-
Patent Agency Ranking
公开(公告)号：US11348328B2
公开(公告)日：2022-05-31
申请号：US17249499
申请日：2021-03-03
Applicant: Snap Inc.
Inventor： Meng Song , Harsh Agrawal , Xiaoyu Wang , Xuan Huang , William Brendel
Abstract: Systems, devices, media, and methods are presented for graphical icon identification within an image or video stream. The systems and methods receive an image including a graphical icon. The systems and methods identify a set of proposed regions of the image, at least one proposed region of the set of proposed regions containing the graphical icon and extract a set of semantic features for each proposed region of the set of proposed regions. Based on the set of semantic features of the set of proposed regions, the systems and methods identify a set of proposed icons corresponding to the graphical icon included in the image and determine a match between the graphical icon and at least one proposed icon of the set of proposed icons.
-
公开(公告)号：US10970577B1
公开(公告)日：2021-04-06
申请号：US16136998
申请日：2018-09-20
Applicant: Snap Inc.
Inventor： Meng Song , Harsh Agrawal , Xiaoyu Wang , Xuan Huang , William Brendel
Abstract: Systems, devices, media, and methods are presented for graphical icon identification within an image or video stream. The systems and methods receive an image including a graphical icon. The systems and methods identify a set of proposed regions of the image, at least one proposed region of the set of proposed regions containing the graphical icon and extract a set of semantic features for each proposed region of the set of proposed regions. Based on the set of semantic features of the set of proposed regions, the systems and methods identify a set of proposed icons corresponding to the graphical icon included in the image and determine a match between the graphical icon and at least one proposed icon of the set of proposed icons.
-
公开(公告)号：US20220262092A1
公开(公告)日：2022-08-18
申请号：US17661868
申请日：2022-05-03
Applicant: Snap Inc.
Inventor： Meng Song , Harsh Agrawal , Xiaoyu Wang , Xuan Huang , William Brendel
Abstract: Systems, devices, media, and methods are presented for graphical icon identification within an image or video stream. The systems and methods receive an image including a graphical icon. The systems and methods identify a set of proposed regions of the image, at least one proposed region of the set of proposed regions containing the graphical icon and extract a set of semantic features for each proposed region of the set of proposed regions. Based on the set of semantic features of the set of proposed regions, the systems and methods identify a set of proposed icons corresponding to the graphical icon included in the image and determine a match between the graphical icon and at least one proposed icon of the set of proposed icons.
-
公开(公告)号：US11676019B2
公开(公告)日：2023-06-13
申请号：US17661868
申请日：2022-05-03
Applicant: Snap Inc.
Inventor： Meng Song , Harsh Agrawal , Xiaoyu Wang , Xuan Huang , William Brendel
CPC classification number: G06N3/08 , G06F18/22 , G06N20/00 , G06V10/751 , G06V20/10
Abstract: Systems, devices, media, and methods are presented for graphical icon identification within an image or video stream. The systems and methods receive an image including a graphical icon. The systems and methods identify a set of proposed regions of the image, at least one proposed region of the set of proposed regions containing the graphical icon and extract a set of semantic features for each proposed region of the set of proposed regions. Based on the set of semantic features of the set of proposed regions, the systems and methods identify a set of proposed icons corresponding to the graphical icon included in the image and determine a match between the graphical icon and at least one proposed icon of the set of proposed icons.
-
公开(公告)号：US20210192259A1
公开(公告)日：2021-06-24
申请号：US17249499
申请日：2021-03-03
Applicant: Snap Inc.
Inventor： Meng Song , Harsh Agrawal , Xiaoyu Wang , Xuan Huang , William Brendel
Abstract: Systems, devices, media, and methods are presented for graphical icon identification within an image or video stream. The systems and methods receive an image including a graphical icon. The systems and methods identify a set of proposed regions of the image, at least one proposed region of the set of proposed regions containing the graphical icon and extract a set of semantic features for each proposed region of the set of proposed regions. Based on the set of semantic features of the set of proposed regions, the systems and methods identify a set of proposed icons corresponding to the graphical icon included in the image and determine a match between the graphical icon and at least one proposed icon of the set of proposed icons.
-
-
-
-
Search Results
5
records
(took 0.016 seconds)
