-
公开(公告)号：US11830241B2
公开(公告)日：2023-11-28
申请号：US16752641
申请日：2020-01-25
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Michele Merler , Dhiraj Joshi , Quoc-Bao Nguyen , Stephen C. Hammer , John Joseph Kent , John R. Smith , Rogerio Feris
IPC: H04N21/233 , H04N21/234 , H04N21/25 , G06N20/10 , G06V10/82 , H04N21/8549 , G06N3/08 , G06N3/04 , H04N21/439 , H04N21/431 , H04N21/466 , H04N21/442 , H04N21/44 , G06N20/00 , G06V20/40 , G06V40/16 , G06V30/19 , G06V30/10
CPC classification number: G06V10/82 , G06N3/04 , G06N3/08 , G06N20/00 , G06V20/46 , G06V30/19173 , G06V40/16 , G06V40/172 , H04N21/439 , H04N21/4312 , H04N21/44 , H04N21/442 , H04N21/466 , H04N21/8549 , G06V30/10
Abstract: 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.
-
公开(公告)号：US20210117736A1
公开(公告)日：2021-04-22
申请号：US16656389
申请日：2019-10-17
Applicant: International Business Machines Corporation
Inventor： Michele Merler , Mauro Martino , Cicero NOGUEIRA DOS SANTOS , Alfio Massimiliano Gliozzo , John R. Smith
Abstract: 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.
-
公开(公告)号：US10943697B2
公开(公告)日：2021-03-09
申请号：US15828806
申请日：2017-12-01
Applicant: International Business Machines Corporation
Inventor： Lilla Boroczky , Francisco Phelan Curbera , Maria Eleftheriou , John R. Smith
Abstract: 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.
-
公开(公告)号：US20200257980A1
公开(公告)日：2020-08-13
申请号：US16270697
申请日：2019-02-08
Applicant: International Business Machines Corporation
Inventor： Bishwaranjan Bhattacharjee , Parag Chandakkar , John R. Smith
Abstract: In an embodiment, a method includes training a neural network model with a first set of training data. In an embodiment, the method includes calculating divergence for a set of layers of the neural network model, the set of layers comprising at least one batch norm layer. In an embodiment, the method includes analyzing, based on the calculated divergence, a stability of each of the set of layers. In an embodiment, the method includes removing, based on the analysis determining a subset of the set of layers fails to meet a threshold stability, the subset of the set of layers of the neural network model.
-
公开(公告)号：US10643093B1
公开(公告)日：2020-05-05
申请号：US16194817
申请日：2018-11-19
Applicant: International Business Machines Corporation
Inventor： Bishwaranjan Bhattacharjee , John R. Smith , Matthew Greenberg
Abstract: 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.
-
Patent Agency Ranking
公开(公告)号：US10553005B2
公开(公告)日：2020-02-04
申请号：US15430057
申请日：2017-02-10
Applicant: International Business Machines Corporation
Inventor： Chung-Ching Lin , Sharathchandra U. Pankanti , Karthikeyan Natesan Ramamurthy , Aleksandr Y. Aravkin , John R. Smith
Abstract: 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.
-
公开(公告)号：US20190172580A1
公开(公告)日：2019-06-06
申请号：US15828806
申请日：2017-12-01
Applicant: International Business Machines Corporation
Inventor： Lilla Boroczky , Francisco Phelan Curbera , Maria Eleftheriou , John R. Smith
Abstract: 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.
-
48.发明授权公开(公告)号：US10282677B2
公开(公告)日：2019-05-07
申请号：US14933842
申请日：2015-11-05
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Michele Merler , Jae-Eun Park , John R. Smith , Rosario Uceda-Sosa
Abstract: 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.
-
49.发明授权System and method for relating corresponding points in images with different viewing angles 有权用于将具有不同视角的图像中的相应点相关联的系统和方法公开(公告)号：US09400939B2
公开(公告)日：2016-07-26
申请号：US14251636
申请日：2014-04-13
Applicant: International Business Machines Corporation
Inventor： Chung-Ching Lin , Sharathchandra U. Pankanti , John R. Smith
CPC classification number: G06K9/4671 , G06K9/52 , G06K9/6203 , G06T3/4038 , G06T7/33 , G06T7/40 , G06T2200/32 , G06T2207/10016 , G06T2207/10024 , G06T2207/20076
Abstract: A system, method and computer program product for relating corresponding points in images with an overlapping scene. An example method includes generating transformed images of a target image using different image transformations for each of transformed images. Texture descriptors are extracted for feature points in the transformed images and a reference image. Matched feature points are identified and inliers from matched feature points are selected. An aligning transformation is generated using the inliers for at least one of the transformed images. A panorama image is created with the target image and reference image after the images are aligned.
Abstract translation: 一种用于将图像中的对应点与重叠场景相关联的系统，方法和计算机程序产品。 示例性方法包括使用对于每个变换图像的不同图像变换来生成目标图像的变换图像。 提取纹理描述符用于变换图像中的特征点和参考图像。 识别匹配的特征点，并选择匹配特征点的内容。 使用用于至少一个变换图像的内联产生对准变换。 在图像对齐后，使用目标图像和参考图像创建全景图像。
-
公开(公告)号：US09292766B2
公开(公告)日：2016-03-22
申请号：US13969783
申请日：2013-08-19
Applicant: International Business Machines Corporation
Inventor： Liangliang Cao , Noel C. F. Codella , Gang Hua , John R. Smith
CPC classification number: G06K9/6256 , G06K9/00657
Abstract: Techniques for generating cross-modality semantic classifiers and using those cross-modality semantic classifiers for ground level photo geo-location using digital elevation are provided. In one aspect, a method for generating cross-modality semantic classifiers is provided. The method includes the steps of: (a) using Geographic Information Service (GIS) data to label satellite images; (b) using the satellite images labeled with the GIS data as training data to generate semantic classifiers for a satellite modality; (c) using the GIS data to label Global Positioning System (GPS) tagged ground level photos; (d) using the GPS tagged ground level photos labeled with the GIS data as training data to generate semantic classifiers for a ground level photo modality, wherein the semantic classifiers for the satellite modality and the ground level photo modality are the cross-modality semantic classifiers.
-
-
-
-
-
-
-
-
-
Search Results
65
records
(took 0.023 seconds)
