-
公开(公告)号：US11717959B2
公开(公告)日：2023-08-08
申请号：US16622309
申请日：2018-06-28
Applicant: Google LLC
Inventor： Eric Jang , Sudheendra Vijayanarasimhan , Peter Pastor Sampedro , Julian Ibarz , Sergey Levine
CPC classification number: B25J9/163 , G06N3/008 , G06N3/045 , G06N3/08 , G05B2219/39536
Abstract: Deep machine learning methods and apparatus related to semantic robotic grasping are provided. Some implementations relate to training a training a grasp neural network, a semantic neural network, and a joint neural network of a semantic grasping model. In some of those implementations, the joint network is a deep neural network and can be trained based on both: grasp losses generated based on grasp predictions generated over a grasp neural network, and semantic losses generated based on semantic predictions generated over the semantic neural network. Some implementations are directed to utilization of the trained semantic grasping model to servo, or control, a grasping end effector of a robot to achieve a successful grasp of an object having desired semantic feature(s).
-
公开(公告)号：US20200349722A1
公开(公告)日：2020-11-05
申请号：US16464608
申请日：2017-12-01
Applicant: Google LLC
Inventor： Cordelia Luise Schmid , Sudheendra Vijayanarasimhan , Susanna Maria Ricco , Bryan Andrew Seybold , Rahul Sukthankar , Aikaterini Fragkiadaki
Abstract: A system comprising an encoder neural network, a scene structure decoder neural network, and a motion decoder neural network. The encoder neural network is configured to: receive a first image and a second image; and process the first image and the second image to generate an encoded representation of the first image and the second image. The scene structure decoder neural network is configured to process the encoded representation to generate a structure output characterizing a structure of a scene depicted in the first image. The motion decoder neural network configured to process the encoded representation to generate a motion output characterizing motion between the first image and the second image.
-
公开(公告)号：US20200215686A1
公开(公告)日：2020-07-09
申请号：US16823947
申请日：2020-03-19
Applicant: Google LLC
Inventor： Sudheendra Vijayanarasimhan , Eric Jang , Peter Pastor Sampedro , Sergey Levine
Abstract: Deep machine learning methods and apparatus related to manipulation of an object by an end effector of a robot. Some implementations relate to training a semantic grasping model to predict a measure that indicates whether motion data for an end effector of a robot will result in a successful grasp of an object; and to predict an additional measure that indicates whether the object has desired semantic feature(s). Some implementations are directed to utilization of the trained semantic grasping model to servo a grasping end effector of a robot to achieve a successful grasp of an object having desired semantic feature(s).
-
公开(公告)号：US20200338722A1
公开(公告)日：2020-10-29
申请号：US16622309
申请日：2018-06-28
Applicant: Google LLC
Inventor： Eric Jang , Sudheendra Vijayanarasimhan , Peter Pastor Sampedro , Julian Ibarz , Sergey Levine
Abstract: Deep machine learning methods and apparatus related to semantic robotic grasping are provided. Some implementations relate to training a training a grasp neural network, a semantic neural network, and a joint neural network of a semantic grasping model. In some of those implementations, the joint network is a deep neural network and can be trained based on both: grasp losses generated based on grasp predictions generated over a grasp neural network, and semantic losses generated based on semantic predictions generated over the semantic neural network. Some implementations are directed to utilization of the trained semantic grasping model to servo, or control, a grasping end effector of a robot to achieve a successful grasp of an object having desired semantic feature(s).
-
公开(公告)号：US20200082173A1
公开(公告)日：2020-03-12
申请号：US16687118
申请日：2019-11-18
Applicant: Google LLC
Inventor： Balakrishnan Varadarajan , George Dan Toderici , Apostol Natsev , Nitin Khandelwal , Sudheendra Vijayanarasimhan , Weilong Yang , Sanketh Shetty
Abstract: A system and methodology provide for annotating videos with entities and associated probabilities of existence of the entities within video frames. A computer-implemented method identifies an entity from a plurality of entities identifying characteristics of video items. The computer-implemented method selects a set of features correlated with the entity based on a value of a feature of a plurality of features, determines a classifier for the entity using the set of features, and determines an aggregation calibration function for the entity based on the set of features. The computer-implemented method selects a video frame from a video item, where the video frame having associated features, and determines a probability of existence of the entity based on the associated features using the classifier and the aggregation calibration function.
