专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20230138254A1 TEMPORAL CONTRASTIVE LEARNING FOR SEMI-SUPERVISED VIDEO ACTION RECOGNITION 有权
公开(公告)号：US20230138254A1
公开(公告)日：2023-05-04
申请号：US17515380
申请日：2021-10-29
申请人： International Business Machines Corporation , Indian Institute of Technology Kharagpur
发明人： Rameswar Panda , Rogerio Schmidt Feris , Abir Das
IPC分类号： G06K9/62 , G06K9/00 , G06N3/04 , G06N3/08 , G06F16/783
摘要： A base pathway of a computerized two-pathway video action recognition model is trained using a plurality of labeled video samples. The base pathway is trained using a plurality of unlabeled video samples at a first framerate. An auxiliary pathway of the computerized two-pathway video action recognition model is trained using a plurality of the unlabeled video samples at a second framerate, the second framerate being slower than the first framerate, wherein the training of the base pathway and the training of the auxiliary pathway result in a trained computerized two-pathway video action recognition model. A candidate video is categorized using the trained computerized two-pathway video action recognition model and the categorized candidate video is stored in a computer-accessible video database system for information retrieval.

2. 发明授权

US10679047B2 System and method for pose-aware feature learning 有权
公开(公告)号：US10679047B2
公开(公告)日：2020-06-09
申请号：US15858314
申请日：2017-12-29
申请人： International Business Machines Corporation
发明人： Rogerio Schmidt Feris , Minkyong Kim , Clifford A. Pickover
IPC分类号： G06K9/00 , G06T7/73 , G06K9/62 , G06T7/13 , G06T7/55
摘要： An object recognition system includes a parameter generator for generating a parameter that indicates whether an object depicted in an image pair is the same or different object, and a pose difference for the image pair and a parameter refiner for refining the parameter, and an applicator for applying the refined parameter to object recognition.

3. 发明申请

US20170140655A1 DYNAMIC MANAGEMENT SYSTEM, METHOD, AND RECORDING MEDIUM FOR COGNITIVE DRONE-SWARMS 审中-公开
公开(公告)号：US20170140655A1
公开(公告)日：2017-05-18
申请号：US15418826
申请日：2017-01-30
申请人： International Business Machines Corporation
发明人： Thomas David Erickson , Rogerio Schmidt Feris , Clifford A. Pickover
IPC分类号： G08G5/00 , B64C39/02 , G07C5/08
CPC分类号： G08G5/0039 , G05D1/0027 , G07C5/0808 , G08G5/0013 , G08G5/0026 , G08G5/0043 , G08G5/0069 , G08G5/0082
摘要： A method, system, and recording medium including a drone and pattern recruiting device configured to recruit a plurality of drones based on a mission, a flocking goal device configured to arrange the plurality of drones in the drone-swarm in a pattern to satisfy the mission, and a changing device configured to adaptively change the pattern of the drone-swarm based on a condition of the mission indicating a needed change and to cause the drone and pattern recruiting device to recruit an additional drone for the needed change.

4. 发明申请

US20150131910A1 Semantic Parsing of Objects in Video 有权
标题翻译：视频中对象的语义分析
公开(公告)号：US20150131910A1
公开(公告)日：2015-05-14
申请号：US14597904
申请日：2015-01-15
申请人： International Business Machines Corporation
发明人： Lisa Marie Brown , Rogerio Schmidt Feris , Arun Hampapur , Daniel Andre Vaquero
IPC分类号： G06K9/00 , G06K9/68 , G06K9/62
CPC分类号： G06K9/00718 , G06K9/00369 , G06K9/00664 , G06K9/469 , G06K9/6201 , G06K9/6202 , G06K9/6232 , G06K9/6857
摘要： Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object derived from a video input, wherein each version has a different resolution of said image of said object; computing an appearance score at each of a plurality of regions on the lowest resolution version of said plurality of versions of said image for at least one attribute for said object, wherein said appearance score denotes a probability of the at least one attribute appearing in the region; determining a configuration of the at least one attribute in the lowest resolution version based on at least the appearance score in each of the plurality of regions in the lowest resolution version; and displaying said configuration.
摘要翻译：本文提供了用于解析视频中对象的方法，系统和计算机程序产品。一种方法包括产生从视频输入导出的对象的图像的多个版本，其中每个版本具有所述对象的所述图像的不同分辨率; 在所述图像的所述多个版本的最低分辨率版本的每个区域上计算用于所述对象的至少一个属性的外观评分，其中所述出现评分表示在所述区域中出现所述至少一个属性的概率 ; 至少基于最低分辨率版本的多个区域中的每一个中的出现得分来确定最低分辨率版本中的至少一个属性的配置; 并显示所述配置。

