Abstract: Described are techniques for oblique image rectification. The techniques include receiving an original image depicting an oblique view of a circular object and pre-processing the original image into an edge image. The techniques further include generating, by a machine learning model based on the edge image, a heatmap including an ellipse formed by the oblique view of the circular object. The techniques further include computing ellipse parameters describing the ellipse of the heatmap. The techniques further include performing, using the ellipse parameters, an affine transformation on the original image to generate a rectified image, where the rectified image converts the ellipse to a circle.

Abstract: Dynamically adjusting, using artificial intelligence (AI), sensors and models of an autonomous roaming robotic device, which includes receiving data regarding an asset at a computer of a roaming robotic device from sensors on the robotic device. The robotic device identifies an asset at a location using the sensors, and the robotic device has instructions, received from a control system, to inspect the location or items at the location. The data is analyzed using the computer of the robotic device, and the analysis includes using historical data for the asset. An AI model is loaded using the computer of the robotic device, based on the identification of the asset. A sensor is selected using the computer of the robotic device, for conducting an inspection of the asset based on the analysis of the data and the AI model.

Abstract: Described are techniques for oblique image rectification. The techniques include receiving an original image depicting an oblique view of a circular object and pre-processing the original image into an edge image. The techniques further include generating, by a machine learning model based on the edge image, a heatmap including an ellipse formed by the oblique view of the circular object. The techniques further include computing ellipse parameters describing the ellipse of the heatmap. The techniques further include performing, using the ellipse parameters, an affine transformation on the original image to generate a rectified image, where the rectified image converts the ellipse to a circle.

Abstract: Described are techniques for oblique image rectification. The techniques include receiving an original image depicting an oblique view of a circular object and pre-processing the original image into an edge image. The techniques further include generating, by a machine learning model based on the edge image, a heatmap including an ellipse formed by the oblique view of the circular object. The techniques further include computing ellipse parameters describing the ellipse of the heatmap. The techniques further include performing, using the ellipse parameters, an affine transformation on the original image to generate a rectified image, where the rectified image converts the ellipse to a circle.

Abstract: Automated analog gauge reading is provided. The method comprises a computer system receiving input of an image and detecting at least one analog gauge in the image. The computer system corrects the orientation of the analog gauge in the image and detects scene text and tick labels on the analog gauge. The computer system determines a position of a pointer on the analog gauge relative to the scene text and outputs a gauge reading value based on an arithmetic progression of tick labels and angle of the pointer with respect to minimum and maximum values on the analog gauge.

Abstract: A system may receive an existing base set of knowledge, train a neural network on the base set of knowledge, deploy the neural network on a new data set, generate, using the deployment, instances of new knowledge, and validate the instances of new knowledge.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: A method, computer program product, and system include a processor(s) that engages, based on a request for an inference, from a group of sensors of multiple modalities at a physical location, sensor(s) of a main modality to provide data to a pipeline to generate the inference. The pipeline includes one or more machine learning models which generate the inference for a downstream task. The processor(s) obtains raw data from the sensor(s) of the main modality and applies an outlier detector to the raw data. Based on determining that there is an outlier the processor(s) automatically engages sensor(s) of at least one different modality than the main modality from the group of sensors of multiple modalities and obtains new raw data from the sensor(s) of the at least one different modality. The processor(s) applies the one or more machine learning models to the new raw data to derive the inference.

Abstract: Dynamically adjusting, using artificial intelligence (AI), sensors and models of an autonomous roaming robotic device, which includes receiving data regarding an asset at a computer of a roaming robotic device from sensors on the robotic device. The robotic device identifies an asset at a location using the sensors, and the robotic device has instructions, received from a control system, to inspect the location or items at the location. The data is analyzed using the computer of the robotic device, and the analysis includes using historical data for the asset. An AI model is loaded using the computer of the robotic device, based on the identification of the asset. A sensor is selected using the computer of the robotic device, for conducting an inspection of the asset based on the analysis of the data and the AI model.

Abstract: Optimizing sensing capabilities of a roaming robotic device using Artificial Intelligence (AI) includes receiving data at a control system having a computer from a robotic device. The control system communicating a policy to the robotic device for choosing navigation actions for the robotic device. The received data is analyzed using the control system for determining when the received data meets a threshold for determining quality of the data. The analysis can include generating a model based on the received data where the model includes vector representation of inputs detected by a sensor array at the location. In response to the received data at the control system not meeting the threshold for determining quality, the robotic device communicating with the control system to collaborate in updating the policy to choose a next action.

Abstract: Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.

Abstract: Systems and methods to analyze a person's social media photos or videos, such as those posted on Twitter, Facebook, Instagram, etc. and determine properties of their social life. Using information on the number of people appearing in the photos or videos, their ages, and genders, this method can predict whether the person is in a romantic relationship, has a close family, is a group person, or is single. This information is valuable for generating audiovisual content recommendations as well as for advertisers, because it allows targeting personalized advertisements to the person posting the photos. The described methods may be performed (and the advertisements or other content may be selected for recommendation) substantially in real-time as the user accesses a specific online resource.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: A method of generating a caption for a social media post is provided. The method may include receiving a social media post to be posted to a social media network; collecting reference data relevant to determining common activities occurring at a category of location associated with the social media post; inferring potential topics for captions from a topic inference model, based on the collected reference data associated with the social media post; setting parameters associated with a language model based on the inferred topic; and generating at least one caption for the social media post based on the identified language model, and the inferred topic.

Abstract: Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: A method associates social media messages with venues. A social network graph includes users, messages from users, and venues. The venues include multiple primary venues and a no-venue. A link between a message and the no-venue node indicates that the message is not associated with a primary venue. Training feature vectors are constructed that measure connectedness between messages and venues. The process trains a classifier to estimate probabilities that messages are associated with venues. A new social media message is received, and the process constructs a feature vector using the same features as the training vectors, measuring connectedness between the new message and the no-venue. The classifier computes a probability that the new message is associated with the no-venue. When the probability exceeds a predefined threshold, the new message is not associated with any of the primary venues. Otherwise, the new message is associated with one of the primary venues.

Abstract: Systems and methods disclosed herein associate images with business venues. An example method includes: receiving a first image and retrieving textual reviews and stored images that are associated with one or more candidate business venues. The method further includes: detecting, using trained visual detectors, a plurality of business-aware concepts in the first image and assessing likelihood that detected business-aware concepts are in the first image. The method additionally includes: (i) generating a first representation of the first image based on the likelihoods and one or more term vectors for high-scoring concepts and (ii) receiving second representations of each candidate based on the retrieved textual reviews and stored images. In accordance with determining that the first representation is most similar to a respective second representation of a first candidate, the method includes: (i) associating the first image with the first candidate and (ii) providing an indication of the association.

Abstract: A method for automatically selecting thematically representative music is disclosed. A processor is used for using a theme-related keyword to search a keyword-indexed video repository to retrieve videos associated with the theme-related keyword; analyzing the retrieved videos to select videos with music; and extracting music tracks and features from the selected videos. The method further includes selecting representative music related to the theme from the extracted music tracks using the extracted features; and storing the selected representative music in a processor accessible memory.