公开(公告)号：US11256960B2

公开(公告)日：2022-02-22

申请号：US16849716

申请日：2020-04-15

Applicant: ADOBE INC.

Inventor： Joonyoung Lee ,  Sanghyun Woo ,  Dahun Kim

IPC: G06K9/62 ,  G06N3/08 ,  G06K9/68

Abstract: A method, apparatus, non-transitory computer readable medium, and system for panoptic segmentation are described. Embodiments may generate a feature pyramid for an input image, wherein the feature pyramid comprises a plurality of feature maps at different resolution levels, apply an attention module to the feature pyramid to produce an enhanced feature map, combine the enhanced feature map with each of the plurality of feature maps to produce an enhanced feature pyramid, generate semantic information for the input image based on the enhanced feature pyramid, generate a plurality of object regions based on the enhanced feature pyramid, generate instance information for each of the plurality of object regions, and generate panoptic segmentation information for the input image based on the semantic information and the instance information for each of the plurality of object regions.

公开(公告)号：US20210319566A1

公开(公告)日：2021-10-14

申请号：US17350129

申请日：2021-06-17

Applicant: Adobe Inc.

Inventor： Xingyu Liu ,  Hailin Jin ,  Joonyoung Lee

IPC: G06T7/246 ,  G06K9/00 ,  G06K9/62

Abstract: Technology is disclosed herein for learning motion in video. In an implementation, an artificial neural network extracts features from a video. A correspondence proposal (CP) module performs, for at least some of the features, a search for corresponding features in the video based on a semantic similarity of a given feature to others of the features. The CP module then generates a joint semantic vector for each of the features based at least on the semantic similarity of the given feature to one or more of the corresponding features and a spatiotemporal distance of the given feature to the one or more of the corresponding features. The artificial neural network is able to identify motion in the video using the joint semantic vectors generated for the features extracted from the video.

公开(公告)号：US11062460B2

公开(公告)日：2021-07-13

申请号：US16274481

申请日：2019-02-13

Applicant: Adobe Inc.

Inventor： Xingyu Liu ,  Hailin Jin ,  Joonyoung Lee

IPC: G06T7/246 ,  G06K9/62 ,  G06K9/00

Abstract: Technology is disclosed herein for learning motion in video. In an implementation, an artificial neural network extracts features from a video. A correspondence proposal (CP) module performs, for at least some of the features, a search for corresponding features in the video based on a semantic similarity of a given feature to others of the features. The CP module then generates a joint semantic vector for each of the features based at least on the semantic similarity of the given feature to one or more of the corresponding features and a spatiotemporal distance of the given feature to the one or more of the corresponding features. The artificial neural network is able to identify motion in the video using the joint semantic vectors generated for the features extracted from the video.

公开(公告)号：US20200258241A1

公开(公告)日：2020-08-13

申请号：US16274481

申请日：2019-02-13

Applicant: Adobe Inc.

Inventor： Xingyu Liu ,  Hailin Jin ,  Joonyoung Lee

IPC: G06T7/246 ,  G06K9/00 ,  G06K9/62

Abstract: Technology is disclosed herein for learning motion in video. In an implementation, an artificial neural network extracts features from a video. A correspondence proposal (CP) module performs, for at least some of the features, a search for corresponding features in the video based on a semantic similarity of a given feature to others of the features. The CP module then generates a joint semantic vector for each of the features based at least on the semantic similarity of the given feature to one or more of the corresponding features and a spatiotemporal distance of the given feature to the one or more of the corresponding features. The artificial neural network is able to identify motion in the video using the joint semantic vectors generated for the features extracted from the video.

公开(公告)号：US11836932B2

公开(公告)日：2023-12-05

申请号：US17350129

申请日：2021-06-17

Applicant: Adobe Inc.

Inventor： Xingyu Liu ,  Hailin Jin ,  Joonyoung Lee

IPC: G06T7/246 ,  G06V20/40 ,  G06V30/19 ,  G06V10/82 ,  G06V10/44 ,  G06F18/2413

CPC classification number: G06T7/246 ,  G06F18/24147 ,  G06V10/454 ,  G06V10/82 ,  G06V20/41 ,  G06V20/46 ,  G06V30/19173 ,  G06T2207/20084

Abstract: Technology is disclosed herein for learning motion in video. In an implementation, an artificial neural network extracts features from a video. A correspondence proposal (CP) module performs, for at least some of the features, a search for corresponding features in the video based on a semantic similarity of a given feature to others of the features. The CP module then generates a joint semantic vector for each of the features based at least on the semantic similarity of the given feature to one or more of the corresponding features and a spatiotemporal distance of the given feature to the one or more of the corresponding features. The artificial neural network is able to identify motion in the video using the joint semantic vectors generated for the features extracted from the video.