-
公开(公告)号：US12174628B2
公开(公告)日：2024-12-24
申请号：US16328202
申请日：2017-08-25
Applicant: Purdue Research Foundation
Inventor： Scott Alan Bronikowski , Daniel Paul Barrett , Haonan Yu , Jeffrey Mark Siskind
Abstract: A system for directing the motion of a vehicle, comprising receiving commands in natural language using a processor, the commands specifying a relative path to be taken by the vehicle with respect to other objects in the environment; and determining an absolute path for the vehicle to follow based on the relative path using the processor, the absolute path comprising a series of coordinates in the environment; and directing the vehicle along the absolute path. Also provided is a system for training a lexicon of a natural language processing system, comprising receiving a data set containing a corpus of absolute paths driven by a vehicle annotated with natural language descriptions of the absolute paths using a processor, and determining parameters of the lexicon based on the data set.
-
公开(公告)号：US12131537B2
公开(公告)日：2024-10-29
申请号：US17135995
申请日：2020-12-29
Applicant: Purdue Research Foundation
Inventor： Jeffrey Mark Siskind , Haonan Yu
CPC classification number: G06V20/41 , G06F18/22 , G06F18/29 , G06T7/20 , G06T7/73 , G06T2207/10016 , G06T2207/10024
Abstract: A system and method for determining the locations and types of objects in a plurality of videos. The method comprises pairing each video with one or more sentences describing the activity or activities in which those objects participate in the associated video, wherein no use is made of a pretrained object detector. The object locations are specified as rectangles, the object types are specified as nouns, and sentences describe the relative positions and motions of the objects in the videos referred to by the nouns in the sentences. The relative positions and motions of the objects in the video are described by a conjunction of predicates constructed to represent the activity described by the sentences associated with the videos.
-
公开(公告)号：US20220207272A1
公开(公告)日：2022-06-30
申请号：US17135995
申请日：2020-12-29
Applicant: Purdue Research Foundation
Inventor： Jeffrey Mark Siskind , Haonan Yu
Abstract: A system and method for determining the locations and types of objects in a plurality of videos. The method comprises pairing each video with one or more sentences describing the activity or activities in which those objects participate in the associated video, wherein no use is made of a pretrained object detector. The object locations are specified as rectangles, the object types are specified as nouns, and sentences describe the relative positions and motions of the objects in the videos referred to by the nouns in the sentences. The relative positions and motions of the objects in the video are described by a conjunction of predicates constructed to represent the activity described by the sentences associated with the videos.
-
公开(公告)号：US20230410504A9
公开(公告)日：2023-12-21
申请号：US17135995
申请日：2020-12-29
Applicant: Purdue Research Foundation
Inventor： Jeffrey Mark Siskind , Haonan Yu
CPC classification number: G06K9/00718 , G06T7/73 , G06K9/6296 , G06K9/6215 , G06T7/20 , G06T2207/10016 , G06T2207/10024
Abstract: A system and method for determining the locations and types of objects in a plurality of videos. The method comprises pairing each video with one or more sentences describing the activity or activities in which those objects participate in the associated video, wherein no use is made of a pretrained object detector. The object locations are specified as rectangles, the object types are specified as nouns, and sentences describe the relative positions and motions of the objects in the videos referred to by the nouns in the sentences. The relative positions and motions of the objects in the video are described by a conjunction of predicates constructed to represent the activity described by the sentences associated with the videos.
