-
1.发明申请公开(公告)号：US20160364633A1
公开(公告)日：2016-12-15
申请号：US14734466
申请日：2015-06-09
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： JIANCHAO YANG , ZHANGYANG WANG , JONATHAN BRANDT , HAILIN JIN , ELYA SHECHTMAN , ASEEM OMPRAKASH AGARWALA
CPC classification number: G06T3/40 , G06K9/6255 , G06K9/6828
Abstract: A convolutional neural network (CNN) is trained for font recognition and font similarity learning. In a training phase, text images with font labels are synthesized by introducing variances to minimize the gap between the training images and real-world text images. Training images are generated and input into the CNN. The output is fed into an N-way softmax function dependent on the number of fonts the CNN is being trained on, producing a distribution of classified text images over N class labels. In a testing phase, each test image is normalized in height and squeezed in aspect ratio resulting in a plurality of test patches. The CNN averages the probabilities of each test patch belonging to a set of fonts to obtain a classification. Feature representations may be extracted and utilized to define font similarity between fonts, which may be utilized in font suggestion, font browsing, or font recognition applications.
Abstract translation: 对卷积神经网络（CNN）进行字体识别和字体相似学习。 在训练阶段，通过引入差异来合成具有字体标签的文本图像，以最小化训练图像与真实世界文本图像之间的差距。 生成训练图像并将其输入到CNN中。 根据CNN正在训练的字体数量，输出被输入到N-way softmax函数中，产生N类标签上分类文本图像的分布。 在测试阶段，每个测试图像的高度被标准化，并以纵横比挤压，从而产生多个测试贴片。 CNN对属于一组字体的每个测试补丁的概率进行平均，以获得分类。 可以提取和利用特征表示来定义可以在字体建议，字体浏览或字体识别应用中使用的字体之间的字体相似性。
-
公开(公告)号：US20180234669A1
公开(公告)日：2018-08-16
申请号：US15433333
申请日：2017-02-15
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： ZHILI CHEN , DUYGU CEYLAN AKSIT , JINGWEI HUANG , HAILIN JIN
CPC classification number: H04N13/117 , G06F3/012 , G06T15/20 , H04N5/23238 , H04N13/144 , H04N13/207 , H04N13/221 , H04N13/344 , H04N13/366 , H04N13/373 , H04N13/376 , H04N13/378 , H04N13/38
Abstract: Systems and methods provide for providing a stereoscopic six-degree of freedom viewing experience with a monoscopic 360-degree video are provided. A monoscopic 360-degree video of a subject scene can be preprocessed by analyzing each frame to recover a three-dimensional geometric representation of the subject scene, and further recover a camera motion path that includes various parameters associated with the camera, such as orientation, translational movement, and the like, as evidenced by the recording. Utilizing the recovered three-dimensional geometric representation of the subject scene and recovered camera motion path, a dense three-dimensional geometric representation of the subject scene is generated utilizing random assignment and propagation operations. Once preprocessing is complete, the processed video can be provided for stereoscopic display via a device, such as a head-mounted display. As user motion data is detected and received, novel viewpoints can be stereoscopically synthesized for presentation to the user in real time, so as to provide an immersive virtual reality experience to the user based on the original monoscopic 360-degree video and the user's detected movement(s).
-
公开(公告)号：US20170061257A1
公开(公告)日：2017-03-02
申请号：US15349876
申请日：2016-11-11
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： JIANCHAO YANG , GUANG CHEN , HAILIN JIN , JONATHAN BRANDT , ELYA SHECHTMAN , ASEEM OMPRAKASH AGARWALA
CPC classification number: G06K9/6282 , G06K9/6219 , G06K9/6267 , G06K9/6807
Abstract: Example systems and methods for classifying visual patterns into a plurality of classes are presented. Using reference visual patterns of known classification, at least one image or visual pattern classifier is generated, which is then employed to classify a plurality of candidate visual patterns of unknown classification. The classification scheme employed may be hierarchical or nonhierarchical. The types of visual patterns may be fonts, human faces, or any other type of visual patterns or images subject to classification.
