An electronic device includes a memory to store neural network model trained for classification tasks of real-time applications. The neural network model is trained with plurality of training data points. The electronic device includes circuitry to retrieve a plurality of external data points. The electronic device applies the neural network model on the plurality of external data points to determine a plurality of impact scores for each external data point. The plurality of impact scores indicates amount of contribution of each training data point towards a prediction of each external data point. The electronic device selects a set of external data points based on the plurality of impact scores. The electronic device updates the plurality of training data points with the set of external data points to generate a second plurality of training data points and re-trains the neural network model based on the second plurality of training data points.

A computer-implemented method of detecting logos in a graphical rendering may comprise detecting, using a first and a second trained object detector, logos in the graphical rendering and outputting a first and a second list of detections and filtering, using at least a first and a second prior performance-based filter, the received first and second lists of detections into a first group of kept detections, a second group of discarded detections and a third group of detections. Detections in the third group of detections may be clustered in at least one cluster comprising detections that are of a same class and that are generally co-located within the electronic image. A cluster score may then be assigned to each cluster. A set of detections of logos in the graphical rendering may then be output, the set comprising the detections in the first group and a detection from each of the clusters whose assigned cluster score is greater than a respective threshold.

An image parsing method includes obtaining feature information of an initial image, parsing first feature information in the feature information using a first channel to obtain a first prediction result, parsing second feature information in the feature information using a second channel to obtain a second prediction result, where a size of the first feature information meets a first size range, a size of the second feature information meets a second size range, and the first size range is less than the second size range, and outputting the first prediction result and the second prediction result as a parsing result of the initial image.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for state and event monitoring. In some implementations, images captured by a camera are obtained, the images depicting an area of a property. Two or more images of the images are provided to a machine learning model. An output of the machine learning model is obtained, the output corresponding to the two or more images. One or more potential states of the area of the property are determined using the output of the machine learning model, each state of the one or more potential states corresponding to an image in the two or more images. An action is performed based on the one or more potential states.

The present embodiments relate to selection and execution of one or more output actions relating to a modification of at least one feature of a vehicle. A series of sensors on a vehicle can acquire data that can be used to identify vehicle environment characteristics indicative of a status of a vehicle environment and an emotional state of the user. The vehicle environment characteristics and the emotional state can be processed using a user model that corresponds to a user to generate one or more selected output actions. The output actions can be executed on the vehicle to increase user experience. The output actions can relate to any of entertainment features, safety features, and/or comfort features of the vehicle.

This application relates to the field of artificial intelligence, and specifically, to the field of computer vision. The method includes: performing feature extraction on an image to obtain a basic feature map of the image; determining a proposal of a region possibly including a pedestrian in the image; processing the basic feature map of the image to obtain an object visibility map in which a response to a pedestrian visible part is greater than a response to a pedestrian blocked part and a background part; performing weighted summation processing on the object visibility map and the basic feature map to obtain an enhanced feature map of the image; and determining, based on the proposal of the image and the enhanced feature map of the image, a bounding box including a pedestrian in the image and a confidence level of the bounding box including the pedestrian in the image.

Systems, apparatuses and methods may provide for technology that identifies a plurality of segments based on semantic features and instance features associated with a scene, fuses the plurality of segments into a plurality of instances, and selects classification labels for the plurality of instances. In one example, the plurality of segments is fused into the plurality of instances via a learnable self-attention based network.

Gait, the walking pattern of individuals, is one of the important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as gait features. These methods suffer from degraded recognition performance when handling confounding variables, such as clothing, carrying and viewing angle. To remedy this issue, this disclosure proposes to explicitly disentangle appearance, canonical and pose features from RGB imagery. A long short-term memory integrates pose features over time as a dynamic gait feature while canonical features are averaged as a static gait feature. Both of them are utilized as classification features.

The present application provides an image processing method and an image processing system. The image processing method includes: obtaining a first image matrix; generating a first classified image matrix, wherein the first classified image matrix Includes a plurality of parts corresponding to a plurality of classification; obtaining a plurality of weightings, for a first image process, corresponding to the plurality of parts of the first classified image matrix, and generating a first weighting matrix accordingly; and performing the first image process upon the first image matrix according to the first weighting matrix to generate a first processed image matrix.

An image processing system for categorising the colour of an item is disclosed. The system comprises processing means configured to: process an image of an item to extract a portion of the image where the item is located; determine a first average colour value of a plurality of colour values associated with the portion of the image where the item is located; map the average colour value to one of a plurality of predetermined colour definitions based on a plurality of colour ranges associated with each colour definition; and categorise the colour of the item according to the mapping.