-
Patent Agency Ranking
公开(公告)号：US10289912B1
公开(公告)日：2019-05-14
申请号：US15143218
申请日：2016-04-29
Applicant: Google LLC
Inventor： Sudheendra Vijayanarasimhan , George Dan Toderici , Yue Hei Ng , Matthew John Hausknecht , Oriol Vinyals , Rajat Monga
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying videos using neural networks. One of the methods includes obtaining a temporal sequence of video frames, wherein the temporal sequence comprises a respective video frame from a particular video at each of a plurality time steps; for each time step of the plurality of time steps: processing the video frame at the time step using a convolutional neural network to generate features of the video frame; and processing the features of the video frame using an LSTM neural network to generate a set of label scores for the time step and classifying the video as relating to one or more of the topics represented by labels in the set of labels from the label scores for each of the plurality of time steps.
-
公开(公告)号：US20190114487A1
公开(公告)日：2019-04-18
申请号：US15782789
申请日：2017-10-12
Applicant: Google LLC
Inventor： Sudheendra Vijayanarasimhan , Alexis Bienvenu , David Ross , Timothy Novikoff , Arvind Balasubramanian
IPC: G06K9/00 , G06N3/04 , G06F3/0484
Abstract: A computer-implemented method includes receiving a video that includes multiple frames. The method further includes identifying a start time and an end time of each action in the video based on application of one or more of an audio classifier, an RGB classifier, and a motion classifier. The method further includes identifying video segments from the video that include frames between the start time and the end time for each action in the video. The method further includes generating a confidence score for each of the video segments based on a probability that a corresponding action corresponds to one or more of a set of predetermined actions. The method further includes selecting a subset of the video segments based on the confidence score for each of the video segments.
-
公开(公告)号：US10049305B2
公开(公告)日：2018-08-14
申请号：US15656192
申请日：2017-07-21
Applicant: Google LLC
Inventor： Sudheendra Vijayanarasimhan , Jay Yagnik
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classification using a neural network. One of the methods for processing an input through each of multiple layers of a neural network to generate an output, wherein each of the multiple layers of the neural network includes a respective multiple nodes includes for a particular layer of the multiple layers: receiving, by a classification system, an activation vector as input for the particular layer, selecting one or more nodes in the particular layer using the activation vector and a hash table that maps numeric values to nodes in the particular layer, and processing the activation vector using the selected nodes to generate an output for the particular layer.
-
公开(公告)号：US20250054306A1
公开(公告)日：2025-02-13
申请号：US18797297
申请日：2024-08-07
Applicant: Google LLC
Inventor： Daniel S. Cohen , Christopher R. Conover , Emily Rose Smith , Anoop Menon , Benjamin Lehn , Sudheendra Vijayanarasimhan , Bo Hu , Shen Yan , Xuehan Xiong , David Alexander Ross
IPC: G06V20/40 , G06V10/70 , H04N21/8549
Abstract: Aspects of the disclosure are directed to methods and systems for short form previews of long form media items. A server can provide, to an artificial intelligence (AI) model, a long form media item to be shared with users. The server can receive, from the AI model, one or more frames that are predicted to contain content that is of interest to the users. The server can extract a segment of the long form media item that corresponds to the one or more frames, where the extracted segment corresponds to a short form media item preview. The short form media item preview can be provided for presentation to the users.
-
公开(公告)号：US12014542B2
公开(公告)日：2024-06-18
申请号：US17120525
申请日：2020-12-14
Applicant: Google LLC
Inventor： Sanketh Shetty , Tomas Izo , Min-Hsuan Tsai , Sudheendra Vijayanarasimhan , Apostol Natsev , Sami Abu-El-Haija , George Dan Toderici , Susana Ricco , Balakrishnan Varadarajan , Nicola Muscettola , WeiHsin Gu , Weilong Yang , Nitin Khandelwal , Phuong Le
IPC: G06K9/00 , G06F16/783 , G06V20/40
CPC classification number: G06V20/41 , G06F16/7834 , G06V20/46 , G06V20/47 , G06V20/49 , G06V2201/10
Abstract: A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.
-
-
-
-
-
-
-
-
-
Search Results
27
records
(took 0.019 seconds)