Abstract translation: 提出了将视觉模式分类为多个类的示例系统和方法。 使用已知分类的参考视觉图案，生成至少一个图像或视觉模式分类器，然后将其用于对未知分类的多个候选视觉图案进行分类。 所使用的分类方案可以是分层的或非分层的。 视觉图案的类型可以是字体，人脸或任何其他类型的可分类的视觉图案或图像。
-
公开(公告)号：US20180267997A1
公开(公告)日：2018-09-20
申请号：US15463769
申请日：2017-03-20
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： ZHE LIN , XIAOHUI SHEN , JIANMING ZHANG , HAILIN JIN , YINGWEI LI
CPC classification number: G06F17/30268 , G06F17/30277 , G06F17/30864 , G06K9/00684 , G06K9/66 , G06N3/04 , G06N3/08 , G06T7/33 , G06T11/60 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084
Abstract: A framework is provided for associating images with topics utilizing embedding learning. The framework is trained utilizing images, each having multiple visual characteristics and multiple keyword tags associated therewith. Visual features are computed from the visual characteristics utilizing a convolutional neural network and an image feature vector is generated therefrom. The keyword tags are utilized to generate a weighted word vector (or “soft topic feature vector”) for each image by calculating a weighted average of word vector representations that represent the keyword tags associated with the image. The image feature vector and the soft topic feature vector are aligned in a common embedding space and a relevancy score is computed for each of the keyword tags. Once trained, the framework can automatically tag images and a text-based search engine can rank image relevance with respect to queried keywords based upon predicted relevancy scores.
-
公开(公告)号：US20170140248A1
公开(公告)日：2017-05-18
申请号：US14940916
申请日：2015-11-13
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： ZHAOWEN WANG , XIANMING LIU , HAILIN JIN , CHEN FANG
CPC classification number: G06N3/0454 , G06K9/4628 , G06K9/6257 , G06K9/627 , G06K9/628 , G06K9/6284 , G06K9/629 , G06N3/04 , G06N3/08 , G06Q50/01
Abstract: Embodiments of the present invention relate to learning image representation by distilling from multi-task networks. In implementation, more than one single-task network is trained with heterogeneous labels. In some embodiments, each of the single-task networks is transformed into a Siamese structure with three branches of sub-networks so that a common triplet ranking loss can be applied to each branch. A distilling network is trained that approximates the single-task networks on a common ranking task. In some embodiments, the distilling network is a Siamese network whose ranking function is optimized to approximate an ensemble ranking of each of the single-task networks. The distilling network can be utilized to predict tags to associate with a test image or identify similar images to the test image.
-
Patent Agency Ranking
公开(公告)号：US20160034788A1
公开(公告)日：2016-02-04
申请号：US14447296
申请日：2014-07-30
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： ZHE LIN , HAILIN JIN , JIANCHAO YANG
CPC classification number: G06T7/33 , G06K9/627 , G06N3/0454
Abstract: A first set of attributes (e.g., style) is generated through pre-trained single column neural networks and leveraged to regularize the training process of a regularized double-column convolutional neural network (RDCNN). Parameters of the first column (e.g., style) of the RDCNN are fixed during RDCNN training Parameters of the second column (e.g., aesthetics) are fine-tuned while training the RDCNN and the learning process is supervised by the label identified by the second column (e.g., aesthetics). Thus, features of the images may be leveraged to boost classification accuracy of other features by learning a RDCNN.
Abstract translation: 通过预训练的单列神经网络产生第一组属性（例如，样式），并且利用正则化的双列卷积神经网络（RDCNN）的训练过程。 在RDCNN训练期间RDCNN的第一列（例如，样式）的参数是固定的在第二列的参数（例如，美学）中进行微调，同时训练RDCNN，学习过程由第二列标识的标签 （如美学）。 因此，可以利用图像的特征来通过学习RDCNN来提高其他特征的分类精度。
-
公开(公告)号：US20180267996A1
公开(公告)日：2018-09-20
申请号：US15463757
申请日：2017-03-20
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： ZHE LIN , XIAOHUI SHEN , JIANMING ZHANG , HAILIN JIN , YINGWEI LI
CPC classification number: G06F16/5866 , G06F16/532 , G06F16/951 , G06K9/00684 , G06K9/4628 , G06K9/4676 , G06K9/6248 , G06K9/6273 , G06K9/66 , G06N3/04 , G06N3/0454 , G06N3/08 , G06T7/33 , G06T11/60 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084
Abstract: A framework is provided for associating dense images with topics. The framework is trained utilizing images, each having multiple regions, multiple visual characteristics and multiple keyword tags associated therewith. For each region of each image, visual features are computed from the visual characteristics utilizing a convolutional neural network, and an image feature vector is generated from the visual features. The keyword tags are utilized to generate a weighted word vector for each image by calculating a weighted average of word vector representations representing keyword tags associated with the image. The image feature vector and the weighted word vector are aligned in a common embedding space and a heat map is computed for the image. Once trained, the framework can be utilized to automatically tag images and rank the relevance of images with respect to queried keywords based upon associated heat maps.
