142results about "Carrier editing" patented technology

Examples are provided relating to media content editing architectures utilizing machine learning techniques. One aspect includes a method for media content editing, the method comprising: receiving a media content from a user; receiving an editing request for the media content from the user; and editing the media content based on the editing request to generate edited media content by: retrieving a prompt from a prompt pool, wherein the retrieved prompt is selected based on the editing request; parsing the retrieved prompt and the editing request using a large language model to generate one or more editing actions to be performed on the media content; and performing the one or more editing actions on the media content to generate the edited media content.

A method may include obtaining a first video that includes sign language content. In some embodiments, the sign language content may include one or more video frames of a figure performing sign language. The method may also include obtaining language data that represents the sign language content in the first video and creating a second video including sign language content by altering the first video. The method may further include training a machine learning model of a translation system configured to translate between sign language and language data using the second video and the language data.

Embodiments of the present invention provide systems, methods, and computer storage media for selection of the best image of a particular speaker's face in a video, and visualization in a diarized transcript. In an example embodiment, candidate images of a face of a detected speaker are extracted from frames of a video identified by a detected face track for the face, and a representative image of the detected speaker's face is selected from the candidate images based on image quality, facial emotion (e.g., using an emotion classifier that generates a happiness score), a size factor (e.g., favoring larger images), and / or penalizing images that appear towards the beginning or end of a face track. As such, each segment of the transcript is presented with the representative image of the speaker who spoke that segment and / or input is accepted changing the representative image associated with each speaker.

A method may include obtaining, at a system, audio during a communication session that includes a first device and a second device. In these and other embodiments, the audio may originate at the second device. The method may further include selecting, automatically and independently by the system based on one or more features of the communication session, a first translation process instead of a second translation process to translate between sign language and language data during the communication session. The method may also include using the selected one of the first translation process and the second translation process to generate a video that includes sign language content based on the audio.

A dubbing interaction method and an apparatus, a computer device, and a storage medium are provided. The method includes: showing character information associated with a text to be dubbed; in response to a selection operation for first character information, obtaining a first dubbing audio of a first user, and associating the first dubbing audio with the first character information, wherein the first dubbing audio is a dub for a text fragment of the text to be dubbed that is associated with the first character information; and obtaining an aggregated dubbing audio corresponding to the text to be dubbed based on the first dubbing audio associated with the first character information and an obtained second dubbing audio respectively corresponding to second character information associated with the text to be dubbed, and showing a first audio identifier corresponding to the aggregated dubbing audio.

Disclosed in the embodiments of the present disclosure are a video generation method, an apparatus, an electronic device and a storage medium. The method comprises: during an image editing process of subjecting an initial image to a series of image editing operations to obtain a target image, acquiring initial key frames, the initial key frames being intermediate images between the initial image and the target image during the image editing process, the different initial key frames being intermediate images generated when different image editing operations of the series of image editing operations are triggered during the image editing process, and the intermediate images showing editing effects corresponding to the image editing operations; and generating a target video according to the initial key frames so as to record the image editing process of the target image. The present disclosure can be used for recording an image editing process.

A method may include obtaining a data stream with language data for translation by a translation system configured to translate between sign language and other language forms. The method may further include storing one or more portions of the data stream and directing a current portion of the data stream to the translation system. The method may also include providing the stored one or more of the portions of the data stream to the translation system and translating, by the translation system, the current portion of the data stream using the current portion of the data stream and the stored one or more of the portions of the data stream provided to the translation system.

A system and method are provided for modifying a graphic narrative to feature select products / services. Panels of the graphic narrative are segmented into elements (e.g., using semantic segmentation models like Fully Convolutional Networks), which are then identified as backgrounds, foregrounds, text bubbles, objects, characters etc. (e.g., using artificial intelligence (AI) classifiers like K-means classifiers). The identified elements are compared to a product database to select products suitable to be promoted by modifying selected elements, resulting in a version of the graphic narrative having modified panels in which the selected element(s) are changed to feature the selected products. For example, generative AI methods can redraw image elements or redraft text to place the selected products within the context of the graphic narrative. Links or watermarks can be placed in the modified panels to provide users with access to interact with or purchase the promoted products.

An aspect of the current invention relates to a method to reduce the emotional impact on a viewer while allowing evaluation of graphic pornographic, pedophilic and / or violent content. In some embodiments the system has various functions that reduce the emotional impact and / or stress inducing factors of a media (e.g., an image and / or a video). For example, the functions may include changing and / or blurring certain parts of the image and / or changing the color and / or contrast of the image and / or presenting part of the media while withholding other parts and / or changing the media in different ways when it is repeatedly presented e.g., to reduce the effect of repeated seeing same distressing content.

