Abstract: Embodiments described herein provide a system for generating synthetic images with localized editing. During operation, the system obtains a source image and a target image for image synthesis and selects a semantic element from the source image. The semantic element indicates a semantically meaningful part of an object depicted in the source image. The system then determines the style information associated with the source and target images. Subsequently, the system generates a synthetic image by transferring the style of the semantic element from the source image to the target image based on the feature representations. In this way, the system can facilitate localized editing of the target image.

Abstract: A method of labeling a dataset of input samples for a machine learning task includes selecting a plurality of pre-trained machine learning models that are related to a machine learning task. The method further includes processing a plurality of input data samples through each of the pre-trained models to generate a set of embeddings. The method further includes generating a plurality of clusterings from the set of embeddings. The method further includes analyzing, by a processing device, the plurality of clusterings to extract superclusters. The method further includes assigning pseudo-labels to the input samples based on analysis.

Abstract: Embodiments described herein provide a system for facilitating dynamic assistance to a user in an augmented reality (AR) environment of an AR device. During operation, the system detects a first element of an object using an object detector, wherein the object is associated with a task and the first element is associated with a step of the task. The system then determines an orientation and an alignment of the first element in the physical world of the user, and an overlay for the first element. The overlay can distinctly highlight one or more regions of the first element and indicate how the first element fits in the object. The system then applies the overlay to the one or more regions of the first element at the determined orientation in the AR environment.

Abstract: Embodiments described herein provide a system for facilitating dynamic assistance to a user in an augmented reality (AR) environment of an AR device. During operation, the system detects a first element of an object using an object detector, wherein the object is associated with a task and the first element is associated with a step of the task. The system then determines an orientation and an alignment of the first element in the physical world of the user, and an overlay for the first element. The overlay can distinctly highlight one or more regions of the first element and indicate how the first element fits in the object. The system then applies the overlay to the one or more regions of the first element at the determined orientation in the AR environment.

Abstract: A method of monitoring user interactions with a networked device includes receiving image data associated with one or more images of a user, computing a plurality of visual features of the one or more images from the image data, and calculating, by a processing device, a style characteristic from the plurality of visual features. The method include calculating, by the processing device, a lifestyle characteristic based on the style characteristic and calculating, by the processing device, a user preference based on the lifestyle characteristic. The method includes determining a recommendation of a product based on the user preference and providing the recommendation to a user device associated with the user.

Abstract: At least one activity history for a plurality of entities is received. The at least one activity history comprises at least two events. An inter-event gap distribution is learned using the at least one activity history for the plurality of entities. A current activity history for a current entity is received. A probability of at least one of an onset and a termination related to the current activity history is determined based on the learned inter-gap distribution. An output is produced based on the determined probability.

Abstract: One embodiment provides a system that facilitates efficient collection of training data. During operation, the system obtains, by a recording device, a first image of a physical object in a scene which is associated with a three-dimensional (3D) world coordinate frame. The system marks, on the first image, a plurality of vertices associated with the physical object, wherein a vertex has 3D coordinates based on the 3D world coordinate frame. The system obtains a plurality of second images of the physical object in the scene while changing one or more characteristics of the scene. The system projects the marked vertices on to a respective second image to indicate a two-dimensional (2D) bounding area associated with the physical object.

Abstract: Embodiments described herein provide a system for assessing the surface of an object for detecting contamination or other defects. During operation, the system obtains an input image indicating the contamination on the object and generates a synthetic image using an artificial intelligence (AI) model based on the input image. The synthetic image can indicate the object without the contamination. The system then determines a difference between the input image and the synthetic image to identify an image area corresponding to the contamination. Subsequently, the system generates a contamination map of the contamination by highlighting the image area based on one or more image enhancement operations.

Abstract: Embodiments described herein provide a system for assessing the surface of an object for detecting contamination or other defects. During operation, the system obtains an input image indicating the contamination on the object and generates a synthetic image using an artificial intelligence (AI) model based on the input image. The synthetic image can indicate the object without the contamination. The system then determines a difference between the input image and the synthetic image to identify an image area corresponding to the contamination. Subsequently, the system generates a contamination map of the contamination by highlighting the image area based on one or more image enhancement operations.

Abstract: One embodiment provides a system that facilitates efficient collection of training data. During operation, the system obtains, by a recording device, a first image of a physical object in a scene which is associated with a three-dimensional (3D) world coordinate frame. The system marks, on the first image, a plurality of vertices associated with the physical object, wherein a vertex has 3D coordinates based on the 3D world coordinate frame. The system obtains a plurality of second images of the physical object in the scene while changing one or more characteristics of the scene. The system projects the marked vertices on to a respective second image to indicate a two-dimensional (2D) bounding area associated with the physical object.

