-
公开(公告)号：US11182639B2
公开(公告)日：2021-11-23
申请号：US15953107
申请日：2018-04-13
Applicant: Facebook, Inc.
Inventor： Evgeny V. Kuzyakov , Renbin Peng , Chien-Nan Chen
Abstract: Systems, methods, and non-transitory computer-readable media can provide at least one frame of a content item to a saliency prediction model, the saliency prediction model being trained to identify salient points of interest that appear in content items. Information describing at least a first salient point of interest that appears in the at least one frame can be obtained from the saliency prediction model. The first salient point of interest can be predicted to be of interest to users accessing the content item. A view-based projection can be applied to a region corresponding to the first salient point of interest, wherein the view-based projection enhances a quality in which the region is presented.
-
公开(公告)号：US20180300584A1
公开(公告)日：2018-10-18
申请号：US15953107
申请日：2018-04-13
Applicant: Facebook, Inc.
Inventor： Evgeny V. Kuzyakov , Renbin Peng , Chien-Nan Chen
IPC: G06K9/46 , H04N13/122 , H04N21/81 , H04N21/234 , G06K9/62 , G06T5/00
Abstract: Systems, methods, and non-transitory computer-readable media can provide at least one frame of a content item to a saliency prediction model, the saliency prediction model being trained to identify salient points of interest that appear in content items. Information describing at least a first salient point of interest that appears in the at least one frame can be obtained from the saliency prediction model. The first salient point of interest can be predicted to be of interest to users accessing the content item. A view-based projection can be applied to a region corresponding to the first salient point of interest, wherein the view-based projection enhances a quality in which the region is presented.
-
公开(公告)号：US20180302601A1
公开(公告)日：2018-10-18
申请号：US15488484
申请日：2017-04-16
Applicant: Facebook, Inc.
Inventor： Chien-Nan Chen
CPC classification number: H04N13/366 , H04N5/23238 , H04N21/23412 , H04N21/25891
Abstract: Systems, methods, and non-transitory computer-readable media can determine a first position corresponding to a user focal point prior to presenting a given frame of a content item. A landscape representation of the given frame is determined. The landscape representation describes the respective popularity of one or more regions in the frame as a topology. A second position corresponding to the user focal point is determined based at least in part on the landscape representation and the first position. The second position is predicted to be the position of the user focal point when presenting the given frame.
-
公开(公告)号：US20180300848A1
公开(公告)日：2018-10-18
申请号：US15953164
申请日：2018-04-13
Applicant: Facebook, Inc.
Inventor： Evgeny V. Kuzyakov , Renbin Peng , Chien-Nan Chen
CPC classification number: G06K9/4671 , G06K9/00671 , G06K9/00677 , G06K9/6256 , G06T3/0062 , G06T3/0087 , G06T5/006 , G06T5/007 , G06T2207/20068 , G06T2207/30196 , H04N21/23418 , H04N21/816
Abstract: Systems, methods, and non-transitory computer-readable media can determine at least one salient point of interest in a frame of a content item based at least in part on a saliency prediction model, the saliency prediction model being trained to identify salient points of interest that appear in content items; determine a barrel projection representation for the frame; and apply a view-based projection to the barrel projection representation for the frame, wherein the view-based projection enhances a quality in which a region corresponding to the at least one salient point of interest is presented.
-
公开(公告)号：US20170084086A1
公开(公告)日：2017-03-23
申请号：US15271099
申请日：2016-09-20
Applicant: Facebook, Inc.
Inventor： David Young Joon Pio , Evgeny V. Kuzyakov , Chien-Nan Chen
CPC classification number: G06T7/60 , G06T3/0012 , H04N21/816
Abstract: Systems, methods, and non-transitory computer-readable media can obtain a spherical media content item that captures at least one scene from a plurality of different positions. A three-dimensional object with a plurality of faces that converge at a point is determined. At least a first portion of the spherical media content item is mapped to at least a first face in the plurality of faces.
-
Patent Agency Ranking
公开(公告)号：US10579898B2
公开(公告)日：2020-03-03
申请号：US15953164
申请日：2018-04-13
Applicant: Facebook, Inc.
Inventor： Evgeny V. Kuzyakov , Renbin Peng , Chien-Nan Chen
Abstract: Systems, methods, and non-transitory computer-readable media can determine at least one salient point of interest in a frame of a content item based at least in part on a saliency prediction model, the saliency prediction model being trained to identify salient points of interest that appear in content items; determine a barrel projection representation for the frame; and apply a view-based projection to the barrel projection representation for the frame, wherein the view-based projection enhances a quality in which a region corresponding to the at least one salient point of interest is presented.
-
公开(公告)号：US10484675B2
公开(公告)日：2019-11-19
申请号：US15488484
申请日：2017-04-16
Applicant: Facebook, Inc.
Inventor： Chien-Nan Chen
IPC: H04N13/366 , H04N21/234 , H04N21/258 , H04N5/232
Abstract: Systems, methods, and non-transitory computer-readable media can determine a first position corresponding to a user focal point prior to presenting a given frame of a content item. A landscape representation of the given frame is determined. The landscape representation describes the respective popularity of one or more regions in the frame as a topology. A second position corresponding to the user focal point is determined based at least in part on the landscape representation and the first position. The second position is predicted to be the position of the user focal point when presenting the given frame.
-
公开(公告)号：US20190236799A1
公开(公告)日：2019-08-01
申请号：US16127905
申请日：2018-09-11
Applicant: Facebook, Inc.
Inventor： David Young Joon Pio , Evgeny V. Kuzyakov , Chien-Nan Chen
CPC classification number: G06T7/60 , G06T3/0012 , H04N21/816
Abstract: Systems, methods, and non-transitory computer-readable media can obtain a spherical media content item that captures at least one scene from a plurality of different positions. A three-dimensional object with a plurality of faces that converge at a point is determined. At least a first portion of the spherical media content item is mapped to at least a first face in the plurality of faces.
-
公开(公告)号：US20180108171A1
公开(公告)日：2018-04-19
申请号：US15847184
申请日：2017-12-19
Applicant: Facebook, Inc.
Inventor： David Young Joon Pio , Evgeny V. Kuzyakov , Chien-Nan Chen
CPC classification number: G06T15/20 , G06F3/011 , G06T3/005 , G06T2200/04 , H04N21/6125 , H04N21/816
Abstract: Systems, methods, and non-transitory computer-readable media can obtain a spherical media content item that captures at least one scene from a plurality of different positions. A three-dimensional shape having a plurality of faces is determined, each face being associated with a respective set of original boundaries. A respective set of expanded boundaries for one or more of the plurality of faces is determined. Respective portions of the spherical media content item are mapped to each of the one or more faces, wherein a first portion of the spherical media content item is mapped to a first face having a set of expanded boundaries.
-
公开(公告)号：US20220092332A1
公开(公告)日：2022-03-24
申请号：US17509980
申请日：2021-10-25
Applicant: Facebook, Inc.
Inventor： Evgeny V. Kuzyakov , Renbin Peng , Chien-Nan Chen
Abstract: Systems, methods, and non-transitory computer-readable media can provide at least one frame of a content item to a saliency prediction model, the saliency prediction model being trained to identify salient points of interest that appear in content items. Information describing at least a first salient point of interest that appears in the at least one frame can be obtained from the saliency prediction model. The first salient point of interest can be predicted to be of interest to users accessing the content item. A view-based projection can be applied to a region corresponding to the first salient point of interest, wherein the view-based projection enhances a quality in which the region is presented.
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.015 seconds)
