International Business Machines Corporation

Other

Xerxes Corporation

Columbia University

Sinoeast Concept Limited

Ibm Thomas J. Watson Search Center

John Richard Smith

Chung-Sheng Li

Apostol Ivanov Natsev

Yuan-Chi Chang

Milind R Naphade

Lawrence David Bergman

Matthew Leon Hill

Sharathchandra UmapathiRao Pankanti

Vittorio R Castelli

Noel C Codella

Michele Merler

Chung-Ching Lin

Lexing Xie

Belle L Tseng

Liangliang Cao

Jelena Tesic

Gang Hua

Ching-Yung Lin

Shih-Fu Chang

Ana Belen Benitez

John Ronald Kender

Rakesh Mohan

Noel C F Codella

Atul Puri

Myron Dale Flickner

Yi Ke Wu

Christian Alexander Lang

Aleksandr Y Aravkin

Rosario A Uceda-Sosa

Robin Berg

John R Burwell

Karthikeyan Natesan Ramamurthy

Quoc-Bao Nguyen

Bernadette R Duponchel

Victoria B Platt

Rogerio Schmidt Feris

Rong Yan

Jonathan Hudson Connell, Ii

Sriram Kolinjivadi Padmanabhan

Stephen Carl Hammer

Qian Huang

Ioana Roxana Stanoi

Hui Wu

Shahram Ebadollahi

Murray Scott Campbell

Seungyup Paek

Albert F Dorris

Dhiraj Joshi

John Joseph Kent

Gong Leiguang

Alejandro Jaimes

Clifford A Pickover

Matthew B Trevathan

Nalini Kanta Ratha

Charu Chandra Aggarwal

Kun-Lung Wu

Philip Shilung Yu

Bishwaranjan Bhattacharjee

Samuel Scott Adams

Alfio Massimiliano Gliozzo

Sandeep Kishan Singhal

Min Wang

Hui-I Hsiao

Lilla Boroczky

Raman Harishankar

Jae-Eun Park

Francisco Phelan Curbera

Chalapathy Venkata Neti

Hiroshi Maruyama

Stephen Eric Jaffe

David Mun-Hien Choy

Stefan Georg Hild

Jy-Jine James Lin

David Leslie Cohn

Guy Jonathan James Rackham

Cicero Nogueira Dos Santos

David B Flaxer

Anant Deep Jhingran

Sankar Basu

Gene Y C Fuh

Mary A Smith

Richard Orville LaMaire

John George Vergo

Mauro Martino

Maria Eleftheriou

George M Galambos

Robin Williams

Hugh William Adams, Jr

Robert D Dill

Seungup Paek

Chris Frank

Marie Smith

Christopher Murasso

Laurie A Tropiano

Richard Han

Brian Michael Landry

Giridharen Iyengar

Ana Belen Benitez-Jimenez

Richard Yeh-whei Han

Paek Seungyup

A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Auto-curation and personalization of sports highlights

An iterative methodology and system (which can also be represented in software), with the option for continual improvement, for the interactive capture, merger, comparison, analysis, cloning and manipulation of anything in the unique universe medium or multiple universes mediums, be it real, virtual or imagined, including thought (of organic or non-organic or other nature), in real time or non-real time, where anything also includes anything infinitely small (or a small base volume of space known as a Senserom), to infinitely large (or a large encapsulating Senseroom volume known as a Senseverse) and can include multiple universes and Senserooms themselves impacting each other, static or dynamic changing over time periods, including the past, present and future. The full set of these infinite Senseroms and Senserooms is considered the Senseverse, which contains anything and/or everything real, virtual and imagined.

Interactive and iterative method and system for using feedback to make measurements, manage data, and printing and scanning anything in real time and non-real time

A method and system of stitching a plurality of image views of a scene, including grouping matched points of interest in a plurality of groups, and determining a similarity transformation with smallest rotation angle for each grouping of the matched points. The method further includes generating virtual matching points on non-overlapping area of the plurality of image views and generating virtual matching points on overlapping area for each of the plurality of image views.

System and method for perspective preserving stitching and summarizing views

A computer-implemented method for finding objects in a collection of images or video, the method comprising: assessing a similarity between two subgraphs; detecting the objects in the collection; assessing a relationship between the objects; finding attributes of the objects; constructing a collection graph for the collection where each of the objects is the vertices and nodes of the collection graph and their relationships with other objects and attributes are edges of the collection graphs; recursively identifying coherent subgraphs and turning the coherent subgraphs into new meta-nodes of the collection graph; identification of the stable graph reducing the collection graph into zero or more distinct stories; assigning a similarity score for each pair of the stories based on a similarity between the corresponding stories; linking the stories into inlier stories based on the similarity score being greater than a first pre-determined threshold level.

