-
公开(公告)号：US20190138860A1
公开(公告)日：2019-05-09
申请号：US15807028
申请日：2017-11-08
Applicant: Adobe Inc.
Inventor： Yang Liu , Zhaowen Wang , Hailin Jin
CPC classification number: G06K9/6828 , G06K9/00422 , G06K9/6256 , G06K9/6273 , G06K9/6277 , G06K9/66 , G06K2209/011 , G06N3/0454 , G06N3/0472 , G06N3/084
Abstract: The present disclosure relates to a font recognition system that employs a multi-task learning framework and adversarial training to improve font classification and remove negative side effects caused by intra-class variances of glyph content. For example, in one or more embodiments, the font recognition system adversarial trains a font recognition neural network by minimizing font classification loss while at the same time maximizing glyph classification loss. By employing an adversarially trained font classification neural network, the font recognition system can improve overall font recognition by removing the negative side effects from diverse glyph content.
-
公开(公告)号：US20190108203A1
公开(公告)日：2019-04-11
申请号：US15729855
申请日：2017-10-11
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Hailin Jin , Aaron Phillip Hertzmann , Shuhui Jiang
Abstract: The present disclosure relates to an asymmetric font pairing system that efficiently pairs digital fonts. For example, in one or more embodiments, the asymmetric font pairing system automatically identifies and provides users with visually aesthetic font pairs for use in different sections of an electronic document. In particular, the asymmetric font pairing system learns visually aesthetic font pairs using joint symmetric and asymmetric compatibility metric learning. In addition, the asymmetric font pairing system provides compact compatibility spaces (e.g., a symmetric compatibility space and an asymmetric compatibility space) to computing devices (e.g., client devices and server devices), which enable the computing devices to quickly and efficiently provide font pairs to users.
-
公开(公告)号：US20240355119A1
公开(公告)日：2024-10-24
申请号：US18305587
申请日：2023-04-24
Applicant: ADOBE INC.
Inventor： Ioana Croitoru , Trung Huu Bui , Zhaowen Wang , Seunghyun Yoon , Franck Dernoncourt , Hailin Jin
CPC classification number: G06V20/41 , G06V10/774 , G06V20/49 , G06V20/70 , G10L15/04 , G10L15/1815 , G10L15/22 , G10L25/57 , G10L15/16
Abstract: One or more aspects of the method, apparatus, and non-transitory computer readable medium include receiving a query relating to a long video. One or more aspects of the method, apparatus, and non-transitory computer readable medium further include generating a segment of the long video corresponding to the query using a machine learning model trained to identify relevant segments from long videos. One or more aspects of the method, apparatus, and non-transitory computer readable medium further include responding to the query based on the generated segment.
-
公开(公告)号：US11966849B2
公开(公告)日：2024-04-23
申请号：US16796878
申请日：2020-02-20
Applicant: Adobe Inc.
Inventor： John Collomosse , Hailin Jin
Abstract: Techniques and systems are provided for configuring neural networks to perform certain image manipulation operations. For instance, in response to obtaining an image for manipulation, an image manipulation system determines the fitness scores for a set of neural networks resulting from the processing of a noise map. Based on these fitness scores, the image manipulation system selects a subset of the set of neural networks for cross-breeding into a new generation of neural networks. The image manipulation system evaluates the performance of this new generation of neural networks and continues cross-breeding this neural networks until a fitness threshold is satisfied. From the final generation of neural networks, the image manipulation system selects a neural network that provides a desired output and uses the neural network to generate the manipulated image.
-
公开(公告)号：US11875435B2
公开(公告)日：2024-01-16
申请号：US17499611
申请日：2021-10-12
Applicant: Adobe Inc.
Inventor： Chinthala Pradyumna Reddy , Zhifei Zhang , Matthew Fisher , Hailin Jin , Zhaowen Wang , Niloy J Mitra
CPC classification number: G06T11/203 , G06T3/40
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for accurately and flexibly generating scalable fonts utilizing multi-implicit neural font representations. For instance, the disclosed systems combine deep learning with differentiable rasterization to generate a multi-implicit neural font representation of a glyph. For example, the disclosed systems utilize an implicit differentiable font neural network to determine a font style code for an input glyph as well as distance values for locations of the glyph to be rendered based on a glyph label and the font style code. Further, the disclosed systems rasterize the distance values utilizing a differentiable rasterization model and combines the rasterized distance values to generate a permutation-invariant version of the glyph corresponding glyph set.
