Fuji Xerox Co., Ltd.

Xerox Corporation

Fujifilm Business Innovation Corp.

Palo Alto Research Center Inc.

Francine R Chen

Yin-Ying Chen

Patrick Chiu

Lynn D Wilcox

Jian Zhao

Scott Carter

Thorsten Brants

Dhiraj Joshi

Dan S Bloomberg

Matthew L Cooper

Ayman Farahat

Qiong Liu

Donald G Kimber

John E Adcock

Daniel Carl Brotsky

Eytan Adar

Hinrich H Schuetze

Yanxia Zhang

Lada A Adamic

Annie E Zaenen

Hao Hu

Steven B Putz

Philip Andrew Chou

Peter L T Pirolli

Laurent Denoue

Ullas Gargi

Andreas Girgensohn

David Ayman Shamma

James Edward Pitkow

Ed H Chi

Karon A Weber

Daniel Avrahami

Lyndon Kennedy

Jan O Pedersen

Jayant Kumar

John W Tukey

Alex D Poon

Julian M Kupiec

Jun Li

Tao Yang

Ioannis Tsochantaridis

Geoffrey D Nunberg

Bokai Cao

Yanjun Zhu

Vijay Balasubramanian

Charles R Mathis

Bor-Chun Chen

Anthony Dunnigan

David Michael Hilbert

Chelhwon Kim

Paula S Newman

Eric Gaussier

Thomas Hofmann

Jennifer Marlow

Ashok Chhabedia Popat

Chunyuan Liao

Shigeyuki Sakaki

Hajime Ueno

Yulius Tjahjadi

Hiroshi Sakaida

Leslie T Niles

Yijuan Lu

Mandy Barrett Korpusik

Cheng Zhang

Dhjraj Joshi

Jyun-Yu Jiang

Heike Adel

Philipp Daniel Harzig

Abhinav Gupta

Sanjeev Kumar Karn

Trista Pei-chun Chen

Bee-Yian Liew

Takanori Fujiwara

Ray Yuan

Peter L Pirolli

Thorsten H Brants

Ashok C Popat

A computer-implemented method of learning sensory media association includes receiving a first type of nontext input and a second type of nontext input; encoding and decoding the first type of nontext input using a first autoencoder having a first convolutional neural network, and the second type of nontext input using a second autoencoder having a second convolutional neural network; bridging first autoencoder representations and second autoencoder representations by a deep neural network that learns mappings between the first autoencoder representations associated with a first modality and the second autoencoder representations associated with a second modality; and based on the encoding, decoding, and the bridging, generating a first type of nontext output and a second type of nontext output based on the first type of nontext input or the second type of nontext input in either the first modality or the second modality.

System and method for learning sensory media association without using text labels

A method and system for analyzing a target network relative to a background network of data using machine learning. The method includes extracting a first feature matrix from an adjacency matrix representative of the target network, extracting a second feature matrix from an adjacency matrix representative of the background network, generating a projection matrix based on the first and second feature matrices using a contrastive learning algorithm, generating a first contrastive matrix representation of the target network based on the projection matrix and the first feature matrix, generating a second contrastive matrix representation of the background network based on the projection matrix and the second feature matrix, and displaying a visualization of unique features of the target network relative to the background network based on the first contrastive matrix and the second contrastive matrix.

System and method for contrastive network analysis and visualization

A method and system for classifying image features using a neural network is provided. The method includes training the neural network using triplet loss processes including receiving an anchor image, selecting a positive image and a negative image, generating a image embedding associated with each of the anchor image, the positive image, and the negative image, classifying image features extracted from the anchor image based on the image embedding of the anchor image, determining an image label location associated with the classified image features, extracting features associated with the determined image label location, and classifying the features associated with the determined image label location; and combining the multi-label loss with localized image classification loss and the triplet loss using a weighted loss sum.

System and method for identification and localization of images using triplet loss and predicted regions

A computer-implemented method, comprising, extracting a video sequence, the video sequence including a series of video frames, estimating current poses of one or more subjects within each video frame and determining joint locations for a joint associated with the one or more subjects within each video frame, computing optical flows from the video sequence, extracting motion features from the video sequence based on the optical flows, and predicting at least one future pose.

System and method for vision-based joint action and pose motion forecasting

A method of analyzing unstructured messages is provided. The method includes extracting a content feature from an embedding associated with each message from a pair of unstructured messages using a neural network, generating, based on extracted content features, a text similarity score between the pair of messages using a second neural network, combining the generated text similarity score with additional data associated with the messages to generate a total similarity score, and generating a message thread based on the generated total similarity score for the pair of messages selected from the plurality of unstructured messages.

System and method for detangling of interleaved conversations in communication platforms

Example implementations described herein involve an interface for calculating and displaying missing links for data represented as a bipartite network, along with novel methods for improving link prediction algorithms in the related art. Through example implementations described herein, the accuracy of link prediction algorithms can be improved upon, thereby providing the user with a more accurate understanding of the data in the bipartite network.

