-
公开(公告)号：US11003692B2
公开(公告)日：2021-05-11
申请号：US14980572
申请日：2015-12-28
申请人： Facebook, Inc.
发明人： Yunchao Gong , Marcin Pawlowski , Fei Yang , Lubomir Bourdev , Louis Dominic Brandy , Robert D. Fergus
IPC分类号： G06F16/28 , H04L29/08 , G06N20/00 , G06F16/901
摘要： Systems, methods, and non-transitory computer-readable media can obtain a first batch of content items to be clustered. A set of clusters can be generated by clustering respective binary hash codes for each content item in the first batch, wherein content items included in a cluster are visually similar to one another. A next batch of content items to be clustered can be obtained. One or more respective binary hash codes for the content items in the next batch can be assigned to a cluster in the set of clusters.
-
公开(公告)号：US20210004662A1
公开(公告)日：2021-01-07
申请号：US17030157
申请日：2020-09-23
申请人： Facebook, Inc.
发明人： Kai Li , Fei Yang , Balamanohar Paluri
IPC分类号： G06N3/04 , G06F16/783
摘要： Systems, methods, and non-transitory computer-readable media can receive a first content item having a set of frames. A binary hash code that represents the first content item is generated using at least an aggregation model and an iterative quantization hash model, the binary hash code being determined based at least in part on the set of frames of the first content item. The binary hash code is stored, wherein a similarity between the first content item and a second content item is capable of being measured based at least in part on a comparison of the binary hash code of the first content item and a binary hash code of the second content item.
-
公开(公告)号：US20170185665A1
公开(公告)日：2017-06-29
申请号：US14980572
申请日：2015-12-28
申请人： Facebook, Inc.
发明人： Yunchao Gong , Marcin Pawlowski , Fei Yang , Lubomir Bourdev , Louis Dominic Brandy , Robert D. Fergus
CPC分类号： G06F16/285 , G06F16/9024 , G06N20/00 , H04L67/10 , H04L67/1097
摘要： Systems, methods, and non-transitory computer-readable media can obtain a first batch of content items to be clustered. A set of clusters can be generated by clustering respective binary hash codes for each content item in the first batch, wherein content items included in a cluster are visually similar to one another. A next batch of content items to be clustered can be obtained. One or more respective binary hash codes for the content items in the next batch can be assigned to a cluster in the set of clusters.
-
公开(公告)号：US10692243B2
公开(公告)日：2020-06-23
申请号：US15971930
申请日：2018-05-04
申请人： Facebook, Inc.
发明人： Peter Vajda , Peizhao Zhang , Fei Yang , Yanghan Wang
IPC分类号： G06K9/00 , G06T7/73 , G06K9/46 , G06T7/11 , G06N3/04 , G06N3/08 , G06K9/62 , G06K9/32 , G06N5/02
摘要： In one embodiment, a system may access an image and generate a feature map for the image using a neural network. The system may identify regions of interest in the feature map. Regional feature maps may be generated for the regions of interest, respectively. Each of the regional feature maps has a first, a second, and a third dimension. The system may generate a first combined regional feature map by combining the regional feature maps. The combined regional feature map has a first, a second, and a third dimension. The system may generate a second combined regional feature map by processing the first combined regional feature map using one or more convolutional layers. The system may generate, for each of the regions of interest, information associated with an object instance based on a portion of the second combined regional feature map associated with that region of interest.
-
5.发明申请公开(公告)号：US20190172223A1
公开(公告)日：2019-06-06
申请号：US15972035
申请日：2018-05-04
申请人： Facebook, Inc.
发明人： Peter Vajda , Peizhao Zhang , Fei Yang , Yanghan Wang
摘要： In one embodiment, a system accesses pose probability models for predetermined parts of a body depicted in an image. Each of the pose probability models is configured for determining a probability of the associated predetermined body part being at a location in the image. The system determines a candidate pose that is defined by a set of coordinates representing candidate locations of the predetermined body parts. The system further determines a first probability score for the candidate pose based on the pose probability models and the set of coordinates of the candidate pose. A pose representation is generated for the candidate pose using a transformation model and the candidate pose. The system determines a second probability score for the pose representation based on a pose-representation probability model. The system selects the candidate pose to represent a pose of the body based on at least the first and second probability scores.
