A control apparatus includes a communication unit configured to receive motion data indicating motion of at least one user outside a vehicle that moves along a route including at least one road, and a controller configured to make a boarding determination of determining whether the at least one user will board the vehicle based on the motion data received by the communication unit and execute, upon determining in the boarding determination that the at least one user will board the vehicle, control for opening a door of the vehicle.

An information processing method performed by a computer includes: obtaining prediction results that are results of prediction performed by predictors on same input data; obtaining, for each of the prediction results, an influence that the input data had on the prediction result; determining, based on the prediction results, one or more combinations of the prediction results; and presenting, side by side or by superposition, using a presentation device, influences obtained for prediction results that are included in the prediction results and are in a same combination among the one or more combinations.

Provided is an image recognition device. The image recognition device includes a frame data change detector that sequentially receives a plurality of frame data and detects a difference between two consecutive frame data, an ensemble section controller that sets an ensemble section in the plurality of frame data, based on the detected difference, an image recognizer that sequentially identifies classes respectively corresponding to a plurality of section frame data by applying different neural network classifiers to the plurality of section frame data in the ensemble section, and a recognition result classifier that sequentially identifies ensemble classes respectively corresponding to the plurality of section frame data by combining the classes in the ensemble section.

An image processing method for extracting a frame from a moving image. The method includes determining a type of the moving image, extracting a frame from the moving image, based on a result of the determination and information indicating a plurality of predetermined types of frame features, the extracted frame having at least one of the plurality of predetermined types of frame features, wherein the plurality of predetermined types of frame features correspond to a plurality of image-capturing scenes, a sorting step of sorting a plurality of frames, which include the frame extracted in the extracting step, into a plurality of frame groups according to the type of the moving image that is determined in the determining step, and displaying the frame extracted in the extracting step on a display device. The plurality of frame groups are displayed on the display device based on the sorting.

There is provided a method of defect detection on a specimen and a system thereof. The method includes: obtaining a runtime image representative of at least a portion of the specimen; processing the runtime image using a supervised model to obtain a first output indicative of the estimated presence of first defects on the runtime image; processing the runtime image using an unsupervised model component to obtain a second output indicative of the estimated presence of second defects on the runtime image; and combining the first output and the second output using one or more optimized parameters to obtain a defect detection result of the specimen.

Methods and systems are described for generating dynamic conversational responses using two-tier machine learning models. The dynamic conversational responses may be generated in real time and reflect the likely goals and/or intents of a user. The two-tier machine learning model may include a first tier that determines an intent cluster based on a feature input, and a second tier that determines a specific intent from the cluster.

A method and system for classifying image features using a neural network is provided. The method includes training the neural network using triplet loss processes including receiving an anchor image, selecting a positive image and a negative image, generating a image embedding associated with each of the anchor image, the positive image, and the negative image, classifying image features extracted from the anchor image based on the image embedding of the anchor image, determining an image label location associated with the classified image features, extracting features associated with the determined image label location, and classifying the features associated with the determined image label location; and combining the multi-label loss with localized image classification loss and the triplet loss using a weighted loss sum.

An item classification system for use in an item handling system is disclosed. The classification system comprises processing means configured to: process an image of an item to determine, based on a first model (101), one or more predetermined first item types, each first item type defined by one or more first item characteristics; process the image to determine, based on the first model (101), a first probability associated with each first item type wherein each first probability is indicative of the likelihood that the item has the first characteristics defining each determined first item type; process the image to determine, based on a second model (103), one or more predetermined second item types, each second item type defined by one or more second item characteristics; process the image to determine, based on the second model (103), a second probability associated with each second item type wherein each second probability is indicative of the likelihood that the item has the second characteristics defining each second item type; and classify the item according to each first item type and each second item type and the probability associated with each first item type and the probability associated with each second item type.

A system receives an observation probability distribution function associated with a target object that was detected by sensors of an autonomous vehicle. The system identifies a target attribute of the target object, and detects a target attribute value associated with the target object. The system determines a first probability distribution function representing a probability of the autonomous vehicle detecting an object having an object label, determines a second probability distribution function defining a probability of the autonomous vehicle detecting the target attribute, determines a third probability distribution function defining a probability of the target attribute being present for the target object based on the target attribute value, and determines an attribute probability distribution function defining a probability that the target attribute is actually present for the target object. The system executes vehicle control instructions that cause the autonomous vehicle to adjust driving operations based on the attribute probability distribution function.

Example aspects of the present disclosure are directed to computing systems and methods that perform whole person association with face screening and/or face hallucination. In particular, one aspect of the closure is directed to a multi-headed person and face detection model that performs both face and person detection in one model. Each of the face and person detection can find landmarks or other pose information and also a confidence score. The pose information for the face and person detections can be used to select certain face and person detections to associate together as a whole person detection, which can be referred to as an “appearance.”