Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for cutting down a user's larger input video into an edited video comprising the most important video segments and applying corresponding video effects. Some embodiments of the present invention are directed to adding captioning video effects to the trimmed video (e.g., applying face-aware and non-face-aware captioning to emphasize extracted video segment headings, important sentences, quotes, words of interest, extracted lists, etc.). For example, a prompt is provided to a generative language model to identify portions of a transcript (e.g., extracted scene summaries, important sentences, lists of items discussed in the video, etc.) to apply to corresponding video segments as captions depending on the type of caption (e.g., an extracted heading may be captioned at the start of a corresponding video segment, important sentences and/or extracted list items may be captioned when they are spoken).

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for identifying the relevant segments that effectively summarize the larger input video and/or form a rough cut, and assembling them into one or more smaller trimmed videos. For example, visual scenes and corresponding scene captions are extracted from the input video and associated with an extracted diarized and timestamped transcript to generate an augmented transcript. The augmented transcript is applied to a large language model to extract sentences that characterize a trimmed version of the input video (e.g., a natural language summary, a representation of identified sentences from the transcript). As such, corresponding video segments are identified (e.g., using similarity to match each sentence in a generated summary with a corresponding transcript sentence) and assembled into one or more trimmed videos. In some embodiments, the trimmed video is generated based on a user's query and/or desired length.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for cutting down a user's larger input video into an edited video comprising the most important video segments and applying corresponding video effects. Some embodiments of the present invention are directed to adding face-aware scale magnification to the trimmed video (e.g., applying scale magnification to simulate a camera zoom effect that hides shot cuts with respect to the subject's face). For example, as the trimmed video transitions from one video segment to the next video segment, a scale magnification may be applied that zooms in on a detected face at a boundary between the video segments to smooth the transition between video segments.

Abstract: Embodiments of the present disclosure provide, a method, a system, and a computer storage media that provide mechanisms for multimedia effect addition and editing support for text-based video editing tools. The method includes generating a user interface (UI) displaying a transcript of an audio track of a video and receiving, via the UI, input identifying selection of a text segment from the transcript. The method also includes in response to receiving, via the UI, input identifying selection of a particular type of text stylization or layout for application to the text segment. The method further includes identifying a video effect corresponding to the particular type of text stylization or layout, applying the video effect to a video segment corresponding to the text segment, and applying the particular type of text stylization or layout to the text segment to visually represent the video effect in the transcript.

Abstract: Embodiments of the present disclosure provide, a method, a system, and a computer storage media that provide mechanisms for multimedia effect addition and editing support for text-based video editing tools. The method includes generating a user interface (UI) displaying a transcript of an audio track of a video and receiving, via the UI, input identifying selection of a text segment from the transcript. The method also includes in response to receiving, via the UI, input identifying selection of a particular type of text stylization or layout for application to the text segment. The method further includes identifying a video effect corresponding to the particular type of text stylization or layout, applying the video effect to a video segment corresponding to the text segment, and applying the particular type of text stylization or layout to the text segment to visually represent the video effect in the transcript.

Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media providing visualizations and mechanisms utilized when performing video edits using wrapped timelines (e.g., effect bars/effect tracks) interspersed between text lines representing video effects being applied to text segments in a transcript. An example embodiment provides a transcript using an audio track from a transcribed video. A transcript interface presents the transcript and accepts an input selecting sentences or words from the transcript. The identified boundaries corresponding to the selected text segment are used as boundaries for a selected video segment. Using the selected text segment, a user selects a video effect in which to apply to the corresponding video segment and within the transcript interface, a wrapped timeline is placed in the transcript along the selected text segment to indicate that the video effect is applied to the corresponding video segment.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for a question search for meaningful questions that appear in a video. In an example embodiment, an audio track from a video is transcribed, and the transcript is parsed to identify sentences that end with a question mark. Depending on the embodiment, one or more types of questions are filtered out, such as short questions less than a designated length or duration, logistical questions, and/or rhetorical questions. As such, in response to a command to perform a question search, the questions are identified, and search result tiles representing video segments of the questions are presented. Selecting (e.g., clicking or tapping on) a search result tile navigates a transcript interface to a corresponding portion of the transcript.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for a visual and text search interface used to navigate a video transcript. In an example embodiment, a freeform text query triggers a visual search for frames of a loaded video that match the freeform text query (e.g., frame embeddings that match a corresponding embedding of the freeform query), and triggers a text search for matching words from a corresponding transcript or from tags of detected features from the loaded video. Visual search results are displayed (e.g., in a row of tiles that can be scrolled to the left and right), and textual search results are displayed (e.g., in a row of tiles that can be scrolled up and down). Selecting (e.g., clicking or tapping on) a search result tile navigates a transcript interface to a corresponding portion of the transcript.

Abstract: A gaze target is recognized via an eye tracking camera. An application launcher is displayed, via a display, at the gaze target based on a user trigger. The application launcher presents a plurality of applications selectable for launching. A user selection of one of the plurality of applications is recognized. The application launcher is replaced with the selected one of the plurality of applications at the gaze target via the display.

Abstract: Embodiments that relate to displaying holographic keyboard and hand images in a holographic environment are provided. In one embodiment depth information of an actual position of a user's hand is received from a capture device. The user's hand is spaced by an initial actual distance from the capture device, and a holographic keyboard image is displayed spatially separated by a virtual distance from a holographic hand image. The user's hand is determined to move to an updated actual distance from the capture device. In response, the holographic keyboard image is maintained spatially separated by substantially the virtual distance from the holographic hand image.

Abstract: Embodiments that relate to displaying holographic keyboard and hand images in a holographic environment are provided. In one embodiment depth information of an actual position of a user's hand is received from a capture device. The user's hand is spaced by an initial actual distance from the capture device, and a holographic keyboard image is displayed spatially separated by a virtual distance from a holographic hand image. The user's hand is determined to move to an updated actual distance from the capture device. In response, the holographic keyboard image is maintained spatially separated by substantially the virtual distance from the holographic hand image.

Abstract: Embodiments that relate to displaying holographic keyboard and hand images in a holographic environment are provided. In one embodiment depth information of an actual position of a user's hand is received. Using the depth information, a holographic hand image representing the user's hand is displayed in a virtual hand plane in the holographic environment. In response to receiving a keyboard activation input from the user and using the depth information, the holographic keyboard image is adaptively displayed in a virtual keyboard plane in the holographic environment at a virtual distance under the holographic hand image representing the user's hand.

Abstract: Embodiments are disclosed for a method of controlling a displayed position of an application launcher. An example method includes recognizing, via an eye-tracking camera, a gaze target, and responsive to a user trigger, displaying, via a display, an application launcher at the gaze target, the application launcher presenting a plurality of applications selectable for launching. The example method further includes recognizing a user selection of one of the plurality of applications, and replacing, via the display, the application launcher with the selected one of the plurality of applications at the gaze target.

Abstract: Embodiments that relate to displaying holographic keyboard and hand images in a holographic environment are provided. In one embodiment depth information of an actual position of a user's hand is received. Using the depth information, a holographic hand image representing the user's hand is displayed in a virtual hand plane in the holographic environment. In response to receiving a keyboard activation input from the user and using the depth information, the holographic keyboard image is adaptively displayed in a virtual keyboard plane in the holographic environment at a virtual distance under the holographic hand image representing the user's hand.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, include structures and techniques for integrating operations of consumer electronic devices. In one aspect, a method includes identifying a program operating on a second device; selecting a code set, from among multiple code sets, based on the identified program operating on the second device; modifying, at a first device, operation of an application installed on the first device by running the selected code set at the first device; and controlling a function of the program operating on the second device using the modified application on the first device.