公开(公告)号：US12190474B2

公开(公告)日：2025-01-07

申请号：US17739004

申请日：2022-05-06

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Ru Wang ,  Yaqing Li ,  Chengjie Tu ,  Shiyao Xiong ,  Linyan Jiang ,  Longtao Peng

IPC: G06T3/4053 ,  G06T3/4046

Abstract: A computing device obtains a to-be-processed video frame sequence of a first resolution. For each to-be-processed video frame in the to-be-processed video frame sequence, the computing device: (i) performs resolution reconstruction according to a resolution reconstruction model so as to obtain an initial reconstructed video frame of a second resolution, (ii) determines a contour region in the initial reconstructed video frame; and (iii) performs contour enhancement on the contour region to obtain a target reconstructed video frame. The computing device generates a reconstructed video frame sequence of the second resolution according to a plurality of target reconstructed video frames corresponding to the plurality of to-be-processed video frames.

公开(公告)号：US10169250B2

公开(公告)日：2019-01-01

申请号：US14734798

申请日：2015-06-09

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Yaqing Li ,  Jianping Zhu

IPC: G06F17/30 ,  G06F12/14 ,  G06F3/06

Abstract: A method and apparatus for controlling access to a hash-based disk is provided, the disk comprising a storage object, the storage object comprising a set of records and a hash value, the method comprising constructing a Bloom filter for the storage object; reading the set of records in the storage object; and filtering an access request to the storage object using the Bloom filter. In accordance with embodiments of the present invention, access requests to storage objects on the disk are filtered by a Bloom filter to reduce unnecessary accesses to the disk, and input and output accesses to the disk are reduced.

公开(公告)号：US11871017B2

公开(公告)日：2024-01-09

申请号：US17723857

申请日：2022-04-19

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Shishen Xu ,  Jingran Wu ,  Jun Zhao ,  Juncheng Ma ,  Yaqing Li ,  Chengjie Tu ,  Liang Wang

IPC: H04N19/40 ,  H04N19/136 ,  H04N19/154

CPC classification number: H04N19/40 ,  H04N19/136 ,  H04N19/154

Abstract: A video data processing method is provided. In the method, video features of a target video are acquired. The video features include background features and key part region features. An expected quality of a key part of the target video is acquired. The expected quality of the key part corresponds to an image quality of the key part in a transcoded target video after the target video is transcoded. A background prediction transcoding parameter of the target video is determined based on the background features and an expected quality of a background. The expected quality of the background corresponds to an overall image quality of the transcoded target video. A target transcoding parameter prediction value is determined based on the background features, the key part region features, and the background prediction transcoding parameter. The target video is transcoded according to the target transcoding parameter prediction value.

公开(公告)号：US20220261960A1

公开(公告)日：2022-08-18

申请号：US17739004

申请日：2022-05-06

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Ru Wang ,  Yaqing Li ,  Chengjie Tu ,  Shiyao Xiong ,  Linyan Jiang ,  Longtao Peng

IPC: G06T3/40

Abstract: A computing device obtains a to-be-processed video frame sequence of a first resolution. For each to-be-processed video frame in the to-be-processed video frame sequence, the computing device: (i) performs resolution reconstruction according to a resolution reconstruction model so as to obtain an initial reconstructed video frame of a second resolution, (ii) determines a contour region in the initial reconstructed video frame; and (iii) performs contour enhancement on the contour region to obtain a target reconstructed video frame. The computing device generates a reconstructed video frame sequence of the second resolution according to a plurality of target reconstructed video frames corresponding to the plurality of to-be-processed video frames.