Visual analysis framework for understanding missing links in bipartite networks

A computer implemented method of grouping media objects is provided, as well as systems, interfaces and devices therefor. The method includes generating a group from the media objects based on a combination of a script of sequential events and an actor associated with one or more of the media objects in the script, segmenting the group into segments each including one or more of the media objects, based on clustering or classification, providing titling and captioning for the segments, and generating filter and annotation recommendations based on knowledge associations in the media objects, data, and the combination of the script and the actor, across the media objects of the group.

Media object grouping and classification for predictive enhancement

A method and system of targeting information for a user is provided. The method includes collecting one or more digital posts that identify a product and are associated with a digital account, identifying, by a neural network, a stage of a decision model associated with each of the one or more digital posts based on a feature representation generated for each digital post, and transmitting product-related information to the digital account, wherein the transmitting is based on the stage of the decision model identified for each of the one or more digital posts.

System and method for using deep learning to identify purchase stages from a microblog post

A method and device for displaying a plurality of content items may be shown. The method may include detecting at least one topic associated with each of the plurality of content items, generating a set of topics based on the at least one topic associated with each of the plurality of content items, the set of topics comprising a number of topics associated with the plurality of content items, reducing the number of topics in the set of topics, by combining one of the number of topic in response to a determination that at least one topic in the set of topics is redundant, and generating a visualization, the visualization including at least one content item from the plurality of content items; and the set of topics.

System and method for user-oriented topic selection and browsing

A method of visualizing relationship data in a network connecting an entity of a first type with an entity of a second type is provided. The method includes detecting, within the network, a subnetwork pattern representing at least one relationship satisfying a condition, generating a visualization based on the detected subnetwork pattern. The visualization includes a first region representative of the first type of entity, a second region representative of the second type of entity, and a linking region connecting the first region to the second region and providing information about the at least one relationship satisfying the condition.

System and method for visual exploration of subnetwork patterns in two-mode networks

A method of visualizing search results is provided. The method includes receiving a content feature, detecting, within a network, a subnetwork pattern representing a relationship satisfying a condition and associated with an entity of a first or a second type, the entity being associated with the content feature, and generating a visualization based on the detected subnetwork pattern. The visualization includes a first region representative of the first type of entity, a second region representative of the second type of entity, and a linking region connecting the first region to the second region and providing information about the represented relationship.

System and method for visual exploration of search results in two-mode networks

A method and system for visualizing data associated with a search inquiry. The method includes receiving, a data set each data item having associated rank information, and similarity information indicative of similarities between the data item and one or more other data items, sorting the data set into a ranked list based on the rank information, masking a contiguous portion of the ranked list based on a boundary parameter, iteratively clustering a portion of the ranked list other than the masked contiguous portion based op the similarity information to produce a clustered, ranked data list; and generating and displaying a visualization representative of the clustered, ranked data list, the visualization comprising a shaped object representative of each cluster in the clustered, ranked data list.

System and method automatically sorting ranked items and generating a visual representation of ranked results

A method and system for determining a treatment order for a plurality of patient imaging records. The method includes extracting, by a trained neural network, image features from each of the plurality of imaging records, generating, by the trained neural network, a written report associated with each of the plurality of imaging records based on the extracted image features, wherein the trained neural network generates the written report based on a sentence annotation model that provides abnormality annotations on an individual sentence basis, determining, by the trained neural network, an abnormality score associated with each written report, and providing the written reports to a treating physician in a sorted order based on the abnormality score associated with each written report.

System and method for generating descriptions of abnormalities in medical images

A computer-implemented method, comprising extracting each frame of a video sequence, estimating current poses of a subject within each frame and determining joint locations for a joint associated with the subject within each frame, computing optical flows between each pair of consecutive video frames, extracting motion features from each video frame of the video sequence based on the optical flows, encoding state information based on the current poses and the motion features, determining a current action label for each motion feature in the state information for a first frame; predicting future action labels for each motion feature in a second frame subsequent to the first frame, based on the current pose, action label and state information, predicting future poses for each motion feature in the second frame based on the current poses and the state information; and refining the current action label, the future action labels, and the future poses.

A method and system for generating summaries of posts of interleaved text are provided. The method includes embedding, by a first neural network, each post through word-to-word encoding; embedding, by a second neural network, overall content of the plurality of posts through post-to-post encoding based on the word-to-word encoding of each post; generating, by at least a third neural network, a summary of the at least one thread through word-to-word decoding based on the overall content embedding of the plurality of posts; and displaying the summary of the at least one thread to a user.

System and method for generating abstractive summaries of interleaved texts

Growing community of inventors

Menlo Park, CA, United States of America

Francine R Chen