Abstract: In certain embodiments, training of a neural network or other prediction model may be facilitated via live stream concept association. In some embodiments, a live video stream may be loaded on a user interface for presentation to a user. A user selection related to a frame of the live video stream may be received via the user interface during the presentation of the live video stream on the user interface, where the user selection indicates a presence of a concept in the frame of the live video stream. In response to the user selection related to the frame, an association of at least a portion of the frame of the live video stream and the concept may be generated, and the neural network or other prediction model may be trained based on the association of at least the portion of the frame with the concept.

Abstract: Systems, methods and computer program code are provided to perform visual searches.

Abstract: A system for optimizing results of processed assets for provision to software applications based on determined sequences of operation is disclosed, the system having a cloud-based engine and a plurality of models that are each usable by the engine to provide artificial intelligence in connection with software applications. Multiple software extensions are executed by the engine in accordance with a respective model for at least one of the general-purpose software applications. Input data are processed as a function of at least one of the models and a set of the plurality of extensions, wherein a given sequence of executing the set of extensions on one of the inputs impacts results provided by the engine. The engine is configured by executing each of the extensions in different sequences to grade a respective degree of inference and selecting an optimum sequence, which is communicated to the general-purpose software application.

Abstract: Systems, methods and computer program code to propose annotations are provided which include identifying an input, applying a grouping model to the input to predict at least a first grouping concept associated with the input, comparing the at least first grouping concept to a set of relationship data to select at least a first ranking model, applying the at least first ranking model to the input to predict at least a first ranking concept associated with the input, and causing a user interface to display the input, the at least first grouping concept and the at least first ranking concept to a user as proposed annotations of the input.

Abstract: In some embodiments, user-selectable/connectable model representations may be provided via a user interface to facilitate artificial intelligence development. The model representations may comprises first and second machine learning model (ML) representations corresponding to first and second ML models, and non-ML model representations corresponding to non-ML models. Based on user input indicating selection of the first and second ML model representations and a non-ML model representation corresponding to a non-ML model, at least a portion of a software application may be generated such that the software application comprises (i) an instance of the first ML model, an instance of the second ML model, and an instance of the non-ML model and (ii) an input/output data path between the instance of the first ML model and at least one other instance, the at least one other instance comprising the instance of the second ML model or the instance of the non-ML model.

Abstract: A system for browsing, searching and/or viewing video content includes at least one user device and a server computer operably connected to the at least one user device. The server computer includes at least one processor operably connected to an electronic storage device, and the at least one processor is programmed with computer program instructions that, when executed, cause the server computer to present a first video on a user interface to the at least one user device, wherein the user interface presents scenes of the first video and semantic labels associated with the scenes of the first video, and wherein the user interface further presents confidence parameters associated with the scenes of the first video and the semantic labels.

Abstract: In some embodiments, reduction of computational resource usage related to image labeling and/or segmentation may be facilitated. In some embodiments, a collection of images may be used to train one or more prediction models. Based on a presentation of an image on a user interface, an indication of a target quantity of superpixels for the image may be obtained. The image may be provided to a first prediction model to cause the prediction model to predict a quantity of superpixels for the image. The target quantity of superpixels may be provided to the first model to update the first model's configurations based on (i) the predicted quantity and (ii) the target quantity. A set of superpixels may be generated for the image based on the target quantity, and segmentation information related to the superpixels set may be provided to a second prediction model to update the second model's configurations.

Abstract: In certain embodiments, training of a prediction model (e.g., recognition or other prediction model) may be facilitated via a training set based on one or more logos or other graphics. In some embodiments, graphics information associated with a logo or graphic (e.g., to be recognized via a recognition model) may be obtained. Media items (e.g., images, videos, etc.) may be generated based on the graphics information, where each of the media items includes (i) content other than the logo and (ii) a given representation of the logo integrated with the other content. In some embodiments, the media items may be processed via the recognition model to generate predictions (related to recognition of the logo or graphic for the media items). The recognition model may be updated based on (i) the generated predictions and (ii) corresponding reference indications (related to recognition of the logo for the media items).

Abstract: A system for optimizing results of processed assets for provision to software applications based on determined sequences of operation is disclosed, the system having a cloud-based engine and a plurality of models that are each usable by the engine to provide artificial intelligence in connection with software applications. Multiple software extensions are executed by the engine in accordance with a respective model for at least one of the general-purpose software applications. Input data are processed as a function of at least one of the models and a set of the plurality of extensions, wherein a given sequence of executing the set of extensions on one of the inputs impacts results provided by the engine. The engine is configured by executing each of the extensions in different sequences to grade a respective degree of inference and selecting an optimum sequence, which is communicated to the general-purpose software application.

Abstract: Systems and methods for browsing, searching, and/or viewing video with associated semantic labels via a user interface are presented herein. Presentation of a user interface may be effectuated. The user interface may be configured to display scenes of one or more videos and/or one or more semantic labels associated with the scenes. A first scene associated with a first video and a first semantic label associated with the first scene may be displayed in the user interface. Playback of the first video in the user interface may cause one or more changes in the display of semantic labels over time, such that responsive to playback of the first video including display of a second scene after the first scene, a second semantic label is displayed and the first semantic label is no longer displayed. The second semantic label may be associated with the second scene.

