Abstract: A computer readable medium for sizing a product includes instructions, that when executed by at least one processor, cause a computing device to: retrieve from a webpage information on a product including product dimensions; present on a display of a client device a graphical button that upon access by a user activates a camera for capturing an image of an object positioned at a focal distance from the camera, the object having a surface; prompt the user to enter boundary information of an imaginary housing to be placed on the surface; generate the imaginary housing dimensions in two dimensions (2D) based on the boundary information and the focal distance; and determine whether the product fits within the imaginary housing by comparing the product dimensions against the imaginary housing dimensions.

Abstract: A system and method and for providing speech assistance during a virtual meeting includes receiving a request over a communication network to provide speech assistance during a virtual meeting between a plurality of participants and analyzing speech data of the virtual meeting, via a speech impediment detection engine, to detect a speech impediment for one of the plurality of participants. Upon detecting the speech impediment, an avatar is automatically generated for the participant experiencing speech impediment and the avatar is synchronized with the participant's speech in real-time during the communication session to provide real-time visual feedback to the participant. The avatar is then provided for display to the participant.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating and providing pose guides that are tailored to a context of a camera viewfinder stream. In particular, in one or more embodiments, the disclosed systems determine a context of the camera viewfinder stream and provide sample pose images that correspond with the determined context. In response to a selection of a sample pose image, the disclosed systems generate and display a pose guide that is customized to the proportions of a subject depicted in the camera viewfinder stream. The disclosed systems further iteratively modify portions of the generated pose guide to indicate that the subject depicted in the camera viewfinder stream is coming into alignment with the generated pose guide. The disclosed systems automatically capture a digital image when the subject is in total alignment with the generated pose guide.

Abstract: A method for streaming videos with internally-variable frame quality is implemented via a computing system including a processor. The method includes accessing a video including and evenly sampling the video frames. The method includes, for each sampled video frame, analyzing the video frame using a CNN model to determine whether the video frame includes high-relevance region(s). The method also includes, for each sampled video frame including high-relevance region(s), extracting coordinates of the high-relevance region(s) using the CNN model, and for each sampled video frame including high-relevance region(s) and each intervening video frame between the sampled video frame and a next sampled video frame, setting a minimum frame quality for the extracted coordinates.

Abstract: A method for content-aware type-on-path generation is implemented via a computing system including a processor. The method includes surfacing an image via a graphics GUI of a graphics application and detecting one or more salient objects within the image using a CNN model. The method also includes generating a contour map for each detected salient object and generating a path along the contours of each salient object by applying a defined offset to the corresponding contour map. The method further includes applying input text characters as type-on-path along the generated path based at least on user input received via the graphics GUI.

Abstract: Technology is disclosed herein for the integration of large language model (LLM) services for content analysis in productivity applications. In an implementation, an application identifies content associated with the application executing on the computing apparatus. The application identifies a context relating to the content, wherein the context comprises contextual information by which to evaluate the content. The application generates a prompt for an LLM service which includes the content and the context. The prompt requests an evaluation of the content to recommend supplemental content and submits the prompt to the LLM service. The application receives a response to the prompt from the LLM service which includes a suggestion for supplemental content based on the evaluation and displays, in a user interface of the application, a recommendation based on the suggestion from the LLM service.

Abstract: A method for streaming videos with internally-variable frame quality is implemented via a computing system including a processor. The method includes accessing a video including and evenly sampling the video frames. The method includes, for each sampled video frame, analyzing the video frame using a CNN model to determine whether the video frame includes high-relevance region(s). The method also includes, for each sampled video frame including high-relevance region(s), extracting coordinates of the high-relevance region(s) using the CNN model, and for each sampled video frame including high-relevance region(s) and each intervening video frame between the sampled video frame and a next sampled video frame, setting a minimum frame quality for the extracted coordinates.

Abstract: A system and method and for automatically enhancing an input image includes detecting a genre for the input image using a genre identification machine-learning model and identifying one or more objects in the input image using an object identification machine-learning model. The identified genre and objects are then compared to a list of genre and object tags for images in an image library to identify a plurality of genre and object tags that are similar to the identified genre and objects. A list of edits corresponding to each of the identified similar genre and object tags is then to the input image to generate a plurality of enhanced images for the input image. An aesthetic value is measured for the plurality of enhanced images and at least one of the plurality of enhanced images is provided as a recommendation for enhancing the input image, based on the aesthetic value.

Abstract: A method of and system for providing accessibility for digital ink is carried out by detecting digital ink input on a user interface (UI) screen, the digital ink input being received via a writing instrument used by a user within a given time period; capturing an image of the digital ink input; examining the image of the digital ink input to detect tremors in the user; assigning a level to the tremors based on discontinuities or irregularities in the digital ink input within the given time period; determining based on the level that the digital ink input requires correction; and applying a correction to the digital ink input to correct the digital ink input.

Abstract: A method for automatically improving the legibility of text within graphic designs is implemented via a computing system including a processor. The method includes executing a graphics application and causing surfacing of a graphic design GUI on a display. The method includes generating a templatized image including text responsive to the user-initiated insertion of a desired image into a design template surfaced via the graphic design GUI. The method also includes assigning a legibility score to the text within the templatized image and, responsive to a determination that the legibility score is less than a predetermined threshold, generating a bounding box around the text area. The method further includes generating an improved templatized image with improved text legibility by selectively blurring the image portion that falls within the bounding box, as well as causing surfacing of the second templatized image via the graphic design GUI.