5. 发明授权

US08588533B2 Semantic parsing of objects in video 有权
标题翻译：视频中对象的语义解析
公开(公告)号：US08588533B2
公开(公告)日：2013-11-19
申请号：US13783749
申请日：2013-03-04
申请人： International Business Machines Corporation
发明人： Lisa Marie Brown , Rogerio Schmidt Feris , Arun Hampapur , Daniel Andre Vaquero
IPC分类号： G06K9/00
CPC分类号： G06K9/00718 , G06K9/00369 , G06K9/00664 , G06K9/469 , G06K9/6201 , G06K9/6202 , G06K9/6232 , G06K9/6857
摘要： Techniques, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing and storing a plurality of versions of an image of an object derived from a video input, wherein each version of said image has a different resolution of said image; computing an appearance score at each of a plurality of regions on the lowest resolution version of said image for a plurality of semantic attributes with associated parts for said object, said appearance score denoting a probability of each semantic attribute appearing in the region; analyzing increasingly higher resolution versions than the lowest resolution version to compute a resolution context score for each region in the lowest resolution version; and ascertaining an optimized configuration of body parts and associated semantic attributes in the lowest resolution version, said ascertaining utilizing the appearance scores and the resolution context scores.
摘要翻译：本文提供了用于解析视频中对象的技术，系统和计算机程序产品。一种方法包括产生和存储从视频输入导出的对象的图像的多个版本，其中所述图像的每个版本具有所述图像的不同分辨率; 在所述图像的最低分辨率版本上的多个区域中的每一个上计算用于多个具有所述对象的相关部分的语义属性的外观评分，所述外观评分表示在该区域中出现每个语义属性的概率; 分析比最低分辨率版本更高的分辨率版本来计算最低分辨率版本中每个区域的分辨率上下文得分; 并且确定最低分辨率版本中的身体部位和相关联的语义属性的优化配置，所述确定利用外观得分和分辨率上下文得分。

6. 发明申请

US20230082448A1 ADAPTIVE REDUNDANCY REDUCTION FOR EFFICIENT VIDEO UNDERSTANDING 有权
公开(公告)号：US20230082448A1
公开(公告)日：2023-03-16
申请号：US17476437
申请日：2021-09-15
申请人： International Business Machines Corporation , Massachusetts Institute of Technology
发明人： Bowen Pan , Rameswar Panda , Camilo Luciano Fosco , Rogerio Schmidt Feris , Aude Jeanne Oliva
IPC分类号： G06N3/08 , G06N3/04 , G06K9/62
摘要： For each convolution layer of a plurality of convolution layers of a convolutional neural network (CNN), apply an input-dependent policy network to determine: a first fraction of input feature maps to the given layer for which first corresponding output feature maps are to be fully computed by the layer; and a second fraction of input feature maps to the layer for which second corresponding output feature maps are not to be fully computed, but to be reconstructed from the first corresponding output feature maps. Fully computing the first corresponding output feature maps and reconstruct the second corresponding output feature maps. For a final one of the convolution layers of the plurality of convolution layers of the neural network, input the first corresponding output feature maps and the second corresponding output feature maps to an output layer to obtain an inference result.

7. 发明授权

US10163355B2 Dynamic management system, method, and recording medium for cognitive drone-swarms 有权
公开(公告)号：US10163355B2
公开(公告)日：2018-12-25
申请号：US15418826
申请日：2017-01-30
申请人： International Business Machines Corporation
发明人： Thomas David Erickson , Rogerio Schmidt Feris , Clifford A. Pickover
IPC分类号： G08G5/00 , G05D1/00 , G07C5/08 , G06F3/00
摘要： A method, system, and recording medium including a drone and pattern recruiting device configured to recruit a plurality of drones based on a mission, a flocking goal device configured to arrange the plurality of drones in the drone-swarm in a pattern to satisfy the mission, and a changing device configured to adaptively change the pattern of the drone-swarm based on a condition of the mission indicating a needed change and to cause the drone and pattern recruiting device to recruit an additional drone for the needed change.

