# US 12,684,204 B2 · Systems and methods for automating video reformatting > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,684,204 B2 - Document ID: US12684204B2 - Status: Granted - Kind: B2 - Application number: 18/521,815 - Filed: 2023-11-28 - Published: 2024-05-30 - Granted: 2026-07-14 - Earliest claimed: 2022-11-28 - Assignees: Meta Platforms, Inc. - Applicants: Meta Platforms, Inc. - Inventors: Matthew Hannan; Stephen Crowley; William B Harding - Web page: https://patentgrep.com/patent/US12684204B2 ## CPC - H04N 21/8456: {by decomposing the content in the time domain, e.g. in time segments} - G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80) - G06V 40/161: {Detection; Localisation; Normalisation} - H04N 21/234372: {for performing aspect ratio conversion} - G06T 2207/10016: Video; Image sequence - G06T 2207/20132: Image cropping - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract The disclosed computer-implemented method may include detecting, by a computing device, a command to clip a video segment from a video stream. The method may also include extracting, by the computing device, the video segment from the video stream based on the command. Additionally, the method may include automatically identifying, by the computing device, one or more points of interest in the video segment. Furthermore, the method may include determining, by the computing device, one or more sets of coordinates to crop the video segment based on a predetermined aspect ratio and the one or more points of interest. Finally, the method may include creating, by the computing device, a short-form video by cropping and reformatting the video segment based on the one or more sets of coordinates. Various other methods, systems, and computer-readable media are also disclosed. ## Claims ### Claim 1 A computer-implemented method comprising: detecting, by a computing device, a command to clip a video segment from a video stream; extracting, by the computing device, the video segment from the video stream based on the command; automatically identifying, by the computing device, at least one point of interest in the video segment; determining, by the computing device, at least one set of coordinates to crop the video segment based on a predetermined aspect ratio and the at least one point of interest; and creating, by the computing device, a short-form video by cropping and reformatting the video segment based on the at least one set of coordinates, wherein creating comprises (i) overlaying a cropped video segment of the at least one point of interest over a portion of a cropped video segment of a second point of interest, and at least one of (ii) adjusting a size of the cropped video segment of the at least one point of interest, or adjusting a position of the cropped video segment of the at least one point of interest. ### Claim 2 (depends on 1) The method of claim 1, wherein the video stream comprises at least one of: a video broadcast by the computing device to at least one other computing device; or a video received by the computing device from the at least one other computing device. ### Claim 3 (depends on 1) The method of claim 1, wherein detecting the command to clip the video segment from the video stream comprises: predicting the command to clip the video segment based on a machine-learning analysis of the video stream; or detecting a user command. ### Claim 4 (depends on 3) The method of claim 3, wherein detecting the user command comprises: detecting a voice command by a user; and using natural language processing to extract the command from the voice command. ### Claim 5 (depends on 1) The method of claim 1, wherein extracting the video segment from the video stream comprises extracting a preset clip length of the video stream from a time prior to a timestamp of the command to the timestamp of the command. ### Claim 6 (depends on 1) The method of claim 1, wherein automatically identifying the at least one point of interest comprises using a machine-learning model to detect at least one of: a focal subject of the video stream; or a face of a user. ### Claim 7 (depends on 6) The method of claim 6, wherein determining the at least one set of coordinates to crop the video segment comprises at least one of: determining a position of the face of the user using a face-tracking model; determining a position of the focal subject based on the position of the face; or using the machine-learning model to determine the position of the focal subject. ### Claim 8 (depends on 1) The method of claim 1, wherein creating the short-form video comprises at least one of: cropping the video segment based on at least one of: the predetermined aspect ratio; a set of coordinates of a first point of interest; or a set of coordinates of a second point of interest. ### Claim 9 (depends on 1) The method of claim 1, wherein overlaying the cropped video segment of the first point of interest over the portion of the cropped video segment of the second point of interest comprises adjusting the cropped video segment of the first point of interest based on at least one of: a position of the second point of interest in the cropped video segment of the second point of interest; or a priority of the first point of interest relative to a priority of the second point of interest. ### Claim 10 (depends on 1) The method of claim 1 wherein creating the short-form video comprises: reformatting the video segment to the predetermined aspect ratio; and formatting the video segment to a predetermined file type. ### Claim 11 (depends on 1) The method of claim 1, further comprising: automatically identifying a change in the at least one point of interest; determining at least one new set of coordinates to crop the video segment based on the change; and re-cropping the video segment based on the at least one new set of coordinates. ### Claim 12 (depends on 1) The method of claim 1, further comprising transmitting the short-form video over a network. ### Claim 13 A system comprising: a detection module, stored in memory, that detects a command to clip a video segment from a video stream; an extraction module, stored in memory, that extracts the video segment from the video stream based on the command; an identification module, stored in memory, that automatically identifies at least one point of interest in the video segment; a determination module, stored in memory, that determines at least one set of coordinates to crop the video segment based on a predetermined aspect ratio and the at least one point of interest; a creation module, stored in memory, that creates a short-form video by cropping and reformatting the video segment based on the at least one set of coordinates, wherein creating comprises (i) overlaying a cropped video segment of the at least one point of interest over a portion of a cropped video segment of a second point of interest, and at least one of (ii) adjusting a size of the cropped video segment of the at least one point of interest, or adjusting a position of the cropped video segment of the at least one point of interest; and at least one processor that executes the detection module, the extraction module, the identification module, the determination module, and the creation module. ### Claim 14 (depends on 13) The system of claim 13, wherein the detection module detects the command to clip the video segment from the video stream by: predicting the command to clip the video segment based on a machine-learning analysis of the video stream; or detecting a user command. ### Claim 15 (depends on 14) The system of claim 14, wherein detecting the user command comprises: detecting a voice command by a user; and using natural language processing to extract the command from the voice command. ### Claim 16 (depends on 13) The system of claim 13, wherein the identification module automatically identifies the at least one point of interest by using a machine-learning model to detect at least one of: a focal subject of the video stream; or a face of a user. ### Claim 17 (depends on 16) The system of claim 16, wherein the determination module determines the at least one set of coordinates to crop the video segment by at least one of: determining a position of the face of the user using a face-tracking model; determining a position of the focal subject based on the position of the face; or using the machine-learning model to determine the position of the focal subject. ### Claim 18 (depends on 13) The system of claim 13, wherein the creation module creates the short-form video by at least one of: cropping the video segment based on at least one of: the predetermined aspect ratio; a set of coordinates of a first point of interest; or a set of coordinates of a second point of interest. ### Claim 19 A non-transitory computer-readable medium comprising one or more computer-executable instructions that, when executed by at least one processor of a computing device, cause the computing device to: detect, by the computing device, a command to clip a video segment from a video stream; extract, by the computing device, the video segment from the video stream based on the command; automatically identify, by the computing device, at least one point of interest in the video segment; determine, by the computing device, at least one set of coordinates to crop the video segment based on a predetermined aspect ratio and the at least one point of interest; and create, by the computing device, a short-form video by cropping and reformatting the video segment based on the at least one set of coordinates, wherein creating comprises (i) overlaying a cropped video segment of the at least one point of interest over a portion of a cropped video segment of a second point of interest, and at least one of (ii) adjusting a size of the cropped video segment of the at least one point of interest, or adjusting a position of the cropped video segment of the at least one point of interest.