Patents Examined by Daquan Zhao
-
Patent number: 12223720Abstract: Presented herein are systems, methods, and datasets for automatically and precisely generating highlight or summary videos of content. In one or more embodiments, the inputs comprise a text (e.g., an article) of the key event(s) (e.g., a goal, a player action, etc.) in an activity (e.g., a game, a concert, etc.) and a video or videos of the activity. In one or more embodiments, the output is a short video of an event or events in the text, in which the video may include commentary about the highlighted events and/or other audio (e.g., music), which may also be automatically synthesized.Type: GrantFiled: November 23, 2021Date of Patent: February 11, 2025Assignee: Baidu USA, LLCInventors: Xin Zhou, Le Kang, Zhiyu Cheng, Hao Tian, Daming Lu, Dapeng Li, Jingya Xun, Jeff Wang, Xi Chen, Xing Li
-
Patent number: 12219200Abstract: A programming access device such as, for example, a cable or satellite set top box (STB), a digital video recorder (DVR), a personal computer, and/or a digital media receiver automatically optimizes an order of content choices presented in a content listing, such as a program guide display, favorite channel display, and/or a recording listing display based on the past viewing and/or recording history of an identified user.Type: GrantFiled: October 25, 2023Date of Patent: February 4, 2025Assignee: Universal Electronics Inc.Inventors: Bhuvanesh Prabhu, Anurag Thakur
-
Patent number: 12211472Abstract: An intelligent system for matching audio with video of the present invention provides a video analysis module targeting color tone, storyboard pace, video dialogue, length and category and director's special requirement, actors expression, movement, weather, scene, buildings, spacial and temporal, things and a music analysis module targeting recorded music form, sectional turn, style, melody and emotional tension, and then uses an AI matching module to adequately match video of the video analysis module with musical characteristics of the music analysis module, so as to quickly complete a creative composition selection function with respect to matching audio with a video.Type: GrantFiled: September 23, 2022Date of Patent: January 28, 2025Inventor: Tzu-Hui Li
-
Patent number: 12212886Abstract: Apparatus, methods, and computer program products that can replicate a digital environment are disclosed. One apparatus includes a processor and a memory that stores code executable by the processor to generate a digital record of a digital environment occurring at an original time in which the digital record includes a set of happenings that occurred in the digital environment at the original time. The code is further executable by the processor to store the digital record for replication of the digital environment. Methods and computer program products that include and/or perform the operations and/or functions of the apparatus are also disclosed.Type: GrantFiled: June 30, 2022Date of Patent: January 28, 2025Assignee: Lenovo (Singapore) Pte. Ltd., New Tech ParkInventors: Allen Richey, Inna Zolin, Matthew Fardig
-
Patent number: 12206955Abstract: Disclosed are a multimedia data generating method, apparatus, electronic device, medium, and program product, applied to the field of multimedia data processing technologies. The method includes: receiving text information inputted by a user; displaying, in response to a recording trigger operation for the text information, the text information and acquiring a first reading speech of the text information; and generating a first multimedia data based on the text information and the first reading speech and displaying the first multimedia data; the first multimedia data includes the first reading speech and a video image matched with the text information; the first multimedia data includes a plurality of first multimedia segments; the plurality of first multimedia segments correspond to a plurality of text segments included in the text information, respectively. The disclose may improve quality of multimedia data generation.Type: GrantFiled: December 13, 2023Date of Patent: January 21, 2025Assignee: BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD.Inventor: Jiajin Cao
-
Patent number: 12205191Abstract: Provided are a watermark adding method and apparatus, a storage medium and a device. The method includes steps described below. To-be-added watermark information is acquired, and a time offset is determined according to the watermark information; a video frame rate is acquired, and time information of a frame image in a video is determined according to the video frame rate; and offset processing is performed on the time information according to the time offset to add the watermark information to the video.Type: GrantFiled: April 22, 2020Date of Patent: January 21, 2025Assignee: ZHEJIANG UNIVIEW TECHNOLOGIES CO., LTD.Inventor: Changhui Cheng
-
Patent number: 12205618Abstract: Indexing of media sources available to media composition applications, such as video editing applications and digital audio workstations, is extended to sources of an arbitrary type, including non-file type sources. Examples of such sources include devices using baseband video and audio protocols, network ports and physical devices connected via USB, Thunderbolt, etc. The sources are discovered and indexed even when not previously known to the application with the result that any available bitstream becomes available to the application. Applications access the sources via feeders, which are addressable portals through which media essence is received. The indexing methods involve the instantiation of a hierarchy of plug-in software modules by a format-handling subsystem of the application or by a media indexing service servicing one or more applications.Type: GrantFiled: February 17, 2023Date of Patent: January 21, 2025Assignee: Avid Technology, Inc.Inventor: Shailendra Mathur