Abstract: A system and method for selection and explanation of solutions is provided. A hierarchy of aggregation factors is maintained for evaluating at least a partial solution. Competing solutions are generated and each solution includes at least a partial solution. Scores are calculated for each of the aggregation factors for each competing solution. A total evaluation score is calculated for each competing solution based on the scores for at least one of the aggregation factors. The competing solution with the best evaluation score is selected and a gist is generated. The gist is a narrative comparing the selected solution with the non-selected solutions based on the at least one aggregation factor. The gist is provided to a user as a rationale for selection of the solution.

Abstract: Embodiments described herein provide a system for facilitating efficient dataset management. During operation, the system obtains a first dataset comprising a plurality of elements. The system then determines a set of categories for a respective element of the plurality of elements by applying a plurality of AI models to the first dataset. A respective category can correspond to an AI model. Subsequently, the system selects a set of sample elements associated with a respective category of a respective AI model and determines a second dataset based on the selected sample elements.

Abstract: Embodiments described herein provide a system for generating synthetic images with localized editing. During operation, the system obtains a source image and a target image for image synthesis and selects a semantic element from the source image. The semantic element indicates a semantically meaningful part of an object depicted in the source image. The system then determines the style information associated with the source and target images. Subsequently, the system generates a synthetic image by transferring the style of the semantic element from the source image to the target image based on the feature representations. In this way, the system can facilitate localized editing of the target image.

Abstract: Embodiments described herein provide a system for assessing the surface of an object for detecting contamination or other defects. During operation, the system obtains an input image indicating the contamination on the object and generates a synthetic image using an artificial intelligence (AI) model based on the input image. The synthetic image can indicate the object without the contamination. The system then determines a difference between the input image and the synthetic image to identify an image area corresponding to the contamination. Subsequently, the system generates a contamination map of the contamination by highlighting the image area based on one or more image enhancement operations.

Abstract: One embodiment provides a system that facilitates efficient collection of training data for training an image-detection artificial intelligence (AI) engine. During operation, the system obtains a three-dimensional (3D) model of a physical object placed in a scene, generates a virtual object corresponding to the physical object based on the 3D model, and substantially superimposes, in a view of an augmented reality (AR) camera, the virtual object over the physical object. The system can further configure the AR camera to capture a physical image comprising the physical object in the scene and a corresponding AR image comprising the virtual object superimposed over the physical object, and create an annotation for the physical image based on the AR image.

Abstract: One embodiment provides a method for facilitating real-world interaction with virtual reality. During operation, the system receives, by a computing device from a virtual reality device associated with a user, instructions to configure physical components, wherein for a first physical component at a first location, the instructions indicate a type and an orientation, and wherein for a second physical component located at a second location, the instructions indicate a type, a length of extension, and an angle. The system executes, by a pose-adjusting unit, the instructions, which involves: physically moving the first physical component to the indicated orientation at the first location; physically extending the second physical component from the second location by the indicated length; and physically rotating the extended second physical component by the indicated angle. The system renders, on the virtual reality device, the configured physical components.

Abstract: One embodiment provides a system that facilitates efficient collection of training data. During operation, the system obtains, by a recording device, a first image of a physical object in a scene which is associated with a three-dimensional (3D) world coordinate frame. The system marks, on the first image, a plurality of vertices associated with the physical object, wherein a vertex has 3D coordinates based on the 3D world coordinate frame. The system obtains a plurality of second images of the physical object in the scene while changing one or more characteristics of the scene. The system projects the marked vertices on to a respective second image to indicate a two-dimensional (2D) bounding area associated with the physical object.

Abstract: One embodiment can provide a system for augmenting perceptions of a machine sensing system. During operation, one or more sensors of the system can obtain sensory information associated with a physical system. The system can determine a state of a first component of the physical system based on the obtained sensory information; select, from a rule database, one or more logical rules associated with at least the first component; and augment a perception of the machine sensing system toward the physical system based on both the determined state of the first component and the selected one or more logical rules, thereby facilitating the machine sensing system to make a decision associated with the physical system.

Abstract: Embodiments described herein provide a system for facilitating dynamic assistance to a user in an augmented reality (AR) environment of an AR device. During operation, the system detects a first element of an object using an object detector, wherein the object is associated with a task and the first element is associated with a step of the task. The system then determines an orientation and an alignment of the first element in the physical world of the user, and an overlay for the first element. The overlay can distinctly highlight one or more regions of the first element and indicate how the first element fits in the object. The system then applies the overlay to the one or more regions of the first element at the determined orientation in the AR environment.

Abstract: One embodiment provides a system that facilitates efficient collection of training data. During operation, the system obtains, by a recording device, a first image of a physical object in a scene which is associated with a three-dimensional (3D) world coordinate frame. The system marks, on the first image, a plurality of vertices associated with the physical object, wherein a vertex has 3D coordinates based on the 3D world coordinate frame. The system obtains a plurality of second images of the physical object in the scene while changing one or more characteristics of the scene. The system projects the marked vertices on to a respective second image to indicate a two-dimensional (2D) bounding area associated with the physical object.