Abstract: In certain embodiments, content items may be obtained, where each of the content items may include multiple data types. Machine learning models may be caused to be trained based on the content items to map data in a vector space by providing at least a first portion of each of the content items as input to at least one of the machine learning models and providing at least a second portion of each of the content items as input to at least another one of the machine learning models. A search request for results may be obtained, where the search request includes search parameters. One or more locations within the vector space may be predicted (e.g., by one or more of the machine learning models) based on the search parameters. Information (indicating content items mapped to or proximate the predicted locations) may be provided as a request response.

Abstract: In certain embodiments, training of a neural network or other prediction model may be facilitated via live stream concept association. In some embodiments, a live video stream may be loaded on a user interface for presentation to a user. A user selection related to a frame of the live video stream may be received via the user interface during the presentation of the live video stream on the user interface, where the user selection indicates a presence of a concept in the frame of the live video stream. In response to the user selection related to the frame, an association of at least a portion of the frame of the live video stream and the concept may be generated, and the neural network or other prediction model may be trained based on the association of at least the portion of the frame with the concept.

Abstract: In certain embodiments, a neural network may be trained to associated context information with multimedia items. In some embodiments, context predictions for multimedia items may be obtained via a neural network. A first multimedia item and a first task related to a first context prediction for the first multimedia item may be presented on a user interface. A user response to the first task may be obtained via the user interface. Based on the user response to the first task, prediction feedback related to the first context prediction or the first multimedia item may be provided to the neural network to cause the neural network to be updated based on the prediction feedback.

Abstract: In certain embodiments, automated routing of media items between user devices may be facilitated. In some embodiments, a routing computer system may automatically obtain images or videos from one or more sources. The routing computer system may perform object recognition on the contents of the images or videos to identify individuals or other objects in the images or videos. The routing computer system may assign first and second images or videos of the images or videos to a first media item group based on (i) the first and second images or videos having similar metadata and (ii) the object recognition identifying an individual or object in the first image or video and an individual or object in the second image or video that are similar to each other. The routing computer system may automatically transmit the first image or video to one or more user devices based on the assignment.

Abstract: In some embodiments, a service platform that facilitates artificial intelligence model and data collection and collection may be provided. Input/output information derived from machine learning models may be obtained via the service platform. The input/output information may indicate (i) first items provided as input to at least one model of the machine learning models, (ii) first prediction outputs derived from the at least one model's processing of the first items, (iii) second items provided as input to at least another model of the machine learning models, (iv) second prediction outputs derived from the at least one other model's processing of the second items, and (v) other inputs and outputs. The input/output information may be provided via the service platform to update a first machine learning model. The first machine learning model may be updated based on the input/output information being provided as input to the first machine learning model.

Abstract: In certain embodiments, media item search and machine learning system training may be facilitated. In some embodiments, a first set of media items may be obtained (based on performance of a query) and presented on a user interface. A user selection of a media item of the first set may be obtained, and the query may be updated based on the user-selected media item. A second set of media items may be obtained based on performance of the updated query, and media items of the second set may be assigned to a group based on their similarities with one another. A predicted name for the group may be determined via a machine learning system and presented on the user interface. A user-indicated update to the predicted name for the group may be obtained and provided to the machine learning system to train the machine learning system.

Abstract: Keyboard-based search of local and/or connected digital media items may be facilitated. A digital media item search interface may be presented in the same view as a messaging interface. The digital media item search interface may receive input such as from an on-screen keyboard to facilitate editing of user-provided search queries and submission of the user-provided search queries. The digital media item search interface may present digital media item tags relating to context information based on input received by the digital media item search query field. The digital media item search interface may present visual previews of local and/or connected digital media items corresponding to digital media item tags presented in the digital media item tag field. The digital media item search interface may receive user selections of individual digital media items to be communicated to one or more other users via the messaging interface.

Abstract: A previously trained classification model associated with the machine learning system is configured to process an input to generate i) a first prediction that represents a characteristic associated with the input, and ii) a representation of accuracy associated with the prediction. A retraining subsystem is configured to receive the input, the first prediction, and the representation of accuracy. The retraining subsystem processes the input to generate a prediction representing a characteristic. A sufficiency of certainty of the first prediction is determined based on at least the input, the first prediction, the measure of accuracy, and the second prediction. Based at least on the determined sufficiency the retraining subsystem causes the machine learning system to be automatically retrained, be retrained using the input with active learning or not retrained.

Abstract: In certain embodiments, a neural network may be trained to associated context information with multimedia items. In some embodiments, context predictions for multimedia items may be obtained via a neural network. A first multimedia item and a first task related to a first context prediction for the first multimedia item may be presented on a user interface. A user response to the first task may be obtained via the user interface. Based on the user response to the first task, prediction feedback related to the first context prediction or the first multimedia item may be provided to the neural network to cause the neural network to be updated based on the prediction feedback.

Abstract: In certain implementations, a user request to add a new concept may be received. A set of media item recommendations may be caused to be loaded on a user interface for presentation to a user responsive to the user request to add the new concept. The media item recommendation set may include a set of recommendations loaded on an on-screen portion of the user interface and a set of recommendations loaded on an off-screen portion of the user interface. The on-screen user interface portion is visible to the user at a first time. The off-screen user interface portion is not being visible to the user at the first time. A user selection of one or more recommendations of the on-screen recommendation set is received. The off-screen recommendation set may be caused to be updated on the user interface during the presentation of the media item recommendation set based on the user recommendation selection.