公开(公告)号：US20220207875A1

公开(公告)日：2022-06-30

申请号：US17550852

申请日：2021-12-14

Applicant: Snap Inc.

Inventor： Kavya Venkata Kota Kopparapu ,  Benjamin Dodson ,  Francesc Xavier Drudis Rius ,  Angus Kong ,  Richard Leider ,  Jian Ren ,  Sergey Tulyakov ,  Jiayao Yu

IPC: G06V20/40 ,  G06N20/00 ,  G06T5/00 ,  G06V10/70 ,  G06V20/70 ,  G06F16/783

Abstract: Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.

公开(公告)号：US20240282110A1

公开(公告)日：2024-08-22

申请号：US18653718

申请日：2024-05-02

Applicant: Snap Inc.

Inventor： Kavya Venkata Kota Kopparapu ,  Benjamin Dodson ,  Francesc Xavier Drudis Rius ,  Angus Kong ,  Richard Leider ,  Jien Ren ,  Sergey Tulyakov ,  Jiayao Yu

IPC: G06V20/40 ,  G06F16/783 ,  G06N20/00 ,  G06T5/70 ,  G06V10/70 ,  G06V20/70

CPC classification number: G06V20/46 ,  G06F16/785 ,  G06N20/00 ,  G06T5/70 ,  G06V10/70 ,  G06V20/70

Abstract: Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.

公开(公告)号：US12008811B2

公开(公告)日：2024-06-11

申请号：US17550852

申请日：2021-12-14

Applicant: Snap Inc.

Inventor： Kavya Venkata Kota Kopparapu ,  Benjamin Dodson ,  Francesc Xavier Drudis Rius ,  Angus Kong ,  Richard Leider ,  Jian Ren ,  Sergey Tulyakov ,  Jiayao Yu

IPC: G06K9/00 ,  G06F16/783 ,  G06N20/00 ,  G06T5/70 ,  G06V10/70 ,  G06V20/40 ,  G06V20/70

CPC classification number: G06V20/46 ,  G06F16/785 ,  G06N20/00 ,  G06T5/70 ,  G06V10/70 ,  G06V20/70

Abstract: Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.