Aerial videos compression

Techniques for content generation are provided. A plurality of discriminative terms is determined based at least in part on a first plurality of documents that are related to a first concept, and a plurality of positive exemplars and a plurality of negative exemplars are identified using the plurality of discriminative terms. A first machine learning (ML) model is trained to classify images into concepts, based on the plurality of positive exemplars and the plurality of negative exemplars. A second concept related to the first concept is then determined, based on the first ML model. A second ML model is trained to generate images based on the second concept, and a first image is generated using the second ML model. The first image is then refined using a style transfer ML model that was trained using a plurality of style images.

Automatic generation of content using multimedia

Aspects of the present invention disclose a method, computer program product, and system for identifying symptoms based on digital media. The method includes one or more processors receiving digital media and information associated with a first animal from a user. The method further includes one or more processors identifying data records, stored in a knowledge database, that are respectively associated with an animal that is similar to the first animal. The method further includes one or more processors determining symptom information corresponding to the first animal based on a comparison of the received digital media and information associated with the first animal and the identified data records. The method further includes presenting the determined symptom information to a user.

Determining information based on an analysis of images and video

Generating a textual description of an image includes classifying an image represented by image data into a domain-specific category, and segmenting one or more elements in the image data based on the domain-specific category. Each element of the one or more elements is compared to a domain-independent model to detect one or more statistical anomalies in the one or more elements. The one or more detected statistical anomalies are characterized using one or more domain-independent text phrases. The one or more domain-independent text phrases are converted to one or more domain-specific descriptions based upon the domain-specific category.

Generating a textual description of an image using domain-independent anomaly analysis

One or more embodiments described herein include a computer-implemented method of determining a bounding box for an object in an image. The method includes determining a label for an object in a first image using a first algorithm, and generating a set of images based on the first image, by cropping the first image from a selected direction. The method further includes determining labels for each image in the set using the first algorithm, and removing images from the set such that the remaining images have a label matching the initial label. The method further includes determining a key image for the set, which is the smallest image from the set that has a confidence score exceeding a threshold. Further, the method includes determining a bounding box for the object in the first image based on a perimeter of a portion of the first image that overlaps the key image.

Automated bounding box generation for objects in an image

A personalization enhancement method and system. The method includes retrieving and analyzing digital content associated with a user. Characteristics describing the digital content are tagged and transferred to a profile of said the user. The profile includes additional characteristics generated during previous analysis of data from the digital content and additional digital content associated with the user. User information associated with products, a location, and a time profile is assigned. The profile is analyzed based on selection and interaction of the user with respect to a consumer Website. The profile includes the characteristics and the additional characteristics with respect to products and services of the consumer Website. A presentation color setting and a group of products and services of are determined for presentation to the user. The group of products and services are presented to the user using the presentation color setting.

Visually generated consumer product presentation

A compression system for compressing a video received from an imaging device, the compression system including a transformation estimation device configured to estimate, based on pixel transformations between a first frame and a second frame of the video, a transformation matrix, an encoding device configured to encode the second frame as an increment with the first frame based on the transformation matrix generated by the transformation device, a compression device configured to compress the increments into compressed data, and a reconstruction device configured to reconstruct the first frame and the second frame using the transformation matrix generated by the transformation estimation device.

System, method, and recording medium for compressing aerial videos

A system and method for analyzing visual memes includes identifying visual memes associated with at least one topic in a data source. The visual memes propagated over time are tracked to extract information associated with identified visual memes. The information associated with the visual memes is analyzed to determine at least one of generation, propagation, and use of the identified memes.

Visual meme tracking for social media analysis

A method and system are provided. The method includes deriving a set of user attributes from an aggregate analysis of images and videos of a user. The deriving step includes recognizing, by a set of visual classifiers, semantic concepts in the images and videos of the user to generate visual classifier scores. The deriving step further includes deriving, by a statistical aggregator, the set of user attributes. The set of user attributes are derived by mapping the visual classifier scores to a taxonomy of semantic categories to be recognized in visual content. The deriving step also includes displaying, by an interactive user interface having a display, attribute profiles for the attributes and comparisons of the attribute profiles.

Individual and user group attributes discovery and comparison from social media visual content

A discrepancy detection system for detecting a discrepancy between a plurality of video images of a same scene captured by an imaging device at different times, the system including a correspondence point detection device configured to detect corresponding points matching each other between a first video image sequence of the plurality of video images and a second video image sequence of the plurality of video images and a comparison device configured to compare image content of the first video image sequence and the second video image sequence for the discrepancy in the image content between the first video image sequence and the second video image sequence.

System, method, and recording medium for detecting events for interest from mobile

Growing community of inventors

New York, NY, United States of America

John Richard Smith