-
Patent Agency Ranking
公开(公告)号：US09183466B2
公开(公告)日：2015-11-10
申请号：US14099300
申请日：2013-12-06
Applicant: Purdue Research Foundation
Inventor： Jeffrey Mark Siskind , Andrei Barbu , Siddharth Narayanaswamy , Haonan Yu
CPC classification number: G06K9/723 , G06F17/3079 , G06F17/30793 , G06K9/00751 , G06K9/00771 , G06K9/6297
Abstract: A method of testing a video against an aggregate query includes automatically receiving an aggregate query defining participant(s) and condition(s) on the participant(s). Candidate object(s) are detected in the frames of the video. A first lattice is constructed for each participant, the first-lattice nodes corresponding to the candidate object(s). A second lattice is constructed for each condition. An aggregate lattice is constructed using the respective first lattice(s) and the respective second lattice(s). Each aggregate-lattice node includes a scoring factor combining a first-lattice node factor and a second-lattice node factor. respective aggregate score(s) are determined of one or more path(s) through the aggregate lattice, each path including a respective plurality of the nodes in the aggregate lattice, to determine whether the video corresponds to the aggregate query. A method of providing a description of a video is also described and includes generating a candidate description with participant(s) and condition(s) selected from a linguistic model; constructing component lattices for the participant(s) or condition(s), producing an aggregate lattice having nodes combining component-lattice factors, and determining a score for the video with respect to the candidate description by determining an aggregate score for a path through the aggregate lattice. If the aggregate score does not satisfy a termination condition, participant(s) or condition(s) from the linguistic model are added to the condition, and the process is repeated. A method of testing a video against an aggregate query by mathematically optimizing a unified cost function is also described.
Abstract translation: 针对聚合查询测试视频的方法包括自动接收定义参与者的聚合查询和参与者的条件。 候选对象在视频的帧中被检测到。 为每个参与者构建第一格子，对应于候选对象的第一格子节点。 为每个条件构建第二个格子。 使用相应的第一晶格和相应的第二晶格构造聚集晶格。 每个聚集网格节点包括组合第一格格节点因子和第二格点节点因子的评分因子。 通过聚合格子确定一个或多个路径的各个聚合分数，每个路径包括聚合格子中的相应多个节点，以确定视频是否对应于聚合查询。 还描述了提供视频描述的方法，并且包括：从参与者和从语言模型中选择的条件生成候选描述; 为参与者或条件构建组件网格，产生具有组合分量 - 晶格因子的节点的聚集网格，以及通过确定通过所述候选描述的路径的总分数来确定所述视频相对于所述候选描述的得分 聚集格子。 如果总分不满足终止条件，则将来自语言模型的参与者或条件添加到条件中，并重复该过程。 还描述了通过数学优化统一成本函数来测试针对聚合查询的视频的方法。
-
公开(公告)号：US20250123626A1
公开(公告)日：2025-04-17
申请号：US18991129
申请日：2024-12-20
Applicant: Purdue Research Foundation
Inventor： Jeffrey Mark Siskind , Haonan Yu , Scott Alan Bronikowski , Daniel Paul Barrett
IPC: G05D1/00 , B60W30/10 , B60W50/08 , B60W50/10 , G05D1/222 , G05D1/227 , G05D1/249 , G05D1/46 , G06N3/08
Abstract: Training a lexicon of a natural language processing system may include receiving a data set containing a corpus of absolute paths driven by a vehicle annotated with natural language descriptions of said absolute paths and determining parameters of the lexicon based on the data set. The degree to which a path taken by the vehicle satisfies the annotated description may be specified by a scoring function. The lexicon may be determined by finding the lexicon parameters that optimize the degree to which the paths taken by the vehicle satisfy the annotated descriptions. Objects in the environment of the same class are disambiguated by specifying their position relative to other objects using prepositions.
-
公开(公告)号：US20190220668A1
公开(公告)日：2019-07-18
申请号：US16323179
申请日：2017-06-06
Applicant: Purdue Research Foundation
Inventor： Jeffrey Mark Siskind , Haonan Yu
CPC classification number: G06K9/00718 , G06K9/00751 , G06K9/6215 , G06K9/6296 , G06K9/726 , G06K2009/00738 , G06T7/20 , G06T7/70 , G06T2207/10016 , G06T2207/10024
Abstract: A system and method for determining the locations and types of objects in a plurality of videos. The method comprises pairing each video with one or more sentences describing the activity or activities in which those objects participate in the associated video, wherein no use is made of a pretrained object detector. The object locations are specified as rectangles, the object types are specified as nouns, and sentences describe the relative positions and motions of the objects in the videos referred to by the nouns in the sentences. The relative positions and motions of the objects in the video are described by a conjunction of predicates constructed to represent the activity described by the sentences associated with the videos.
