-
公开(公告)号：US20230316536A1
公开(公告)日：2023-10-05
申请号：US17657430
申请日：2022-03-31
Applicant: ADOBE INC.
Inventor： Joon-Young Lee , Seoungwug Oh , Sanghyun Woo , Kwanyong Park
IPC: G06T7/20 , G06T3/40 , G06T3/00 , G06V10/764 , G06V10/774 , G06V10/82 , G06V10/776 , G06N3/04
CPC classification number: G06T7/20 , G06T3/40 , G06T3/0006 , G06V10/764 , G06V10/774 , G06V10/82 , G06T2207/10016 , G06N3/0454 , G06T2207/20081 , G06T2207/20084 , G06T2207/20212 , G06T2207/20132 , G06V2201/07 , G06V10/776
Abstract: Systems and methods for object tracking are described. One or more aspects of the systems and methods include receiving a video depicting an object; generating object tracking information for the object using a student network, wherein the student network is trained in a second training phase based on a teacher network using an object tracking training set and a knowledge distillation loss that is based on an output of the student network and the teacher network, and wherein the teacher network is trained in a first training phase using an object detection training set that is augmented with object tracking supervision data; and transmitting the object tracking information in response to receiving the video.
-
公开(公告)号：US11657230B2
公开(公告)日：2023-05-23
申请号：US16899994
申请日：2020-06-12
Applicant: ADOBE INC.
Inventor： Joon-Young Lee , Seonguk Seo
CPC classification number: G06F40/30 , G06F16/90332 , G06F17/16 , G06F18/25 , G06F40/20 , G06T7/10 , G06V20/70 , G06T2207/20081 , G06T2207/20084
Abstract: A method, apparatus, and non-transitory computer readable medium for referring image segmentation are described. Embodiments of the method, apparatus, and non-transitory computer readable medium may extract an image feature vector from an input image, extract a plurality of language feature vectors for a referral expression, wherein each of the plurality of language feature vectors comprises a different number of dimensions, combine each of the language feature vectors with the image feature vector using a fusion module to produce a plurality of self-attention vectors, combine the plurality of self-attention vectors to produce a multi-modal feature vector, and decode the multi-modal feature vector to produce an image mask indicating a portion of the input image corresponding to the referral expression.
-
公开(公告)号：US11526698B2
公开(公告)日：2022-12-13
申请号：US16893803
申请日：2020-06-05
Applicant: ADOBE INC.
Inventor： Joon-Young Lee , Seonguk Seo
Abstract: Systems and methods for video object segmentation are described. Embodiments of systems and methods may receive a referral expression and a video comprising a plurality of image frames, generate a first image mask based on the referral expression and a first image frame of the plurality of image frames, generate a second image mask based on the referral expression, the first image frame, the first image mask, and a second image frame of the plurality of image frames, and generate annotation information for the video including the first image mask overlaid on the first image frame and the second image mask overlaid on the second image frame.
-
公开(公告)号：US20200143171A1
公开(公告)日：2020-05-07
申请号：US16183560
申请日：2018-11-07
Applicant: Adobe Inc.
Inventor： Joon-Young Lee , Seoungwug Oh , Ning Xu
Abstract: In implementations of segmenting objects in video sequences, user annotations designate an object in any image frame of a video sequence, without requiring user annotations for all image frames. An interaction network generates a mask for an object in an image frame annotated by a user, and is coupled both internally and externally to a propagation network that propagates the mask to other image frames of the video sequence. Feature maps are aggregated for each round of user annotations and couple the interaction network and the propagation network internally. The interaction network and the propagation network are trained jointly using synthetic annotations in a multi-round training scenario, in which weights of the interaction network and the propagation network are adjusted after multiple synthetic annotations are processed, resulting in a trained object segmentation system that can reliably generate realistic object masks.
-
公开(公告)号：US11949964B2
公开(公告)日：2024-04-02
申请号：US17470441
申请日：2021-09-09
Applicant: Adobe Inc.
Inventor： Bryan Russell , Ruppesh Nalwaya , Markus Woodson , Joon-Young Lee , Hailin Jin
IPC: H04N21/81 , G06N3/08 , G06V20/40 , H04N21/845
CPC classification number: H04N21/8133 , G06N3/08 , G06V20/46 , H04N21/8456
Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for automatic tagging of videos. In particular, in one or more embodiments, the disclosed systems generate a set of tagged feature vectors (e.g., tagged feature vectors based on action-rich digital videos) to utilize to generate tags for an input digital video. For instance, the disclosed systems can extract a set of frames for the input digital video and generate feature vectors from the set of frames. In some embodiments, the disclosed systems generate aggregated feature vectors from the feature vectors. Furthermore, the disclosed systems can utilize the feature vectors (or aggregated feature vectors) to identify similar tagged feature vectors from the set of tagged feature vectors. Additionally, the disclosed systems can generate a set of tags for the input digital videos by aggregating one or more tags corresponding to identified similar tagged feature vectors.
