-
公开(公告)号:US20220030244A1
公开(公告)日:2022-01-27
申请号:US17492789
申请日:2021-10-04
Applicant: Apple Inc.
Inventor: Yeping Su , Xingyu Zhang , Chris Chung , Jun Xin , Hsi-Jung Wu
IPC: H04N19/136 , H04N19/103 , G06N20/00 , H04N19/179
Abstract: Techniques are disclosed by which a coding parameter is determined to encode video data resulting in encoded video data possessing a highest possible video quality. Features may be extracted from an input video sequence. The extracted features may be compared to features described in a model of coding parameters generated by a machine learning algorithm from reviews of previously-coded videos, extracted features of the previously-coded videos, and coding parameters of the previously-coded videos. When a match is detected between the extracted features of the input video sequence and extracted features represented in the model, a determination may be made as to whether coding parameters that correspond to the matching extracted feature correspond to a tier of service to which the input video sequence is to be coded. When the coding parameters that correspond to the matching extracted feature correspond to the tier of service to which the input video sequence is to be coded, the input video sequence may be coded according to the coding parameters.
-
公开(公告)号:US11240492B2
公开(公告)日:2022-02-01
申请号:US16254528
申请日:2019-01-22
Applicant: Apple Inc.
Inventor: Jiefu Zhai , Xingyu Zhang , Xiaosong Zhou , Jun Xin , Hsi-Jung Wu , Yeping Su
IPC: H04N19/105 , H04N19/61 , H04N19/147 , H04N19/159 , H04N19/176 , G06N3/08
Abstract: Systems and methods disclosed for video compression, utilizing neural networks for predictive video coding. Processes employed combine multiple banks of neural networks with codec system components to carry out the coding and decoding of video data.
-
公开(公告)号:US11166027B2
公开(公告)日:2021-11-02
申请号:US15614881
申请日:2017-06-06
Applicant: Apple Inc.
Inventor: Yeping Su , Xingyu Zhang , Chris Chung , Jun Xin , Hsi-Jung Wu
IPC: H04B1/66 , H04N19/136 , H04N19/103 , G06N20/00 , H04N19/179 , H04N21/845 , H04N21/2343
Abstract: Techniques are disclosed by which a coding parameter is determined to encode video data resulting in encoded video data possessing a highest possible video quality. Features may be extracted from an input video sequence. The extracted features may be compared to features described in a model of coding parameters generated by a machine learning algorithm from reviews of previously-coded videos, extracted features of the previously-coded videos, and coding parameters of the previously-coded videos. When a match is detected between the extracted features of the input video sequence and extracted features represented in the model, a determination may be made as to whether coding parameters that correspond to the matching extracted feature correspond to a tier of service to which the input video sequence is to be coded. When the coding parameters that correspond to the matching extracted feature correspond to the tier of service to which the input video sequence is to be coded, the input video sequence may be coded according to the coding parameters.
-
公开(公告)号:US20170359580A1
公开(公告)日:2017-12-14
申请号:US15614881
申请日:2017-06-06
Applicant: Apple Inc.
Inventor: Yeping Su , Xingyu Zhang , Chris Chung , Jun Xin , Hsi-Jung Wu
IPC: H04N19/139 , H04N19/103 , H04N19/44 , G06N99/00 , H04N21/845
CPC classification number: G06N20/00 , H04N19/103 , H04N19/136 , H04N19/179 , H04N21/23439 , H04N21/8456
Abstract: Techniques are disclosed by which a coding parameter is determined to encode video data resulting in encoded video data possessing a highest possible video quality. Features may be extracted from an input video sequence. The extracted features may be compared to features described in a model of coding parameters generated by a machine learning algorithm from reviews of previously-coded videos, extracted features of the previously-coded videos, and coding parameters of the previously-coded videos. When a match is detected between the extracted features of the input video sequence and extracted features represented in the model, a determination may be made as to whether coding parameters that correspond to the matching extracted feature correspond to a tier of service to which the input video sequence is to be coded. When the coding parameters that correspond to the matching extracted feature correspond to the tier of service to which the input video sequence is to be coded, the input video sequence may be coded according to the coding parameters.
-
公开(公告)号:US12192440B2
公开(公告)日:2025-01-07
申请号:US17568266
申请日:2022-01-04
Applicant: Apple Inc.
Inventor: Jiefu Zhai , Xingyu Zhang , Xiaosong Zhou , Jun Xin , Hsi-Jung Wu , Yeping Su
IPC: H04N19/105 , G06N3/08 , H04N19/147 , H04N19/159 , H04N19/176 , H04N19/61
Abstract: Systems and methods disclosed for video compression, utilizing neural networks for predictive video coding. Processes employed combine multiple banks of neural networks with codec system components to carry out the coding and decoding of video data.
-
公开(公告)号:US12149699B2
公开(公告)日:2024-11-19
申请号:US17492789
申请日:2021-10-04
Applicant: Apple Inc.
Inventor: Yeping Su , Xingyu Zhang , Chris Chung , Jun Xin , Hsi-Jung Wu
IPC: H04N19/136 , G06N20/00 , H04N19/103 , H04N19/179 , H04N21/2343 , H04N21/845
Abstract: Techniques are disclosed by which a coding parameter is determined to encode video data resulting in encoded video data possessing a highest possible video quality. Features may be extracted from an input video sequence. The extracted features may be compared to features described in a model of coding parameters generated by a machine learning algorithm from reviews of previously-coded videos, extracted features of the previously-coded videos, and coding parameters of the previously-coded videos. When a match is detected between the extracted features of the input video sequence and extracted features represented in the model, a determination may be made as to whether coding parameters that correspond to the matching extracted feature correspond to a tier of service to which the input video sequence is to be coded. When the coding parameters that correspond to the matching extracted feature correspond to the tier of service to which the input video sequence is to be coded, the input video sequence may be coded according to the coding parameters.
-
-
-
-
-