-
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.
-
公开(公告)号：US11036915B2
公开(公告)日：2021-06-15
申请号：US15067108
申请日：2016-03-10
Applicant: ADOBE INC.
Inventor： I-Ming Pao , Zhaowen Wang , Hailin Jin , Alan Lee Erickson
IPC: G06F40/109 , G06N3/04
Abstract: Embodiments of the present invention are directed at providing a font similarity system. In one embodiment, a new font is detected on a computing device. In response to the detection of the new font, a pre-computed font list is checked to determine whether the new font is included therein. The pre-computed font list including feature representations, generated independently of the computing device, for corresponding fonts. In response to a determination that the new font is absent from the pre-computed font list, a feature representation for the new font is generated. The generated feature representation capable of being utilized for a similarity analysis of the new font. The feature representation is then stored in a supplemental font list to enable identification of one or more fonts installed on the computing device that are similar to the new font. Other embodiments may be described and/or claimed.
-
公开(公告)号：US10997463B2
公开(公告)日：2021-05-04
申请号：US16184779
申请日：2018-11-08
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.
-
公开(公告)号：US10803377B2
公开(公告)日：2020-10-13
申请号：US15053448
申请日：2016-02-25
Applicant: Adobe Inc.
Inventor： Anirban Roychowdhury , Trung Bui , John Kucera , Hung Bui , Hailin Jin
Abstract: Techniques for predictively selecting a content presentation in a client-server computing environment are described. In an example, a content management system detects an interaction of a client with a server and accesses client features. Responses of the client to potential content presentations are predicted based on a multi-task neural network. The client features are mapped to input nodes and the potential content presentations are associated with tasks mapped to output nodes of the multi-task neural network. The tasks specify usages of the potential content presentations in response to the interaction with the server. In an example, the content management system selects the content presentation from the potential content presentations based on the predicted responses. For instance, the content presentation is selected based on having the highest likelihood. The content management system provides the content presentation to the client based on the task corresponding to the content presentation.
-
公开(公告)号：US10778949B2
公开(公告)日：2020-09-15
申请号：US13725041
申请日：2012-12-21
Applicant: Adobe Inc.
Inventor： Hailin Jin
IPC: H04N13/10 , H04N13/00 , G06T7/70 , G06T7/246 , G06T7/579 , H04N5/232 , H04N17/00 , G06K9/32 , G06K9/46 , G06T5/00
Abstract: A robust system and method for estimating camera rotation in image sequences. A rotation-based reconstruction technique is described that is directed to performing reconstruction for image sequences with a zero or near-zero translation component. The technique may estimate only the rotation component of the camera motion in an image sequence, and may also estimate the camera intrinsic parameters if not known. Input to the technique may include an image sequence, and output may include the camera intrinsic parameters and the rotation parameters for all the images in the sequence. By only estimating a rotation component of camera motion, the assumption is made that the camera is not moving throughout the entire sequence. However, the camera is allowed to rotate and zoom arbitrarily. The technique may support both the case where the camera intrinsic parameters are known and the case where the camera intrinsic parameters are not known.
-
Patent Agency Ranking
公开(公告)号：US10762135B2
公开(公告)日：2020-09-01
申请号：US15357864
申请日：2016-11-21
Applicant: Adobe Inc.
Inventor： Matthew Douglas Hoffman , Longqi Yang , Hailin Jin , Chen Fang
IPC: G06F16/9032 , G06F16/2457 , G06F40/166
Abstract: A digital medium environment includes an asset processing application that performs editing of assets. A projection function is trained using pairs of actions pertaining to software edits, and assets resulting from the actions to learn a joint embedding between the actions and the assets. The projection function is used in the asset processing application to recommend software actions to create an asset, and also to recommend assets to demonstrate the effects of software actions. Recommendations are based on ranking distance measures that measure distances between actions representations and asset representations in a vector space.
-
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
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：US10733228B2
公开(公告)日：2020-08-04
申请号：US16432834
申请日：2019-06-05
Applicant: Adobe Inc.
Inventor： Hailin Jin , John Philip Collomosse
Abstract: Sketch and style based image retrieval in a digital medium environment is described. Initially, a user sketches an object to be searched in connection with an image search. Styled images are selected to indicate a desired style of images to be returned by the search. A search request is generated based on the sketch and selected images. Responsive to the request, an image repository is searched to identify images having the desired object and styling. To search the image repository, a neural network is utilized that is capable of recognizing the desired object in images based on visual characteristics of the sketch and independently recognizing the desired styling in images based on visual characteristics of the selected images. This independent recognition allows desired styling to be specified by selecting images having the style but not the desired object. Images having the desired object and styling are returned.
-
公开(公告)号：US20200242822A1
公开(公告)日：2020-07-30
申请号：US16841246
申请日：2020-04-06
Applicant: Adobe Inc.
Inventor： Hailin Jin , John Philip Collomosse , Brian Lynn Price
Abstract: Techniques and systems are described for style-aware patching of a digital image in a digital medium environment. For example, a digital image creation system generates style data for a portion to be filled of a digital image, indicating a style of an area surrounding the portion. The digital image creation system also generates content data for the portion indicating content of the digital image of the area surrounding the portion. The digital image creation system selects a source digital image based on similarity of both style and content of the source digital image at a location of the patch to the style data and content data. The digital image creation system transforms the style of the source digital image based on the style data and generates the patch from the source digital image in the transformed style for incorporation into the portion to be filled of the digital image.
-
公开(公告)号：US10699166B2
公开(公告)日：2020-06-30
申请号：US15853120
申请日：2017-12-22
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Luoqi Liu , Hailin Jin
Abstract: Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.
-
-
-
-
-
-
-
-
-
Search Results
92
records
(took 0.016 seconds)