-
Patent Agency Ranking
公开(公告)号：US20240037750A1
公开(公告)日：2024-02-01
申请号：US18487453
申请日：2023-10-16
Applicant: Adobe Inc.
Inventor： Jaedong Hwang , Seoung Wug Oh , Joon-Young Lee
IPC: G06T7/11 , G06V10/40 , G06F18/2413
CPC classification number: G06T7/11 , G06V10/40 , G06F18/24137 , G06T2207/20084
Abstract: This disclosure describes one or more implementations of a panoptic segmentation system that generates panoptic segmented digital images that classify both known and unknown instances of digital images. For example, the panoptic segmentation system builds and utilizes a panoptic segmentation neural network to discover, cluster, and segment new unknown object subclasses for previously unknown object instances. In addition, the panoptic segmentation system can determine additional unknown object instances from additional digital images. Moreover, in some implementations, the panoptic segmentation system utilizes the newly generated unknown object subclasses to refine and tune the panoptic segmentation neural network to improve the detection of unknown object instances in input digital images.
-
公开(公告)号：US11200424B2
公开(公告)日：2021-12-14
申请号：US16293126
申请日：2019-03-05
Applicant: Adobe Inc.
Inventor： Joon-Young Lee , Ning Xu , Seoungwug Oh
IPC: G06K9/00
Abstract: Certain aspects involve using a space-time memory network to locate one or more target objects in video content for segmentation or other object classification. In one example, a video editor generates a query key map and a query value map by applying a space-time memory network to features of a query frame from video content. The video editor retrieves a memory key map and a memory value map that are computed, with the space-time memory network, from a set of memory frames from the video content. The video editor computes memory weights by applying a similarity function to the memory key map and the query key map. The video editor classifies content in the query frame as depicting the target feature using a weighted summation that includes the memory weights applied to memory locations in the memory value map.
-
公开(公告)号：US11176381B2
公开(公告)日：2021-11-16
申请号：US16856292
申请日：2020-04-23
Applicant: Adobe Inc.
Inventor： Joon-Young Lee , Seoungwug Oh , Kalyan Krishna Sunkavalli
Abstract: Various embodiments describe video object segmentation using a neural network and the training of the neural network. The neural network both detects a target object in the current frame based on a reference frame and a reference mask that define the target object and propagates the segmentation mask of the target object for a previous frame to the current frame to generate a segmentation mask for the current frame. In some embodiments, the neural network is pre-trained using synthetically generated static training images and is then fine-tuned using training videos.
-
公开(公告)号：US20210326638A1
公开(公告)日：2021-10-21
申请号：US16852647
申请日：2020-04-20
Applicant: ADOBE INC.
Inventor： Joon-Young Lee , Sanghyun Woo , Dahun Kim
Abstract: Systems and methods for panoptic video segmentation are described. A method may include identifying a target frame and a reference frame from a video, generating target features for the target frame and reference features for the reference frame, combining the target features and the reference features to produce fused features for the target frame, generating a feature matrix comprising a correspondence between objects from the reference features and objects from the fused features; and generating panoptic segmentation information for the target frame based on the feature matrix.
-
10.发明授权公开(公告)号：US10915798B1
公开(公告)日：2021-02-09
申请号：US15980636
申请日：2018-05-15
Applicant: ADOBE INC.
Inventor： Jianming Zhang , Rameswar Panda , Haoxiang Li , Joon-Young Lee , Xin Lu
Abstract: Disclosed herein are embodiments of systems, methods, and products for a webly supervised training of a convolutional neural network (CNN) to predict emotion in images. A computer may query one or more image repositories using search keywords generated based on the tertiary emotion classes of Parrott's emotion wheel. The computer may filter images received in response to the query to generate a weakly labeled training dataset labels associated with the images that are noisy or wrong may be cleaned prior to training of the CNN. The computer may iteratively train the CNN leveraging the hierarchy of emotion classes by increasing the complexity of the labels (tags) for each iteration. Such curriculum guided training may generate a trained CNN that is more accurate than the conventionally trained neural networks.
-
-
-
-
-
-
-
-
-
Search Results
39
records
(took 0.016 seconds)
