Abstract: A video localization system localizes actions in videos based on a classification model and an actionness model. The classification model is trained to make predictions of which segments of a video depict an action and to classify the actions in the segments. The actionness model predicts whether any action is occurring in each segment, rather than predicting a particular type of action. This reduces the likelihood that the video localization system over-relies on contextual information in localizing actions in video. Furthermore, the classification model and the actionness model are trained based on weakly-labeled data, thereby reducing the cost and time required to generate training data for the video localization system.

Abstract: A tabular data model, which may be pre-trained on a different data set, is used to generate data samples for a target class with a given set of context data points. The tabular data model is trained to predict class membership of a given data point with a set of context data points. Rather than use the predicted class directly, the class predictions are used to determine a class-conditional energy for a synthetic data point with respect to the target class. The synthetic data point may then be updated based on the class-conditional energy with a stochastic update algorithm, such as stochastic gradient Langevin dynamics or Adaptive Moment Estimation with noise. The value of the synthetic data point is sampled as a data point for the target class. This permits effective data augmentation for tabular data for downstream models.

Abstract: A video localization system localizes actions in videos based on a classification model and an actionness model. The classification model is trained to make predictions of which segments of a video depict an action and to classify the actions in the segments. The actionness model predicts whether any action is occurring in each segment, rather than predicting a particular type of action. This reduces the likelihood that the video localization system over-relies on contextual information in localizing actions in video. Furthermore, the classification model and the actionness model are trained based on weakly-labeled data, thereby reducing the cost and time required to generate training data for the video localization system.

Abstract: The disclosed embodiments include computer-implemented processes and systems that establish configurable pipelines for training and deploying machine-learning processes in distributed computing environments. By way of example, an apparatus may obtain a dataset comprising a plurality of indexed data elements, and based on sample and temporal identifiers associated with each of the indexed data elements, the apparatus may perform operations that partition the dataset into corresponding ones of a plurality of partitioned datasets in accordance with first configuration data. The apparatus may generate feature vectors associated with each of the partitioned datasets based on a corresponding subset of the indexed data elements and in accordance with second configuration data.

Abstract: The disclosed embodiments include computer-implemented processes and systems that establish configurable pipelines for training and deploying machine-learning processes in distributed computing environments. By way of example, an apparatus may execute sequentially a plurality of application engines within a training pipeline in accordance with first configuration data, and the executed application engines may cause the at least one processor to perform operations that train a machine-learning process based on corresponding ones of a plurality of partitioned datasets. Based on artifact data associated with the sequential execution of the application engines, the apparatus may generate elements of explainability data that characterize the training of the machine-learning process within the training pipeline and in accordance with second configuration data, and transmit the explainability data to a computing system. The computer system may generate at least a portion of the second configuration data.

Abstract: The disclosed embodiments include computer-implemented processes and systems that establish configurable pipelines for training and deploying machine-learning processes in distributed computing environments. For example, an apparatus may obtain configuration data associated with a plurality of application engines, and pipelining data characterizing a sequential execution of at least a subset of the application engines. Based on the pipelining data, the apparatus may execute sequentially a subset of the application engines in accordance with the configuration data, which may cause the apparatus to perform operations that at least one of (i) train a machine-learning process or (ii) apply the trained machine-learning process to an input dataset.

Abstract: The disclosed embodiments include computer-implemented processes and systems that establish configurable pipelines for training and deploying machine-learning processes in distributed computing environments. By way of example, an apparatus may execute sequentially a plurality of application engines within an inferencing pipeline in accordance with first configuration data, and the executed application engines may cause the at least one processor to perform operations that apply a trained, machine-learning process to an input dataset on an inferencing date. The apparatus may obtain elements of artifact data associated with the sequential execution of the application engines, and may perform operations that populate a data record with at least an identifier of the inferencing pipeline, the inferencing date, and the elements of artifact data.

Abstract: An image retrieval system receives an image for which to identify relevant images from an image repository. Relevant images may be of the same environment or object and features and other characteristics. Images in the repository are represented in an image retrieval graph by a set of image nodes connected by edges to other related image nodes with edge weights representing the similarity of the nodes to each other. Based on the received image, the image traversal system identifies an image in the image retrieval graph and alternatively explores and traverses (also termed “exploits”) the image nodes with the edge weights. In the exploration step, image nodes in an exploration set are evaluated to identify connected nodes that are added to a traversal set of image nodes. In the traversal step, the relevant nodes in the traversal set are added to the exploration set and a query result set.

Abstract: An image retrieval system receives an image for which to identify relevant images from an image repository. Relevant images may be of the same environment or object and features and other characteristics. Images in the repository are represented in an image retrieval graph by a set of image nodes connected by edges to other related image nodes with edge weights representing the similarity of the nodes to each other. Based on the received image, the image traversal system identifies an image in the image retrieval graph and alternatively explores and traverses (also termed “exploits”) the image nodes with the edge weights. In the exploration step, image nodes in an exploration set are evaluated to identify connected nodes that are added to a traversal set of image nodes. In the traversal step, the relevant nodes in the traversal set are added to the exploration set and a query result set.