Mapping a source video stream to a screen of a target device includes extracting separate objects from the source video stream, identifying a subset of the objects that correspond to a presentation area, and creating a target video stream that is displayed on the target device by arranging the separate objects to enhance the presentation area on the screen of the target device based on a form factor, screen resolution, and / or aspect ratio of the target device. The presentation area may include a presenter and presentation materials. Creating the target video stream may include scaling different ones of the objects. Different scaling factors may be applied to different objects to enhance the presentation area on the screen of the target device. A separate video image corresponding to a linear mapping of the source video stream onto a target device may be provided in addition to the target video stream.

To automatically edit a moving image attractively.SOLUTION: A reproduction information generation device for generating a moving image based on a plurality of image materials or information necessary for reproduction of the moving image comprises a retrieval unit which retrieves a plurality of cuts used for the moving image from the plurality of image materials using information on a theme of the moving image to be reproduced.SELECTED DRAWING: Figure 2

To provide an audio signal processing device capable of shortening a setting time related to setting data for each channel.SOLUTION: In an audio system that has a mixing device and an audio signal processing device, an audio signal processing device 3 that is connected comprises: an operation acceptance unit 37 that accepts from a user a selection operation for selecting a channel of the mixing device; an audio signal input unit 32 that receives an audio signal to the channel accepted by the operation acceptance unit; a sound source identification unit 361 that analyzes the audio signal received by the audio signal input unit 32 to identify the type of a sound source; a setting data acquisition unit 362 that acquires setting data according to the type of the sound source identified by the sound source identification unit 361; and a setting data setting unit 363 that makes the mixing device set the setting data acquired by the setting data acquisition unit 362 to the accepted channel.SELECTED DRAWING: Figure 3

A production process involves predetermined number of cameras simultaneously filming a background at predetermined angles, and filming actors in a studio with the same number of cameras and the same angles, used in conjunction with a virtual studio system. In studio, the actors perform before a green screen and the virtual studio system composites the actors onto the background in real-time. Camera tracking allows the in-studio cameras to pan, tilt, focus, zoom, and make limited other movements as the virtual studio system adjusts display of the background in a corresponding manner, resulting in a realistic scene without transporting actors and crew to the background location.

To provide an audio generation method and a system.SOLUTION: A method for generating audio assets includes a step of receiving a plurality of input audio assets, a step of converting each of the input audio assets into an input graphic representation, a step of generating an input image from each of the input graphic representations, a step of feeding the input image to a generative model and extracting an output graphic representation from each of the output images in order to learn the generative model and generate one or more output images including the output graphic representations, and a step of converting the output graphic representation into an output audio asset.SELECTED DRAWING: Figure 2

Disclosed are an electronic apparatus capable of synchronizing between documents and voices through matching between a voice and an editing object, and operating method thereof. The present invention provides an electronic apparatus capable of synchronizing between documents and voices through matching between a voice and an editing object, and an operating method thereof, when a user edits a document while recording the voice to support the user to view editing objects inserted into the document in chronological order at the time when recording the voice.

To provide an information recording device that can record desired video data and voice data, and that can leave necessary voice data while paying attention to privacy protection.SOLUTION: Video data and voice data are acquired from a camera C and a microphone MC provided in a vehicle, event information indicating that an event such as rapid steering occurs in the vehicle is acquired, and after the acquired video data and voice data are recorded, the voice data recorded being associated with the event information for the recorded voice data is left in a recording unit R.SELECTED DRAWING: Figure 4

To easily divide the entire video data in which a series of work is recorded into a plurality of parts for each work process, and to store the divided video data in chronological order. [Solution] The system comprises a memory unit 5 that stores a series of work processes including multiple element work processes that have been filmed in advance for one person, one machine, or one item as one work video file; an identification unit (control unit 10) that analyzes the video data that makes up one work video file stored in the memory unit 5 and automatically identifies the start timing of the multiple element work processes; a division unit (control unit 10) that divides the entire work video file into multiple element work period videos while positioning the video period from the previous start timing to the current start timing identified by the identification unit as one element work period video; and an editing unit (control unit 10) that associates each of the divided element work period videos with a work procedure and stores them as new work video files in the memory unit.

A system, apparatus and method for performing adaptive audio mixing are disclosed. A trained neural network dynamically selects and mixes pre-recorded human-composed music stems arranged in a mutually compatible set. Stem and track selection, volume mixing, filtering, dynamic compression, acoustic / reverberation characteristics, segue, tempo, beat matching and cross-fade parameters generated by the neural network are inferred from game scene characteristics and other dynamically changing factors. The trained neural network selects pre-recorded stems of artists and mixes the stems in a unique way in real time to dynamically adjust and change background music based on factors such as the game scenario, the player's unique storyline, scene elements, player's profile, interests, performance, adjustments made to game controls (e.g., music volume), number of viewers, comments received, player popularity, player's native language, player's influence and / or other factors. The trained neural network generates unique music that dynamically changes according to real-time conditions.