-
6.发明申请公开(公告)号：US20190171870A1
公开(公告)日：2019-06-06
申请号：US15971997
申请日：2018-05-04
申请人： Facebook, Inc.
发明人： Peter Vajda , Peizhao Zhang , Fei Yang , Yanghan Wang
摘要： In one embodiment, a method includes a system accessing an image and generating a feature map using a first neural network. The system identifies a plurality of regions of interest in the feature map. A plurality of regional feature maps may be generated for the plurality of regions of interest, respectively. Using a second neural network, the system may detect at least one regional feature map in the plurality of regional feature maps that corresponds to a person depicted in the image, and generate a target region definition associated with a location of the person using the regional feature map. Based on the target region definition associated with the location of the person, a target regional feature map may be generated by sampling the feature map for the image. The system may process the target regional feature map to generate a keypoint mask and an instance segmentation mask.
-
公开(公告)号：US10565729B2
公开(公告)日：2020-02-18
申请号：US15971997
申请日：2018-05-04
申请人： Facebook, Inc.
发明人： Peter Vajda , Peizhao Zhang , Fei Yang , Yanghan Wang
摘要： In one embodiment, a method includes a system accessing an image and generating a feature map using a first neural network. The system identifies a plurality of regions of interest in the feature map. A plurality of regional feature maps may be generated for the plurality of regions of interest, respectively. Using a second neural network, the system may detect at least one regional feature map in the plurality of regional feature maps that corresponds to a person depicted in the image, and generate a target region definition associated with a location of the person using the regional feature map. Based on the target region definition associated with the location of the person, a target regional feature map may be generated by sampling the feature map for the image. The system may process the target regional feature map to generate a keypoint mask and an instance segmentation mask.
-
公开(公告)号：US20180189281A1
公开(公告)日：2018-07-05
申请号：US15396303
申请日：2016-12-30
申请人： Facebook, Inc.
发明人： Kai Li , Fei Yang , Balamanohar Paluri
CPC分类号： G06N3/0454 , G06F16/783
摘要： Systems, methods, and non-transitory computer-readable media can receive a first content item having a set of frames. A binary hash code that represents the first content item is generated using at least an aggregation model and an iterative quantization hash model, the binary hash code being determined based at least in part on the set of frames of the first content item. The binary hash code is stored, wherein a similarity between the first content item and a second content item is capable of being measured based at least in part on a comparison of the binary hash code of the first content item and a binary hash code of the second content item.
-
公开(公告)号：US10817774B2
公开(公告)日：2020-10-27
申请号：US15396303
申请日：2016-12-30
申请人： Facebook, Inc.
发明人： Kai Li , Fei Yang , Balamanohar Paluri
IPC分类号： G06N3/04 , G06F16/783
摘要： Systems, methods, and non-transitory computer-readable media can receive a first content item having a set of frames. A binary hash code that represents the first content item is generated using at least an aggregation model and an iterative quantization hash model, the binary hash code being determined based at least in part on the set of frames of the first content item. The binary hash code is stored, wherein a similarity between the first content item and a second content item is capable of being measured based at least in part on a comparison of the binary hash code of the first content item and a binary hash code of the second content item.
-
10.发明授权公开(公告)号：US10586350B2
公开(公告)日：2020-03-10
申请号：US15972035
申请日：2018-05-04
申请人： Facebook, Inc.
发明人： Peter Vajda , Peizhao Zhang , Fei Yang , Yanghan Wang
摘要： In one embodiment, a system accesses pose probability models for predetermined parts of a body depicted in an image. Each of the pose probability models is configured for determining a probability of the associated predetermined body part being at a location in the image. The system determines a candidate pose that is defined by a set of coordinates representing candidate locations of the predetermined body parts. The system further determines a first probability score for the candidate pose based on the pose probability models and the set of coordinates of the candidate pose. A pose representation is generated for the candidate pose using a transformation model and the candidate pose. The system determines a second probability score for the pose representation based on a pose-representation probability model. The system selects the candidate pose to represent a pose of the body based on at least the first and second probability scores.
-
-
-
-
-
-
-
-
-
搜索结果
11 条记录 (耗时 0.024 秒)