Abstract: An image retrieval system receives an image for which to identify relevant images from an image repository. Relevant images may be of the same environment or object and features and other characteristics. Images in the repository are represented in an image retrieval graph by a set of image nodes connected by edges to other related image nodes with edge weights representing the similarity of the nodes to each other. Based on the received image, the image traversal system identifies an image in the image retrieval graph and alternatively explores and traverses (also termed “exploits”) the image nodes with the edge weights. In the exploration step, image nodes in an exploration set are evaluated to identify connected nodes that are added to a traversal set of image nodes. In the traversal step, the relevant nodes in the traversal set are added to the exploration set and a query result set.

Abstract: A content retrieval system uses a graph neural network architecture to determine images relevant to an image designated in a query. The graph neural network learns a new descriptor space that can be used to map images in the repository to image descriptors and the query image to a query descriptor. The image descriptors characterize the images in the repository as vectors in the descriptor space, and the query descriptor characterizes the query image as a vector in the descriptor space. The content retrieval system obtains the query result by identifying a set of relevant images associated with image descriptors having above a similarity threshold with the query descriptor.

Abstract: A text-video recommendation model determines relevance of a text to a video in a text-video pair (e.g., as a relevance score) with a text embedding and a text-conditioned video embedding. The text-conditioned video embedding is a representation of the video used for evaluating the relevance of the video to the text, where the representation itself is a function of the text it is evaluated for. As such, the input text may be used to weigh or attend to different frames of the video in determining the text-conditioned video embedding. The representation of the video may thus differ for different input texts for comparison. The text-conditioned video embedding may be determined in various ways, such as with a set of the most-similar frames to the input text (the top-k frames) or may be based on an attention function based on query, key, and value projections.

Abstract: This application provides a communication method and a communications device. One example method includes: receiving, by a first communications device, first information from a third communications device; and sending, by the third communications device, the first information to the first communications device.

Abstract: An image retrieval system receives an image for which to identify relevant images from an image repository. Relevant images may be of the same environment or object and features and other characteristics. Images in the repository are represented in an image retrieval graph by a set of image nodes connected by edges to other related image nodes with edge weights representing the similarity of the nodes to each other. Based on the received image, the image traversal system identifies an image in the image retrieval graph and alternatively explores and traverses (also termed “exploits”) the image nodes with the edge weights. In the exploration step, image nodes in an exploration set are evaluated to identify connected nodes that are added to a traversal set of image nodes. In the traversal step, the relevant nodes in the traversal set are added to the exploration set and a query result set.

Abstract: The present disclosure relates to the field of wireless communications technologies, relates to a signal sending device, a signal receiving device, a symbol timing synchronization method, and a system, and resolves a problem that complexity of symbol timing synchronization performed by a terminal with relatively low crystal oscillator accuracy is high. In a receiving device, a receiving module receives a synchronization signal including a first signal and a second signal. The first signal includes N1 generalized ZC sequences, and the second signal includes N2 generalized ZC sequences. The second signal is used to distinguish different cells or different cell groups. There are at least two generalized ZC sequences with different root indexes in (N1+N2) generalized ZC sequences.

Abstract: This application provides a communication method and a communications device. One example method includes: receiving, by a first communications device, first information from a third communications device; and sending, by the third communications device, the first information to the first communications device.

Abstract: An object detection model and relationship prediction model are jointly trained with parameters that may be updated through a joint backbone. The offset detection model predicts object locations based on keypoint detection, such as a heatmap local peak, enabling disambiguation of objects. The relationship prediction model may predict a relationship between detected objects and be trained with a joint loss with the object detection model. The loss may include terms for object connectedness and model confidence, enabling training to focus first on highly-connected objects and later on lower-confidence items.

Abstract: A communication method and a communications apparatus are provided. The communication method includes: sending, by a terminal device, a first indication message, where the first indication message is used to indicate a first time type and/or a first time precision, or the first indication message is used to indicate an access network device to send time information to the terminal device; receiving, by the terminal device, the time information; and synchronizing, by the terminal device, a time of the terminal device based on the time information. Correspondingly, a communications apparatus is further provided. According to the embodiments of this application, the terminal device can obtain, based on requirements of different application scenarios, a time type and/or time precision preferred by the terminal device.

Abstract: This application provides a communication method and a communications device. The method includes: obtaining, by a first communications device, authorization information, where the authorization information indicates that a second communications device is a device that needs to perform time synchronization; and providing, by the first communications device, time information for the second communications device based on the authorization information; or obtaining, by the first communications device, authorization information, where the authorization information indicates that the second communications device is not a device that needs to perform time synchronization; and skipping, by the first communications device, providing time information for the second communications device based on the authorization information, to avoid broadcasting the time information to all communications devices, so that a time synchronization service can be provided for a specific communications device.

Abstract: A content retrieval system uses a graph neural network architecture to determine images relevant to an image designated in a query. The graph neural network learns a new descriptor space that can be used to map images in the repository to image descriptors and the query image to a query descriptor. The image descriptors characterize the images in the repository as vectors in the descriptor space, and the query descriptor characterizes the query image as a vector in the descriptor space. The content retrieval system obtains the query result by identifying a set of relevant images associated with image descriptors having above a similarity threshold with the query descriptor.