公开(公告)号：US11076168B2

公开(公告)日：2021-07-27

申请号：US16597606

申请日：2019-10-09

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Sixin Lin ,  Hongshun Zhang ,  Yaqing Li

IPC: H04N19/517 ,  H04N19/52 ,  H04N19/105 ,  H04N19/139 ,  H04N19/159 ,  H04N19/176

Abstract: Embodiments of the present disclosure provide an inter-frame prediction method performed at a computing device. The method includes: determining at least one reference encoded block spatially adjacent to a to-be-processed prediction unit of a to-be-processed encoded block; for each preset reference frame, separately determining a corresponding AMVP of the to-be-processed prediction unit according to reference information of each reference encoded block; determining a target AMVP under the reference frames, and using a reference frame corresponding to the target AMVP as a candidate reference frame; when the candidate reference frame is different from the first reference frame, performing motion estimation on the to-be-processed prediction unit separately and determining a target reference frame from the candidate reference frame and the first reference frame according to their corresponding encoding costs obtained through the motion estimation.

公开(公告)号：US20150278117A1

公开(公告)日：2015-10-01

申请号：US14734798

申请日：2015-06-09

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Yaqing Li ,  Jianping Zhu ,  Zhimin He

IPC: G06F12/14 ,  G06F17/30

CPC classification number: G06F12/14 ,  G06F3/0616 ,  G06F3/0659 ,  G06F3/0676 ,  G06F17/3033 ,  G06F2212/1052

Abstract: A method and apparatus for controlling access to a hash-based disk is provided, the disk comprising a storage object, the storage object comprising a set of records and a hash value, the method comprising constructing a Bloom filter for the storage object; reading the set of records in the storage object; and filtering an access request to the storage object using the Bloom filter. In accordance with embodiments of the present invention, access requests to storage objects on the disk are filtered by a Bloom filter to reduce unnecessary accesses to the disk, and input and output accesses to the disk are reduced.

Abstract translation: 提供了一种用于控制对基于散列的盘的访问的方法和装置，所述盘包括存储对象，所述存储对象包括一组记录和散列值，所述方法包括为所述存储对象构建布隆过滤器; 读取存储对象中的记录集; 并使用Bloom过滤器对存储对象的访问请求进行过滤。 根据本发明的实施例，通过Bloom过滤器来过滤对盘上的存储对象的访问请求，以减少对盘的不必要的访问，并且减少对盘的访问和访问。

公开(公告)号：US12052427B2

公开(公告)日：2024-07-30

申请号：US17713205

申请日：2022-04-04

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Jingran Wu ,  Shishen Xu ,  Jun Zhao ,  Hao Li ,  Yaqing Li ,  Chengjie Tu ,  Zirong Zhu ,  Liang Wang

IPC: H04N19/146 ,  H04N19/159 ,  H04N19/172 ,  H04N19/34

CPC classification number: H04N19/146 ,  H04N19/159 ,  H04N19/172 ,  H04N19/34

Abstract: A video data processing method is provided to a server. The method includes: obtaining a video sequence associated with a video source and obtaining a video quality standard parameter associated with the video sequence; determining a video feature according to video quality standard parameter; predicting an encoding bit rate according to the video quality standard parameter and the video feature; and encoding the video sequence according to the encoding bit rate to obtain an encoded video sequence associated with the video source.

公开(公告)号：US20200045330A1

公开(公告)日：2020-02-06

申请号：US16597606

申请日：2019-10-09

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Sixin LIN ,  Hongshun ZHANG ,  Yaqing Li

IPC: H04N19/517 ,  H04N19/105 ,  H04N19/139 ,  H04N19/159 ,  H04N19/176

Abstract: Embodiments of the present disclosure provide an inter-frame prediction method performed at a computing device. The method includes: determining at least one reference encoded block spatially adjacent to a to-be-processed prediction unit of a to-be-processed encoded block; for each preset reference frame, separately determining a corresponding AMVP of the to-be-processed prediction unit according to reference information of each reference encoded block; determining a target AMVP under the reference frames, and using a reference frame corresponding to the target AMVP as a candidate reference frame; when the candidate reference frame is different from the first reference frame, performing motion estimation on the to-be-processed prediction unit separately and determining a target reference frame from the candidate reference frame and the first reference frame according to their corresponding encoding costs obtained through the motion estimation.