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.

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).

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.

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.

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.

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.

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.

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.

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).

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.

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.

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.

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.

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.

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.

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).

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.

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).

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).

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.