-
公开(公告)号：US20190179316A1
公开(公告)日：2019-06-13
申请号：US16328202
申请日：2017-08-25
Applicant: Purdue Research Foundation
Inventor： Jeffrey Mark SISKIND , Haonan Yu , Scott Alan BRONIKOWSKI , Daniel Paul BARRETT
Abstract: A system for directing the motion of a vehicle, comprising receiving commands in natural language using a processor, the commands specifying a relative path to be taken by the vehicle with respect to other objects in the environment; and determining an absolute path for the vehicle to follow based on the relative path using the processor, the absolute path comprising a series of coordinates in the environment; and directing the vehicle along the absolute path. Also provided is a system for training a lexicon of a natural language processing system, comprising receiving a data set containing a corpus of absolute paths driven by a vehicle annotated with natural language descriptions of the absolute paths using a processor, and determining parameters of the lexicon based on the data set.
-
公开(公告)号：US20140369596A1
公开(公告)日：2014-12-18
申请号：US14099300
申请日：2013-12-06
Applicant: Purdue Research Foundation
Inventor： Jeffrey Mark Siskind , Andrei Barbu , Siddharth Narayanaswamy , Haonan Yu
IPC: G06K9/66
CPC classification number: G06K9/723 , G06F17/3079 , G06F17/30793 , G06K9/00751 , G06K9/00771 , G06K9/6297
Abstract: A method of testing a video against an aggregate query includes automatically receiving an aggregate query defining participant(s) and condition(s) on the participant(s). Candidate object(s) are detected in the frames of the video. A first lattice is constructed for each participant, the first-lattice nodes corresponding to the candidate object(s). A second lattice is constructed for each condition. An aggregate lattice is constructed using the respective first lattice(s) and the respective second lattice(s). Each aggregate-lattice node includes a scoring factor combining a first-lattice node factor and a second-lattice node factor. respective aggregate score(s) are determined of one or more path(s) through the aggregate lattice, each path including a respective plurality of the nodes in the aggregate lattice, to determine whether the video corresponds to the aggregate query. A method of providing a description of a video is also described and includes generating a candidate description with participant(s) and condition(s) selected from a linguistic model; constructing component lattices for the participant(s) or condition(s), producing an aggregate lattice having nodes combining component-lattice factors, and determining a score for the video with respect to the candidate description by determining an aggregate score for a path through the aggregate lattice. If the aggregate score does not satisfy a termination condition, participant(s) or condition(s) from the linguistic model are added to the condition, and the process is repeated. A method of testing a video against an aggregate query by mathematically optimizing a unified cost function is also described.
Abstract translation: 针对聚合查询测试视频的方法包括自动接收定义参与者的聚合查询和参与者的条件。 候选对象在视频的帧中被检测到。 为每个参与者构建第一格子，对应于候选对象的第一格子节点。 为每个条件构建第二个格子。 使用相应的第一晶格和相应的第二晶格构造聚集晶格。 每个聚集网格节点包括组合第一格格节点因子和第二格点节点因子的评分因子。 通过聚合格子确定一个或多个路径的各个聚合分数，每个路径包括聚合格子中的相应多个节点，以确定视频是否对应于聚合查询。 还描述了提供视频描述的方法，并且包括：从参与者和从语言模型中选择的条件生成候选描述; 为参与者或条件构建组件网格，产生具有组合分量 - 晶格因子的节点的聚集网格，以及通过确定通过所述候选描述的路径的总分数来确定所述视频相对于所述候选描述的得分 聚集格子。 如果总分不满足终止条件，则将来自语言模型的参与者或条件添加到条件中，并重复该过程。 还描述了通过数学优化统一成本函数来测试针对聚合查询的视频的方法。
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.047 seconds)