8. 发明授权

US09679201B2 Semantic parsing of objects in video 有权
公开(公告)号：US09679201B2
公开(公告)日：2017-06-13
申请号：US14997789
申请日：2016-01-18
申请人： International Business Machines Corporation
发明人： Lisa Marie Brown , Rogerio Schmidt Feris , Arun Hampapur , Daniel Andre Vaquero
IPC分类号： G06K9/00 , G06K9/46 , G06K9/68 , G06K9/62
CPC分类号： G06K9/00718 , G06K9/00369 , G06K9/00664 , G06K9/469 , G06K9/6201 , G06K9/6202 , G06K9/6232 , G06K9/6857
摘要： Methods, systems, and computer program products for parsing objects are provided herein. A method includes producing a plurality of versions of an image of an object derived from an input, wherein each version comprises one of one multiple resolutions of said image of said object; computing an appearance probability at each of a plurality of regions on the one or more lowest resolution versions of said plurality of versions of said image for at least one attribute for said object; determining a configuration of the at least one attribute in the one or more lowest resolution versions based on at least the appearance probability in each of the plurality of regions; and outputting said configuration.

9. 发明授权

US08774522B2 Semantic parsing of objects in video 有权
标题翻译：视频中对象的语义解析
公开(公告)号：US08774522B2
公开(公告)日：2014-07-08
申请号：US13948325
申请日：2013-07-23
申请人： International Business Machines Corporation
发明人： Lisa Marie Brown , Rogerio Schmidt Feris , Arun Hampapur , Daniel Andre Vaquero
IPC分类号： G06K9/00
CPC分类号： G06K9/00718 , G06K9/00369 , G06K9/00664 , G06K9/469 , G06K9/6201 , G06K9/6202 , G06K9/6232 , G06K9/6857
摘要： Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object, wherein each version has a different resolution of said image of said object, and computing an appearance score at each of a plurality of regions on the lowest resolution version for at least one semantic attribute for said object. Such a method also includes analyzing one or more other versions to compute a resolution context score for each of the plurality of regions in the lowest resolution version, wherein said resolution context score denotes an extent to which finer spatial structure exists in the one or more others versions than in the lowest resolution version, and determining a configuration of the at least one semantic attribute in the lowest resolution version based on the appearance score and the resolution context score.
摘要翻译：本文提供了用于解析视频中对象的方法，系统和计算机程序产品。一种方法包括产生对象的图像的多个版本，其中每个版本具有所述对象的所述图像的不同分辨率，以及针对至少一个最小分辨率版本的多个区域中的每个区域计算出现得分所述对象的语义属性。这种方法还包括分析一个或多个其他版本以计算最低分辨率版本中的多个区域中的每一个的分辨率上下文得分，其中所述分辨率上下文得分表示一个或多个其中存在更细的空间结构的程度版本比最低分辨率版本，并且基于出现得分和分辨率上下文得分确定最低分辨率版本中的至少一个语义属性的配置。

10. 发明授权

US09659238B2 Video object classification 有权
公开(公告)号：US09659238B2
公开(公告)日：2017-05-23
申请号：US14253266
申请日：2014-04-15
申请人： International Business Machines Corporation
发明人： Lisa Marie Brown , Longbin Chen , Rogerio Schmidt Feris , Arun Hampapur , Yun Zhai
IPC分类号： G06K9/62 , G06K9/00 , G06K9/32 , G06K9/20
CPC分类号： G06K9/6267 , G06K9/00369 , G06K9/00771 , G06K9/2081 , G06K9/3241 , G06K2209/23
摘要： A system comprises an input component, a feature extractor, an object classifier, an adaptation component and a calibration tool. The input component is configured to receive one or more images, and the feature extractor is configured to extract features for one or more objects in the one or more images, the extracted features comprising at least one view-independent feature. The object classifier is configured to classify the one or more objects based at least in part on the extracted features and one or more object classification parameters, and the adaptation component is configured to adjust the classification of at least one of the objects based on one or more contextual parameters. The calibration tool is configured to adjust one or more of the object classification parameters based on likelihoods for characteristics associated with one or more object classes.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式