-
Patent number: 12198733Abstract: In order to provide a recording and reproducing device that allows a user to select and manage arbitrary play lists, a unit of management for managing all registered play list information and an upper management hierarchical level are added. The unit of management is adapted to be handled on the same level with unified information that indicates a reproduction range of all AV data. User-defined unified information is adapted to be handled on the added management hierarchical level. The user-defined unified information is formed to allow arbitrary reproduction ranges contained on a lower hierarchical level to be registered.Type: GrantFiled: February 8, 2024Date of Patent: January 14, 2025Assignee: MAXELL, LTD.Inventors: Susumu Yoshida, Junji Shiokawa, Hiroo Okamoto
-
Patent number: 12198728Abstract: A system and method for generating a multi-source video to expedite video editing are disclosed.Type: GrantFiled: July 22, 2021Date of Patent: January 14, 2025Inventor: Claude Shires
-
Patent number: 12198160Abstract: Disclosed are methods, systems, and non-transitory computer-readable medium for transition-coded media, measuring engagement of transition-coded media, and distribution of components of transition-coded media. For instance, the method may include: obtaining a media file; determining whether the media file includes transition-coded media; in response to determining the media file includes the transition-coded media, setting up a dynamic media environment; detecting whether a user is interacting with the transition-coded media; and in response to detecting the user is interacting with the transition-coded media, executing the transition-coded media with the dynamic media environment.Type: GrantFiled: October 26, 2023Date of Patent: January 14, 2025Assignee: Capital One Services, LLCInventor: Eric K. Barnum
-
Patent number: 12190914Abstract: Exemplary embodiments of present disclosure are directed towards a system and method for extracting objects from videos in real-time to create virtual situations, comprising a computing device comprises video creating and editing module configured to enable a user to record videos and select frames automatically from the user recorded videos thereby transferring the automatically selected frames from the computing device to a server. The server comprises video processing module configured receive the automatically selected frames thereby detecting and extracting objects from the automatically selected frames and transfer extracted objects to computing device and display the extracted objects to the user. The video creating and editing module configured to place the extracted objects on a new frame automatically and allow the user to reposition extracted objects on new frame and enable the user to customize the background and foreground elements in the new frame to create virtual situations.Type: GrantFiled: January 4, 2023Date of Patent: January 7, 2025Assignee: SILVERLABS TECHNOLOGIES INCInventors: Lakshminath Reddy Dondeti, Vidya Narayanan
-
Patent number: 12183121Abstract: A method performed by a computer for generating a video comprising blink data of a user viewing a scene depicted as video data, where the blink data is overlayed on the video data. The method includes receiving sensor data. The sensor data includes at least the video data including at least one video frame, and gaze tracking data at least indicative of viewed positions within the scene depicted by at least one video frame of the video data. The method includes processing the sensor data to generate blink data indicative of blink motion of at least one eye of the user. The method includes generating a video overlay by rendering the blink data. generating an output video by mixing the video data and the video overlay.Type: GrantFiled: January 9, 2023Date of Patent: December 31, 2024Assignee: Tobii ABInventor: Richard Andersson
-
Patent number: 12175757Abstract: A method for action localization is disclosed. The method includes dividing a video comprising a first number of frames into a second number of clips, each of the clips comprising at least one of the frames; processing the clips to obtain a first clip descriptor for the each of the clips and feature maps for each of the frames; obtaining a representation of the video based on the first clip descriptor for the each of the clips; predicting an action classification of the video based on the representation of the video; calculating an importance weight for each of the feature maps based on a gradient of the action classification; and obtaining a localization map for the each of the frames based on importance weights of corresponding feature maps.Type: GrantFiled: September 23, 2022Date of Patent: December 24, 2024Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.Inventor: Jenhao Hsiao
-
Patent number: 12170007Abstract: Embodiments of the present invention are directed to systems, devices, and methods for displaying and securing articles of merchandise. In one example, a merchandise security system includes a plurality of articles of merchandise on display in a retail store and at least one machine learning camera configured to capture images of one or more of the articles of merchandise for detecting information regarding the articles of merchandise, making predictions based on such information, and providing notifications based on such information.Type: GrantFiled: March 26, 2020Date of Patent: December 17, 2024Assignee: InVue Security Products Inc.Inventors: Jeffrey A. Grant, Christopher J. Fawcett, Laura Abbott Lynch, Gary A. Taylor, David N. Berglund, James Richard Terrell, II
