibrated from a white balance image, and the color appearance of the object is compared with the three-dimensional candidate. The first or second confidence score is selected to determine which of the three-dimensional candidate or the two-dimensional candidate corresponds with the object.

Object recognition

A learning graph is generated for documents according to a sequencing approach. The learning graph includes nodes corresponding to the documents and edges. Each edge connects two of the nodes and indicates a sequencing relationship between two of the documents to which the two of the nodes correspond that specifies an order in which the two of the documents are to be reviewed in satisfaction of the learning goal. The learning graph is a directed graph specifying a learning path through the documents to achieve a learning goal in relation to a subject.

Learning graph

Examples disclosed herein relate to web page output selection. A processor may determine the features of a section of a web page and assign a weight to each of the features respectively. The processor may determine a score for the section based on the weights of the features and determine to output the section based on the score.

Web page output selection

Examples relate to grouping students using content fields. Student data including a plurality of content fields is obtained. Each content field of the plurality of content fields includes a value that represents an unstructured marking linked to a content data collection. Student profiles are generated by assigning a student identification number to each of the plurality of content fields. Each of the student identification numbers are organized into at least one student group by analyzing the set of student profiles.

Group analysis using content data

Automated content selection is disclosed. An example method includes generating a plurality of rankings for each document in a set of input documents, each ranking based on separate interesting document properties. The method also includes selecting a subset of the set of input documents, wherein each document selected for the subset is based on rankings of the selected document. The method also includes determining interesting properties of the subset. The method also includes selecting a subset with respect to parameters being optimized. The method also includes outputting a composition including the documents in the subset.

Automated content selection

Systems and methods associated with external resource identification are disclosed. One example method may be embodied on a non-transitory computer-readable medium storing computer-executable instructions. The instructions, when executed by a computer may cause the computer to perform the method. The method includes classifying a segment of a document into a member of a set of topics discussed within the document. The method also includes identifying, based on the structure of the segment and keywords from the segment, information that a reader of the document could seek upon reading the segment. The method also includes obtaining, based on the member of the set of topics, a set of candidate external resources that potentially contain the information. The method also includes presenting, in response to a user interaction with the document, a member of the set of candidate external resources identified as being likely to contain the information.

External resource identification

Examples disclosed herein relate to selecting an image based on text topic and image explanatory value. In one implementation, a processor selects an image to associate with a text based on a criteria indicating the explanatory value of a context information related to the image in relation to the topic of the text. The processor may output the selected image.

Image selection based on text topic and image explanatory value

Examples herein disclose capturing an image of printed text and a handwritten annotation and determining a topic as related to the printed text in the captured image. The examples disclose identifying a resource based on the handwritten annotation.

Identifying a resource based on a handwritten annotation

Examples herein disclose obtaining regions of digital content and determining a correlation measurement between the multiple regions of digital content adjacently located to each other. The examples disclose identifying a breakpoint in the digital content based on the determined correlation measurement.

Identification of a breakpoint based on a correlation measurement

A device including a processor and a memory communicatively coupled to the processor is provided. The memory stores instructions causing the processor, after execution of the instructions by the processor, to: display a reference page number with each displayed page of a digital document having reference page numbers, the digital document corresponding to a reference document having page numbers that correspond to the reference page numbers; and display a fractional page number with each displayed page of the digital document, each fractional page number corresponding to a portion of a page of the reference document.

Digital document including reference page numbers and fractional page numbers

A media table can be created by searching a digital document to identify media content within the digital document in a format associated with a client device and creating a media table containing a view of each of the identified media content.

Media table for a digital document

Examples associated with keyframe annotation are disclosed. One example includes extracting a set of keyframes from a video presentation. A subset of the keyframes is selected to present to a user based on a user preference. Annotations are generated for the subset of the keyframes. The annotations are personalized to the user. The subset of the keyframes and the annotations are presented to the user.

Keyframe annotation

Examples of the present disclosure may include methods, systems, and computer readable media with executable instructions. An example method for determining document structure similarity can include segmenting path sequences () of Document Object Model (DOM) trees () from a number of web pages () into B components (). Path signals () corresponding to the path sequences () are determined based on a count of the occurrences of particular paths in the Bcomponent (), and unique path signals () are transformed into discrete wavelet signals ()(). The discrete wavelet signals () are analyzed at multiple DOM tree resolution levels ().

Discrete wavelet transform method for document structure similarity

Growing community of inventors

Sunnyvale, CA, United States of America

Jerry J Liu