Abstract: Off-line deep neural network operations on client computing platforms may be enabled by cooperative machine learning across multiple client computing platforms and the cloud. A given client computing platform may include a client-side machine learning model configured to facilitate deep neural network operations on structured data. The operations may be performed by a client application installed on the given client computing platform. The client application may locally access the client-side machine learning model in order to perform the operations. Deep neural network operations on structured data may be performed at one or more servers. Sharing of model states may be facilitated between the cloud machine learning model and the client-side machine learning model. The cloud machine learning model may be improved, at one or more servers, based on usage of the application and user interactions with the given client computing platform.

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: 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: 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, training of a prediction model (e.g., recognition or other prediction model) may be facilitated via a training set generated 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. Training media items (e.g., images, videos, etc.) may be generated based on the graphics information, where each of the training media items includes (i) content other than the logo and (ii) a given representation of the logo integrated with the other content. The training media items may be processed via the recognition model to generate predictions (related to recognition of the logo or graphic for the training 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 training media items).

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 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, 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: A system configured for learning new trained concepts used to retrieve content relevant to the concepts learned. The system may comprise one or more hardware processors configured by machine-readable instructions to obtain one or more digital media items. The one or more hardware processors may be further configured to obtain an indication conveying a concept to be learned from the one or more digital media items. The one or more hardware processors may be further configured to receive feedback associated with individual ones of the one or more digital media items. The one or more hardware processors may be configured to obtain individual neural network representations for the individual ones of the one or more digital media items. The one or more hardware processors may be configured to determine a trained concept based on the feedback and the neural network representations of the one or more digital media items.

Abstract: A system configured for learning new trained concepts used to retrieve content relevant to the concepts learned. The system may comprise one or more hardware processors configured by machine-readable instructions to obtain one or more digital media items. The one or more hardware processors may be further configured to obtain an indication conveying a concept to be learned from the one or more digital media items. The one or more hardware processors may be further configured to receive feedback associated with individual ones of the one or more digital media items. The one or more hardware processors may be configured to obtain individual neural network representations for the individual ones of the one or more digital media items. The one or more hardware processors may be configured to determine a trained concept based on the feedback and the neural network representations of the one or more digital media items.

Abstract: Systems and methods for facilitating searching, labeling, and/or filtering of digital media items are described. Users may provide queries for digital media items. Results from a search may be presented to the users. A user may provide selection of one or more displayed digital media items. A user selection may provide a digital media item exemplar that may be used to update the user-provided queries. Further searches based on the updated queries may be performed. A repository of digital media items may be queried both with an original text query supplied by a user and an updated query based user selection of digital media items returned from the original text query search. A user may be able to refine an initial text, image, and/or other query without having to know additional search terms.

Abstract: Context information may be associated with multimedia items. One or more multimedia items may be obtained from a repository, the multimedia items(s) including one or more of an image, a video, audio, a text file, combinations thereof, and/or other considerations. Predicted context information may be associated with individual ones of the multimedia items. Labels and/or other context information associated with multimedia item(s) may be stored as metadata associated with the multimedia item(s). A user interface may be configured to display one or more of the obtained multimedia items and the predicted context information associated with the one or more obtained multimedia items. Entry and/or selection may be obtained from one or more users of an addition, removal, correction, and/or confirmation of the predicted context information for individual ones of the multimedia items and/or groups of multimedia items displayed in the user interfaces.

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

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 and methods for facilitating the sharing of digital media items between source computing platforms and end computing platforms based on information associated with and/or derived from the media items are presented herein. Automatic routing of a media item to one or more users may be in response to obtaining digital media items, such as a photo, a video, an audio file, or text file, from one or more media item source computing platforms, obtaining information associated with individual ones of the media items, and associating one or more media items with one or more groups based on the obtained information. Other aspects of the disclosure may be related to making media items easy to locate, generating notifications to one or more users who have indicated interest in a media item and/or media item group, suggesting that a media item be shared with one or more users, and/or other features.