Abstract: Devices and techniques are generally described for learning personalized concepts for natural language processing. In various examples, a first natural language input may be received. In some examples, a determination may be made that the first natural language input comprises non-actionable slot data. A dialog session may be initiated with the user. In some examples, first slot data that is indicated by the user during the dialog session may be determined. In various examples, data representing the first slot data may be stored in a database in association with the first natural language input.

Abstract: Devices and techniques are generally described for class-agnostic object detection. In some examples, a first frame of image data comprising a first plurality of pixels may be received. First class-agnostic feature data representing the first plurality of pixels may be generated. A first object detection component may be used to determine that the first plurality of pixels corresponds to an arbitrary object represented in the first frame of image data based at least in part on the first class-agnostic feature data. Class-agnostic data indicating that the first plurality of pixels in the first frame of image data corresponds to the arbitrary object may be generated.

Abstract: Techniques for using a federated learning framework to update machine learning models for spoken language understanding (SLU) system are described. The system determines which labeled data is needed to update the models based on the models generating an undesired response to an input. The system identifies users to solicit labeled data from, and sends a request to a user device to speak an input. The device generates labeled data using the spoken input, and updates the on-device models using the spoken input and the labeled data. The updated model data is provided to the system to enable the system to update the system-level (global) models.

Abstract: A system can operate a speech-controlled device in a mode where the speech-controlled device determines that an utterance is directed at the speech-controlled device using image data showing the user speaking the utterance. If the user is directing the user's gaze at the speech-controlled device while speaking, the system may determine the utterance is system directed and thus may perform further speech processing based on the utterance. If the user's gaze is directed elsewhere, the system may determine the utterance is not system directed (for example directed at another user) and thus the system may not perform further speech processing based on the utterance and may take other actions, for example discarding audio data of the utterance.

Abstract: In a method and system for generating vehicle image data, and to improve the generation of vehicle image data, 2D object information having at least 2D object data and object location data of one or more objects, perspective vehicle image data, and vehicle image location data for at least a portion of said vehicle image data are obtained. The object location data is compared with said vehicle image location data; and in case said object location data corresponds to said image location data, said 2D object data is correlated with said perspective vehicle image data using the object location data and the vehicle image location data to obtain a segmented vehicle image dataset.

Abstract: An in-vehicle system for identifying exit-only lanes and shared exit lanes on a roadway having a first camera for obtaining image data regarding lane markings on the roadway, a second camera for obtaining image data regarding exit signs, a lane marking detection module for detecting lane markings on the roadway, an exit sign detection module for detecting exit signs, and an exit sign analyzer for detecting arrows on the detected exit signs. The in-vehicle system categorizes detected lane markings as one of standard frequency dashed lane markings, high frequency dashed lane markings, and solid lane markings, and identifies an exit-only lane and a shared exit lane in response to the categorizations of the detected lane markings and characteristics of the detected arrows.

Abstract: An in-vehicle system for identifying exit-only lanes and shared exit lanes on a roadway having a first camera for obtaining image data regarding lane markings on the roadway, a second camera for obtaining image data regarding exit signs, a lane marking detection module for detecting lane markings on the roadway, an exit sign detection module for detecting exit signs, and an exit sign analyzer for detecting arrows on the detected exit signs. The in-vehicle system categorizes detected lane markings as one of standard frequency dashed lane markings, high frequency dashed lane markings, and solid lane markings, and identifies an exit-only lane and a shared exit lane in response to the categorizations of the detected lane markings and characteristics of the detected arrows.

Abstract: In a method and system for generating vehicle image data, and to improve the generation of vehicle image data, 2D object information having at least 2D object data and object location data of one or more objects, perspective vehicle image data, and vehicle image location data for at least a portion of said vehicle image data are obtained. The object location data is compared with said vehicle image location data; and in case said object location data corresponds to said image location data, said 2D object data is correlated with said perspective vehicle image data using the object location data and the vehicle image location data to obtain a segmented vehicle image dataset.

Abstract: An in-vehicle system for identifying exit-only lanes and shared exit lanes on a roadway having a first camera for obtaining image data regarding lane markings on the roadway, a second camera for obtaining image data regarding exit signs, a lane marking detection module for detecting lane markings on the roadway, an exit sign detection module for detecting exit signs, and an exit sign analyzer for detecting arrows on the detected exit signs. The in-vehicle system categorizes detected lane markings as one of standard frequency dashed lane markings, high frequency dashed lane markings, and solid lane markings, and identifies an exit-only lane and a shared exit lane in response to the categorizations of the detected lane markings and characteristics of the detected arrows.

