-
公开(公告)号：US10726306B1
公开(公告)日：2020-07-28
申请号：US16226035
申请日：2018-12-19
Applicant: Snap Inc.
Inventor： Linjie Yang , Kevin Dechau Tang , Jianchao Yang , Jia Li
Abstract: A dense captioning system and method is provided for analyzing an image to generate proposed bounding regions for a plurality of visual concepts within the image, generating a region feature for each proposed bounding region to generate a plurality of region features of the image, and determining a context feature for the image using a proposed bounding region that is a largest in size of the proposed bounding regions. For each region feature of the plurality of region features of the image, the dense captioning system and method further provides for analyzing the region feature to determine for the region feature a detection score that indicates a likelihood that the region feature comprises an actual object, and generating a caption for a visual concept in the image using the region feature and the context feature when a detection score is above a specified threshold value.
-
公开(公告)号：US20200050866A1
公开(公告)日：2020-02-13
申请号：US16654898
申请日：2019-10-16
Applicant: Snap Inc.
Inventor： Samuel Edward Hare , Fedir Poliakov , Guohui Wang , Xuehan Xiong , Jianchao Yang , Linjie Yang , Shah Tanmay Anilkumar
Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.
-
公开(公告)号：US10395100B1
公开(公告)日：2019-08-27
申请号：US16226084
申请日：2018-12-19
Applicant: Snap Inc.
Inventor： Jia Li , Xutao Lv , Xiaoyu Wang , Xuehan Xiong , Jianchao Yang
Abstract: Systems, devices, media, and methods are presented for modeling facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial features within the portion of the face. The systems and methods generate a descriptor function representing the set of facial features, fit object functions of the descriptor function, identify an identification probability for each facial feature, and assign an identification to each facial feature.
-
公开(公告)号：US20190087660A1
公开(公告)日：2019-03-21
申请号：US15706096
申请日：2017-09-15
Applicant: Snap Inc.
Inventor： Samuel Edward Hare , Fedir Poliakov , Guohui Wang , Xuehan Xiong , Jianchao Yang , Linjie Yang , Shah Tanmay Anilkumar
Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.
-
公开(公告)号：US10198626B2
公开(公告)日：2019-02-05
申请号：US15297789
申请日：2016-10-19
Applicant: Snap Inc.
Inventor： Jia Li , Xutao Lv , Xiaoyu Wang , Xuehan Xiong , Jianchao Yang
Abstract: Systems, devices, media, and methods are presented for modeling facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial features within the portion of the face. The systems and methods generate a descriptor function representing the set of facial features, fit object functions of the descriptor function, identify an identification probability for each facial feature, and assign an identification to each facial feature.
-
Patent Agency Ranking
公开(公告)号：US20240249522A1
公开(公告)日：2024-07-25
申请号：US18624757
申请日：2024-04-02
Applicant: Snap Inc.
Inventor： Samuel Edward Hare , Fedir Poliakov , Guohui Wang , Xuehan Xiong , Jianchao Yang , Linjie Yang , Shah Tanmay Anilkumar
CPC classification number: G06V20/40 , G06T1/20 , G06T7/248 , G06V20/46 , G06T2200/28 , G06T2207/10016 , G06T2207/20081
Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.
-
公开(公告)号：US11889381B2
公开(公告)日：2024-01-30
申请号：US18090654
申请日：2022-12-29
Applicant: Snap Inc.
Inventor： Nicholas Richard Allen , Sheldon Chang , Maria Pavlovskaia , Amer Shahnawaz , Jianchao Yang
CPC classification number: H04W4/021 , H04L12/1859 , H04L51/52 , H04L67/52
Abstract: Systems and methods are provided for receiving input increasing a default predetermined window of time that the new media collection is accessible and activating the new media collection for the increased predetermined window of time and a geographic boundary size for where media content originates. The systems and methods further cause a plurality of content messages comprising media content originating in the geographical boundary size to be included in the new media collection and displayed in response to a request from a computing device to view the new media collection based on determining the request occurs within the increased predetermined window of time that the new media collection is accessible.
-
公开(公告)号：US11727660B2
公开(公告)日：2023-08-15
申请号：US17722955
申请日：2022-04-18
Applicant: Snap Inc.
Inventor： Jia Li , Linjie Luo , Rahul Bhupendra Sheth , Ning Xu , Jianchao Yang
CPC classification number: G06T19/20 , G06T7/248 , G06T19/006 , H04L51/52 , G06T2207/20104
Abstract: Systems and methods for local augmented reality (AR) tracking of an AR object are disclosed. In one example embodiment a device captures a series of video image frames. A user input is received at the device associating a first portion of a first image of the video image frames with an AR sticker object and a target. A first target template is generated to track the target across frames of the video image frames. In some embodiments, global tracking based on a determination that the target is outside a boundary area is used. The global tracking comprises using a global tracking template for tracking movement in the video image frames captured following the determination that the target is outside the boundary area. When the global tracking determines that the target is within the boundary area, local tracking is resumed along with presentation of the AR sticker object on an output display of the device.
-
公开(公告)号：US11645843B2
公开(公告)日：2023-05-09
申请号：US17248393
申请日：2021-01-22
Applicant: Snap Inc.
Inventor： Samuel Edward Hare , Fedir Poliakov , Guohui Wang , Xuehan Xiong , Jianchao Yang , Linjie Yang , Shah Tanmay Anilkumar
CPC classification number: G06V20/40 , G06T1/20 , G06T7/248 , G06V20/46 , G06T2200/28 , G06T2207/10016 , G06T2207/20081
Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.
-
公开(公告)号：US20230135137A1
公开(公告)日：2023-05-04
申请号：US18090577
申请日：2022-12-29
Applicant: Snap Inc.
Inventor： Linjie Yang , Jianchao Yang , Xuehan Xiong , Yanran Wang
Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.
-
-
-
-
-
-
-
-
-
Search Results
84
records
(took 0.021 seconds)