-
Patent Agency Ranking
76.发明申请公开(公告)号：US20220148325A1
公开(公告)日：2022-05-12
申请号：US17584962
申请日：2022-01-26
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Tianlang Chen , Ning Xu , Hailin Jin
IPC: G06V30/244 , G06K9/62 , G06F16/906 , G06N3/08 , G06F16/903 , G06F40/109 , G06V10/40
Abstract: The present disclosure relates to a tag-based font recognition system that utilizes a multi-learning framework to develop and improve tag-based font recognition using deep learning neural networks. In particular, the tag-based font recognition system jointly trains a font tag recognition neural network with an implicit font classification attention model to generate font tag probability vectors that are enhanced by implicit font classification information. Indeed, the font recognition system weights the hidden layers of the font tag recognition neural network with implicit font information to improve the accuracy and predictability of the font tag recognition neural network, which results in improved retrieval of fonts in response to a font tag query. Accordingly, using the enhanced tag probability vectors, the tag-based font recognition system can accurately identify and recommend one or more fonts in response to a font tag query.
-
公开(公告)号：US11238362B2
公开(公告)日：2022-02-01
申请号：US14996959
申请日：2016-01-15
Applicant: Adobe Inc.
Inventor： Hailin Jin , Zhou Ren , Zhe Lin , Chen Fang
Abstract: Modeling semantic concepts in an embedding space as distributions is described. In the embedding space, both images and text labels are represented. The text labels describe semantic concepts that are exhibited in image content. In the embedding space, the semantic concepts described by the text labels are modeled as distributions. By using distributions, each semantic concept is modeled as a continuous cluster which can overlap other clusters that model other semantic concepts. For example, a distribution for the semantic concept “apple” can overlap distributions for the semantic concepts “fruit” and “tree” since can refer to both a fruit and a tree. In contrast to using distributions, conventionally configured visual-semantic embedding spaces represent a semantic concept as a single point. Thus, unlike these conventionally configured embedding spaces, the embedding spaces described herein are generated to model semantic concepts as distributions, such as Gaussian distributions, Gaussian mixtures, and so on.
-
公开(公告)号：US11146862B2
公开(公告)日：2021-10-12
申请号：US16386031
申请日：2019-04-16
Applicant: Adobe Inc.
Inventor： Bryan Russell , Ruppesh Nalwaya , Markus Woodson , Joon-Young Lee , Hailin Jin
IPC: H04N21/81 , H04N21/845 , G06N3/08 , G06K9/00
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.
-
公开(公告)号：US20210312698A1
公开(公告)日：2021-10-07
申请号：US16838429
申请日：2020-04-02
Applicant: Adobe Inc.
Inventor： Tong He , John Collomosse , Hailin Jin
Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for utilizing an encoder-decoder architecture to learn a volumetric 3D representation of an object using digital images of the object from multiple viewpoints to render novel views of the object. For instance, the disclosed systems can utilize patch-based image feature extraction to extract lifted feature representations from images corresponding to different viewpoints of an object. Furthermore, the disclosed systems can model view-dependent transformed feature representations using learned transformation kernels. In addition, the disclosed systems can recurrently and concurrently aggregate the transformed feature representations to generate a 3D voxel representation of the object. Furthermore, the disclosed systems can sample frustum features using the 3D voxel representation and transformation kernels. Then, the disclosed systems can utilize a patch-based neural rendering approach to render images from frustum feature patches to display a view of the object from various viewpoints.
-
公开(公告)号：US20210241032A1
公开(公告)日：2021-08-05
申请号：US17240097
申请日：2021-04-26
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Hailin Jin , Yang Liu
Abstract: In implementations of recognizing text in images, text recognition systems are trained using noisy images that have nuisance factors applied, and corresponding clean images (e.g., without nuisance factors). Clean images serve as supervision at both feature and pixel levels, so that text recognition systems are trained to be feature invariant (e.g., by requiring features extracted from a noisy image to match features extracted from a clean image), and feature complete (e.g., by requiring that features extracted from a noisy image be sufficient to generate a clean image). Accordingly, text recognition systems generalize to text not included in training images, and are robust to nuisance factors. Furthermore, since clean images are provided as supervision at feature and pixel levels, training requires fewer training images than text recognition systems that are not trained with a supervisory clean image, thus saving time and resources.
-
-
-
-
-
-
-
-
-
Search Results
91
records
(took 0.036 seconds)
