Systems and methods for identifying scene changes in video files

    公开(公告)号:US12079274B2

    公开(公告)日:2024-09-03

    申请号:US16162212

    申请日:2018-10-16

    发明人: Qiang Fu

    摘要: Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of: receiving at least two consecutive frames of a video file; determining a level of difference between the at least two consecutive frames of the video file; receiving a subtitle file associated with the video file; analyzing the subtitle file to identify a gap in conversation in the video file; and identifying a scene change in the video file when: (1) the level of difference between the at least two consecutive frames of the video file is above a predefined threshold; and (2) the level of difference between the at least two consecutive frames of the video file occurs during the gap in the conversation. Other embodiments are disclosed herein.

    AUTOMATICALLY AUTHENTICATING AND INPUTTING OBJECT INFORMATION

    公开(公告)号:US20240221167A1

    公开(公告)日:2024-07-04

    申请号:US18147642

    申请日:2022-12-28

    发明人: Qiang FU

    摘要: According to at least one embodiment, a multi-angle multi-time-point method authenticates 2D objects with high confidence by sampling the object through space and time while being capable of automatically authenticating and inputting object information. Some embodiments further enhance authentication confidence by utilizing unique characteristics of hologram and/or personal photo. While this method possesses artificial intelligence comparable to human's in term of authenticating and extracting information from 2D objects, it's also highly efficient and can achieve real-time performance (e.g., processing 5 frames per second) on ordinary personal computers. Structural information is first extracted from a 2D image to reduce processing time for subsequent steps as more operations on the 2D images are avoided. By employing similar divide-and-conquer strategy according to a binary search algorithm for 1D data array, a Visual Binary Edge Search Algorithm is applied to a 2D image application.

    Spread channel multi-CDN streaming

    公开(公告)号:US11910053B2

    公开(公告)日:2024-02-20

    申请号:US17644752

    申请日:2021-12-16

    发明人: Qiang Fu

    摘要: Traditional streaming sequentially downloads content fragments one by one from one CDN. The disclosed streaming method concurrently downloads content fragments from multiple CDNs. It first creates a sequence of bundles of fragments, and then downloads a subsequent bundle by spreading requests to download the fragments within the bundle to multiple CDNs simultaneously with each CDN acting as a channel to download a different fragment. Depending on business needs, various request dispatching strategies can be deployed. When there is a volume based pricing contract with a CDN, a dispatch strategy is to send more requests to the CDN in order to reach contract volume therefore reduce unit cost. Another strategy is to send the request for the earliest fragment to the fastest CDN in order to reduce latency and possibility of buffer underrun. Fault tolerance can be provided by re-routing a request failed at a CDN to another CDN.

    DYNAMIC TONE-MAPPING SYSTEM NORMALIZED AROUND REFERENCE WHITE

    公开(公告)号:US20240029219A1

    公开(公告)日:2024-01-25

    申请号:US18076140

    申请日:2022-12-06

    IPC分类号: G06T5/00 G06T9/00

    摘要: A dynamic and selective tone mapping system that receives digital imagery content and adjusts the digital imagery content using defined perceptual point parameters that correspond to particular luminance points or regions of the digital imagery content. The defined perceptual point parameters include a first white reference value, wherein the tone mapping system adjusts the digital imagery content by compressing luminance values above the first white reference value at different compression rates to produce digital imagery content that is compatible with various media viewing devices with varying display brightness capabilities while preserving influence over the intended look of the displayed image resulting from the digital imagery content.

    Determining subtitle synchronization when compared to audio track

    公开(公告)号:US11776559B2

    公开(公告)日:2023-10-03

    申请号:US17450548

    申请日:2021-10-11

    摘要: According to at least one embodiment, a method for determining a level of synchronicity between subtitle text in audiovisual content and speech that would be heard during display of the audiovisual content includes: accessing a first binary sequence, each bit of the first binary sequence indicating whether the speech is provided at a respective sampling time of a plurality of sampling times; and accessing a second binary sequence, each bit of the second binary sequence indicating whether the subtitle text is provided at a respective sampling time of a plurality of sampling times. The method further includes comparing the first binary sequence and the second binary sequence to determine the level of synchronicity between the subtitle text and the speech.

    SPREAD CHANNEL MULTI-CDN STREAMING
    8.
    发明公开

    公开(公告)号:US20230199247A1

    公开(公告)日:2023-06-22

    申请号:US17644752

    申请日:2021-12-16

    发明人: Qiang FU

    摘要: Traditional streaming sequentially downloads content fragments one by one from one CDN. The disclosed streaming method concurrently downloads content fragments from multiple CDNs. It first creates a sequence of bundles of fragments, and then downloads a subsequent bundle by spreading requests to download the fragments within the bundle to multiple CDNs simultaneously with each CDN acting as a channel to download a different fragment. Depending on business needs, various request dispatching strategies can be deployed. When there is a volume based pricing contract with a CDN, a dispatch strategy is to send more requests to the CDN in order to reach contract volume therefore reduce unit cost. Another strategy is to send the request for the earliest fragment to the fastest CDN in order to reduce latency and possibility of buffer underrun. Fault tolerance can be provided by re-routing a request failed at a CDN to another CDN.

    SYSTEMS AND METHODS FOR PERFORMING WORD-SENSE DISAMBIGUATION FOR CONTEXT-SENSITIVE SERVICES

    公开(公告)号:US20220405482A1

    公开(公告)日:2022-12-22

    申请号:US17349456

    申请日:2021-06-16

    发明人: Gregory A. Tam

    IPC分类号: G06F40/35 G06F3/0482

    摘要: A word-sense disambiguation service may be performed to determine the semantic context of an ambiguous targeted word in an electronic data corpus. The word-sense disambiguation service may determine the semantic context of the words in the electronic data corpus by evaluating a main word and the context words surrounding the main word in a portion of text, then determine which context words are useful in defining the semantic context of the main word. The word-sense disambiguation service may then cluster the defining context words together and use the defining context words to train a word-embedding model to recognize the semantic context of an instance of the main word based on the proximity of the defining context words to the main word. A context-sensitive service may then receive input of a desired target word, then retrieve and display the various semantic contexts of the desired target word using the results gathered by the word-sense disambiguation service.