Embodiments of the present invention relate to interacting with semantic video segments via interactive tiles. The embodiments relate to interactive tiles representing video segments that are segments of a video. In some embodiments, each interactive tile represents a different video segment from a specific video segment (e.g., a default video segment). Each interactive tile includes a thumbnail (e.g., the first frame of the video segment represented by the tile), a script from the beginning of the video segment, a visualization of detected faces in the video segment, and one or more faceted timelines that visualize the categories of detected features (e.g., visualizations of detected visual scenes, audio classifications, and visual artifacts). In some embodiments, interacting with a specific interactive tile can navigate to the corresponding portion of the video, add the corresponding video segment to the selection, and / or scan through the tile thumbnail.

Examples are provided that relate to implementing actions on social media network content based on natural language input. One aspect includes a computing system configured to implement a social media network, the computing system including one or more processors and a storage device, the storage device including instructions executable to receive user input from a dialog agent, the user input including a natural language description of a request for an action of a content item, the dialogue agent is configured to participate in a dialogue using at least a language model and generate cues to the language model based on at least a user input. The instructions are further executable to input the cue word to the language model to generate an output describing an operation for implementing the action, invoke a backend service of the social media network to execute the command to implement the operation, and output a result of executing the command.

An apparatus for processing an audio input recording to obtain a processed audio recording according to an embodiment is provided. The apparatus comprises an input interface (110) for receiving a plurality of audio input portions of the audio input recording. Moreover, the apparatus comprises a processor (120) for processing a plurality of audio input portions of the audio input recording to obtain a processed audio recording. The processor (120) is configured to determine, whether or not an audio input portion of the plurality of audio input portions comprises speech. If the processor (120) has detected that the audio input portion comprises speech, the processor (120) is configured to generate the processed audio recording by modifying the audio input portion to obtain a modified audio portion, and by generating the processed audio recording such that the processed audio recording comprises the modified audio portion instead of the audio input portion. Or, if the processor (120) has detected that the audio input portion comprises speech, the processor (120) is configured to generate the processed audio recording, such that the processed audio recording does not comprise the audio input portion.

Devices, systems, and methods for remote capture and viewing of workstation activity are provided. The system may comprise a worker computer, a data-streamer, a segmenter, a server, a requester, a stitcher, and a watcher computer. The segmenter creates segment files associated with segments of data-streams of captures of workstation activity. The stitcher creates data-streams of captures of workstation activity from such segment files. Gains in speed and efficiency are achieved by segmenting data-streams into segments for transmission, storage, and processing.

An embodiment of the present disclosure relates to a video editing method, apparatus, device, and medium, in which the method includes: obtaining and displaying at least one storyboard shooting instruction information and a video editing draft for recording a video material segment, wherein a video material segment of a target storyboard of the at least one storyboard is shot by a second device according to the shooting instruction information of the target storyboard and saved in the video editing draft; displaying a video editing interface based on the video editing draft in response to an editing command triggered on the video editing draft; displaying an operation mark in the editing track and an editing effect of the editing operation on the video material segment in a preview player in response to an editing operation on the video track segment; and generating a target video based on the editing operation and the video material segment in the video editing interface. In the embodiment of the present disclosure, the efficiency of video editing is improved by the cooperation between the first device and the second device.

Provided is a method for processing a video. The method for processing the video can segment an initial video into a plurality of video clips, and calculate color temperatures of the plurality of video clips. For each target video clip in the plurality of video clips, the method can determine a color temperature adjustment coefficient of the target video clip based on a color temperature of the target video clip and a color balance correction coefficient thereof, and adjust a color temperature of at least one video frame in the target video clip by using the color temperature adjustment coefficient.

The embodiments of the present disclosure disclose a video generating method, an apparatus, an electronic device, and a storage medium, the method including: obtaining an initial key frame in an image editing process of performing a series of image editing operations on an initial image to obtain a target image, the initial key frame being an intermediate state image between the initial image and the target image in the image editing process, where different initial key frames are intermediate state images when different image editing operations in the series of image editing operations are triggered in the image editing process, and the intermediate state images exhibit editing effects of corresponding image editing operations; generating a target video based on the initial key frame to record the image editing process of the target image. The present disclosure can be used for recording the image editing process.

The present invention enables emotion data, which represents user emotion for each scene of moving image content, to be effectively used.　A representative emotion scene is extracted by an extraction unit on the basis of emotion metadata having user emotion information for each scene of the moving image content. On the basis of the extracted representative emotion scene, playing back a portion of the moving image content or editing for taking out a portion of the moving image content can be effectively performed. For example, the extraction unit extracts the representative emotion scene on the basis of the type or degree of user emotion.

Devices, systems, and methods for remote capture and viewing of workstation activity are provided. The system may comprise a worker computer, a data-streamer, a segmenter, a server, a requester, a stitcher, and a watcher computer. The segmenter creates segment files associated with segments of data-streams of captures of workstation activity. The stitcher creates data-streams of captures of workstation activity from such segment files. Gains in speed and efficiency are achieved by segmenting data-streams into segments for transmission, storage, and processing.