Abstract: Techniques are provided herein for retrieving images that correspond to a target subject matter within a target context. Although useful in a number of applications, the techniques provided herein are particularly useful in contextual product association and visualization. A method is provided to apply product images to a neural network. The neural network is configured to classify the products in the images. The images are associated with a context representing the combination of classified products in the images. These techniques leverage both seller-provided images of products and user-generated content, which potentially includes hundreds or thousands of images of the same or similar products as the seller-provided images. A graphical user interface is configured to permit a user to select the context of interest in which to visualize the products.

Abstract: Techniques are disclosed for identifying and presenting video content that demonstrates features of a target product. The video content can be accessed, for example, from a media database of user-generated videos that demonstrate one or more features of the target product so that a user can see and hear the product in operation via a product webpage before making a purchasing decision. The product functioning videos supplement any static images of the target product and the textual product description to provide the user with additional context for each of the product's features, depending on the textual product description. The user can quickly and easily interact with the product webpage to access and playback the product functioning video to see and/or hear the product in operation.

Abstract: Methods, systems, and computer storage media for providing a disrupted-speech assistance service associated with a disrupted-speech management engine of a meeting management system. The disrupted-speech assistance service is an accessibility service that supports accessibility operations of a disrupted-speech management engine to provide disrupted-speech assistance features in a meeting management system. In operation, meeting data comprising audio data is accessed. The audio data is analyzed to determine that the audio data comprises disrupted-speech at a threshold level of disrupted-speech. Based on the audio data comprising disrupted-speech at the threshold level of disrupted-speech, one or more disrupted-speech assistance operations for a meeting can be executed. The one or more disrupted-speech assistance operations comprises identifying a disrupted-speech word; determining an alternative word for the disrupted-speech word.

Abstract: A method for streaming videos with internally-variable frame quality is implemented via a computing system including a processor. The method includes accessing a video including and evenly sampling the video frames. The method includes, for each sampled video frame, analyzing the video frame using a CNN model to determine whether the video frame includes high-relevance region(s). The method also includes, for each sampled video frame including high-relevance region(s), extracting coordinates of the high-relevance region(s) using the CNN model, and for each sampled video frame including high-relevance region(s) and each intervening video frame between the sampled video frame and a next sampled video frame, setting a minimum frame quality for the extracted coordinates.

Abstract: A method for content-aware type-on-path generation is implemented via a computing system including a processor. The method includes surfacing an image via a graphics GUI of a graphics application and detecting one or more salient objects within the image using a CNN model. The method also includes generating a contour map for each detected salient object and generating a path along the contours of each salient object by applying a defined offset to the corresponding contour map. The method further includes applying input text characters as type-on-path along the generated path based at least on user input received via the graphics GUI.

Abstract: Review videos on product pages are enhanced with user interface elements that cause playback of the review videos at points at which particular topics are discussed. A review video is processed by converting speech to text and timestamping the text. Topics are identified in the text, and a time in the review video corresponding to each topic is identified from the timestamps for the text. In some configurations, sentiment is also determined for each topic. User interface elements corresponding to each identified topic are presented with the review video on the product page. When a user viewing the product page selects a user interface element, the review video is played at a time corresponding to the topic of the selected user interface element.

Abstract: A method for generating geolocation-specific subtitles for a video is implemented via a computing system including a processor. The method includes accessing, via the processor, a video including an embedded subtitle file, extracting the subtitle file from the video, extracting unit values from the subtitle file, and extracting a geolocation of a user executing a video streaming application. The method also includes converting the unit values within the subtitle file to geolocation-specific unit values using a unit conversion map, where the geolocation-specific unit values correspond to the extracted geolocation of the user. The method further includes streaming the video with subtitles from the subtitle file on a video GUI of the video streaming application and, simultaneously with the streaming of the video, surfacing the geolocation-specific unit values within a unit conversion GUI of the video streaming application that is surfaced on top of the video GUI.

Abstract: Methods, systems, and non-transitory computer readable media are disclosed for determining a sub-set of user-submitted images that are similar to a curated image and presenting the sub-set of user-submitted images in connection with the curated image. The disclosed system presents a curated image depicting a product via a graphical user interface (e.g., on an e-commerce platform). In one or more embodiments, the disclosed system extracts feature vectors from the curated image and a plurality of user-submitted images. The disclosed system compares the feature vectors from the curated image and the plurality of user-submitted images to determine a sub-set of user-submitted images that are similar to the curated image. The disclosed system presents the sub-set of user-submitted images based on a user selection of the curated image.

Abstract: A computer readable medium for sizing a product includes instructions, that when executed by at least one processor, cause a computing device to: retrieve from a webpage information on a product including product dimensions; present on a display of a client device a graphical button that upon access by a user activates a camera for capturing an image of an object positioned at a focal distance from the camera, the object having a surface; prompt the user to enter boundary information of an imaginary housing to be placed on the surface; generate the imaginary housing dimensions in two dimensions (2D) based on the boundary information and the focal distance; and determine whether the product fits within the imaginary housing by comparing the product dimensions against the imaginary housing dimensions.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating and providing pose guides that are tailored to a context of a camera viewfinder stream. In particular, in one or more embodiments, the disclosed systems determine a context of the camera viewfinder stream and provide sample pose images that correspond with the determined context. In response to a selection of a sample pose image, the disclosed systems generate and display a pose guide that is customized to the proportions of a subject depicted in the camera viewfinder stream. The disclosed systems further iteratively modify portions of the generated pose guide to indicate that the subject depicted in the camera viewfinder stream is coming into alignment with the generated pose guide. The disclosed systems automatically capture a digital image when the subject is in total alignment with the generated pose guide.