Abstract: A system and method for early detection of turning intent and automatic actuation of a turn signal in a vehicle is provided. The system has an image recognition system and turn determination unit for identifying turn predictors and processing them to determine if a turn is about to happen. In response, a corresponding turn signal is automatically initiated for a predetermined period of time, and further vehicle systems can be updated.

Abstract: A system and method for early detection of turning intent and automatic actuation of a turn signal in a vehicle is provided. The system has an image recognition system and turn determination unit for identifying turn predictors and processing them to determine if a turn is about to happen. In response, a corresponding turn signal is automatically initiated for a predetermined period of time, and further vehicle systems can be updated.

Abstract: An in-vehicle system for determining whether a vehicle has moved off of a main roadway and into an exit lane. A navigation unit determines that an exit is approaching on a first side of the vehicle, and a camera obtains image data regarding lane markings and exit signs in response to a notification that the exit is approaching. An image processor identifies predetermined patterns among the lane markings, including V-shaped patterns or Y-shaped patterns. The system determines that the vehicle has moved into the exit lane in response to an identification of one of the predetermined patterns on a second side of the vehicle opposite the first side of the vehicle. The system may verify its determination based on recognition of an exit sign on the second side of the vehicle.

Abstract: An in-vehicle system for identifying exit-only lanes and shared exit lanes on a roadway having a first camera for obtaining image data regarding lane markings on the roadway, a second camera for obtaining image data regarding exit signs, a lane marking detection module for detecting lane markings on the roadway, an exit sign detection module for detecting exit signs, and an exit sign analyzer for detecting arrows on the detected exit signs. The in-vehicle system categorizes detected lane markings as one of standard frequency dashed lane markings, high frequency dashed lane markings, and solid lane markings, and identifies an exit-only lane and a shared exit lane in response to the categorizations of the detected lane markings and characteristics of the detected arrows.

Abstract: An approach to computation of kernel descriptors is accelerated using precomputed tables. In one aspect, a fast algorithm for kernel descriptor computation that takes O(1) operations per pixel in each patch, based on pre-computed kernel values. This speeds up the kernel descriptor features under consideration, to levels that are comparable with D-SIFT and color SIFT, and two orders of magnitude faster than STIP and HoG3D. In some examples, kernel descriptors are applied to extract gradient, flow and texture based features for video analysis. In tests of the approach on a large database of internet videos used in the TRECVID MED 2011 evaluations, the flow based kernel descriptors are up to two orders of magnitude faster than STIP and HoG3D, and also produce significant performance improvements. Further, using features from multiple color planes produces small but consistent gains.

Abstract: An in-vehicle system for determining whether a vehicle has moved off of a main roadway and into an exit lane. A navigation unit determines that an exit is approaching on a first side of the vehicle, and a camera obtains image data regarding lane markings and exit signs in response to a notification that the exit is approaching. An image processor identifies predetermined patterns among the lane markings, including V-shaped patterns or Y-shaped patterns. The system determines that the vehicle has moved into the exit lane in response to an identification of one of the predetermined patterns on a second side of the vehicle opposite the first side of the vehicle. The system may verify its determination based on recognition of an exit sign on the second side of the vehicle.

Abstract: An approach to segmentation or clustering of a set of elements combines separate procedures and uses training data for those procedures on labeled data. This approach is applied to elements being components of an image of text (e.g., printed or handwritten). In some examples, the elements are connected sets of pixels. In images of text, the clusters can correspond to individual lines. The approach provides improved clustering performance as compared to any one of the procedures taken alone.

Abstract: A computationally efficient approach to determining inner products between feature vectors is provided that eliminates or reduces the need for multiplication, and more specifically, provides an efficient and accurate basis selection for techniques such as Orthogonal Matching Pursuit.

Abstract: Distributional information for a set of ? vectors is determined using a sparse basis selection approach to representing an input image or video. In some examples, this distributional information is used for a classification task.

Abstract: Distributional information for a set of ? vectors is determined using a sparse basis selection approach to representing an input image or video. In some examples, this distributional information is used for a classification task.

Abstract: A computationally efficient approach to determining inner products between feature vectors is provided that eliminates or reduces the need for multiplication, and more specifically, provides an efficient and accurate basis selection for techniques such as Orthogonal Matching Pursuit.