Abstract: Taxonomy-based image generation is used for item searching, and enhances the quality and personalization of search results. Prior interacted items are classified into a categorical taxonomy. A generative AI model can be used to classify the prior interacted items, by generating categories or assigning to existing categories. A set of prior interacted items is selected from one of the categories and provided to an image model that generates a photo-realistic image in response. The photo-realistic image includes item renderings that are rendered illustrations of items. An item search using a search engine can be performed based on the generated photo-realistic image. For instance, the photo-realistic image or a portion thereof could be provided as a search query using an image-based search or described to perform a text-based search. Search results are identified for the search query and are provided in response.

Abstract: Devices, systems and methods are disclosed for improving a playback of video data and generation of a video summary. For example, annotation data may be generated for individual video frames included in the video data to indicate content present in the individual video frames, such as faces, objects, pets, speech or the like. A video summary may be determined by calculating a priority metric for individual video frames based on the annotation data. In response to input indicating a face and a period of time, a video summary can be generated including video segments focused on the face within the period of time. The video summary may be directed to multiple faces and/or objects based on the annotation data.

Abstract: Devices, systems and methods are disclosed for improving a playback of video data and generation of a video summary. For example, annotation data may be generated for individual video frames included in the video data to indicate content present in the individual video frames, such as faces, objects, pets, speech or the like. A video summary may be determined by calculating a priority metric for individual video frames based on the annotation data. In response to input indicating a face and a period of time, a video summary can be generated including video segments focused on the face within the period of time. The video summary may be directed to multiple faces and/or objects based on the annotation data.

Abstract: Devices, systems and methods are disclosed for improving a playback of video data and generation of a video summary. For example, annotation data may be generated for individual video frames included in the video data to indicate content present in the individual video frames, such as faces, objects, pets, speech or the like. A video summary may be determined by calculating a priority metric for individual video frames based on the annotation data. In response to input indicating a face and a period of time, a video summary can be generated including video segments focused on the face within the period of time. The video summary may be directed to multiple faces and/or objects based on the annotation data.