-
Patent number: 12170099Abstract: Systems, apparatus, and methods for encoding telemetry data as audio waveforms. Action cameras may be used to capture telemetry data, which in some applications, may be more useful than its audio/visual media capture. For example, a user may desire the “look-and-feel” of one camera but would like to use the telemetry track information from an action camera. In so-called “piggybacking” operation, the user may rigidly affix the two cameras and use the video track with the telemetry track in post-processing. Unfortunately, time-aligning the two tracks can result in relative drift over time. Various embodiments of the present disclosure transfer telemetry data as data-over-audio. The data-over-audio may be sampled according to the recipient device and recorded at capture. Subsequent post-processing may be performed with the time-aligned tracks.Type: GrantFiled: June 2, 2022Date of Patent: December 17, 2024Assignee: GoPro, Inc.Inventors: David Newman, Robert McIntosh
-
Patent number: 12169275Abstract: A light filed (LF) display system for displaying holographic performance content (e.g., a live performance) to viewers in a venue. The LF display system in the venue includes LF display modules tiled together to form an array of LF modules. The array of LF modules create a performance volume (e.g., a stage) for displaying the performance content in the venue. The array of LF modules displays the performance content to viewers in viewing volumes. The LF display system can be included in a LF presentation network. The LF presentation network allows holographic performance content to be recorded at one location and displayed (concurrently or non-concurrently) at another location. The LF presentation network includes a network system to manage the digital rights of the holographic performance content.Type: GrantFiled: August 10, 2022Date of Patent: December 17, 2024Assignee: Light Field Lab, Inc.Inventors: Jonathan Sean Karafin, Brendan Elwood Bevensee, John Dohm
-
Patent number: 12154598Abstract: A system and method for editing videos is disclosed. Specifically, the embodiments provide systems and methods that allow users to generate synthetic video segments that are synchronized with an edited audio track. The system and method make use of autoencoders to modify the facial features, including mouth movements, of a subject.Type: GrantFiled: March 28, 2023Date of Patent: November 26, 2024Assignee: United Services Automobile Association (USAA)Inventors: Mark Paxman Warnick, Ravi Durairaj, Joel S. Hartshorn, Nathan Lee Post
-
Patent number: 12149778Abstract: Systems and methods are disclosed herein for classifying, based on most recent information associated with recorded content, the recorded content to an appropriate deletion classifier. A media guidance application may receive information about an event that is associated with a recorded media asset. The media guidance application may determine, based on the event and a current deletion classifier associated with the recorded media asset, whether the current deletion classifier associated with the recorded media asset needs to be updated to a new deletion classifier. The media guidance application may make this determination by accessing a deletion classification database containing rules for classifying recorded media assets into a variety of deletion classifiers.Type: GrantFiled: November 22, 2022Date of Patent: November 19, 2024Assignee: Adeia Guides Inc.Inventors: Vishwas Sharadanagar Panchaksharaiah, Gaurav Gupta, Nimit Dineshbhai Kalaria
-
Patent number: 12148214Abstract: With rapidly evolving technologies and emerging tools, sports-related videos generated online are rapidly increasing. To automate the sports video editing/highlight generation process, a key task is to precisely recognize and locate events-of-interest in videos. Embodiments herein comprise a two-stage paradigm to detect categories of events and when these events happen in videos. In one or more embodiments, multiple action recognition models extract high-level semantic features, and a transformer-based temporal detection module locates target events. These novel approaches achieved state-of-the-art performance in both action spotting and replay grounding. While presented in the context of sports, it shall be noted that the systems and methods herein may be used for videos comprising other content and events.Type: GrantFiled: January 10, 2022Date of Patent: November 19, 2024Inventors: Zhiyu Cheng, Le Kang, Xin Zhou, Hao Tian, Xing Li, Bo He, Jingyu Xin
-
Patent number: 12142296Abstract: Disclosed in the embodiments of the present disclosure are an audio processing method and apparatus, and an electronic device and a storage medium. The method comprises: in response to a trigger operation of entering a video editing page for a target video for the first time, displaying the video editing page; and if original audio in the target video meets a preset condition, performing sound repair processing on the original audio while displaying the video editing page, and displaying, in the video editing page, a target control in a first state, wherein the target control in the first state is used for indicating that the sound repair processing is being performed on the original audio.Type: GrantFiled: December 22, 2023Date of Patent: November 12, 2024Assignee: Beijing Zitiao Network Technology Co., Ltd.Inventors: Wenwen Zhang, Weiming Zheng, Wanli Che