-
8.发明申请公开(公告)号：US20180174070A1
公开(公告)日：2018-06-21
申请号：US15381637
申请日：2016-12-16
Applicant: Adobe Systems Incorporated
Inventor： MATTHEW HOFFMAN , LONGQI YANG , HAILIN JIN , CHEN FANG
CPC classification number: G06N20/00 , G06N7/005 , G06Q30/0255 , G06Q30/0277 , G06T11/00 , H04L67/22 , H04W12/06
Abstract: This disclosure involves personalizing user experiences with electronic content based on application usage data. For example, a user representation model that facilitates content recommendations is iteratively trained with action histories from a content manipulation application. Each iteration involves selecting, from an action history for a particular user, an action sequence including a target action. An initial output is computed in each iteration by applying a probability function to the selected action sequence and a user representation vector for the particular user. The user representation vector is adjusted to maximize an output that is generated by applying the probability function to the action sequence and the user representation vector. This iterative training process generates a user representation model, which includes a set of adjusted user representation vectors, that facilitates content recommendations corresponding to users' usage pattern in the content manipulation application.
-
公开(公告)号：US20170011291A1
公开(公告)日：2017-01-12
申请号：US14793157
申请日：2015-07-07
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： HAILIN JIN , JONATHAN KRAUSE , JIANCHAO YANG
CPC classification number: G06N3/088 , G06F17/30247 , G06K9/00362 , G06K9/4628 , G06K9/6218 , G06K9/627 , G06N99/005
Abstract: Embodiments of the present invention relate to finding semantic parts in images. In implementation, a convolutional neural network (CNN) is applied to a set of images to extract features for each image. Each feature is defined by a feature vector that enables a subset of the set of images to be clustered in accordance with a similarity between feature vectors. Normalized cuts may be utilized to help preserve pose within each cluster. The images in the cluster are aligned and part proposals are generated by sampling various regions in various sizes across the aligned images. To determine which part proposal corresponds to a semantic part, a classifier is trained for each part proposal and semantic part to determine which part proposal best fits the correlation pattern given by the true semantic part. In this way, semantic parts in images can be identified without any previous part annotations.
Abstract translation: 本发明的实施例涉及在图像中发现语义部分。 在实现中，将卷积神经网络（CNN）应用于一组图像以提取每个图像的特征。 每个特征由特征向量定义，其使得能够根据特征向量之间的相似性来聚集图像集合的子集。 可以利用归一化切割来帮助保持每个群集内的姿态。 集群中的图像对齐，并通过对齐的图像中的各种尺寸的各种区域进行采样来生成部件提案。 为了确定哪个部分提案与语义部分相对应，针对每个部分提议和语义部分训练分类器，以确定哪个部分提案最符合真实语义部分给出的相关模式。 以这种方式，可以识别图像中的语义部分，而不需要任何先前的部分注释。
-
公开(公告)号：US20150339273A1
公开(公告)日：2015-11-26
申请号：US14286242
申请日：2014-05-23
Applicant: ADOBE SYSTEMS INCORPORATED
Inventor： JIANCHAO YANG , HAILIN JIN , JONATHAN BRANDT
IPC: G06F17/21 , G06F3/0484 , G06F17/30
CPC classification number: G06F17/214 , G06F3/0484 , G06F3/04842 , G06F17/30 , G06F17/30864 , G06F17/30958 , G06T11/206
Abstract: Font graphs are defined having a finite set of nodes representing fonts and a finite set of undirected edges denoting similarities between fonts. The font graphs enable users to browse and identify similar fonts. Indications corresponding to a degree of similarity between connected nodes may be provided. A selection of a desired font or characteristics associated with one or more attributes of the desired font is received from a user interacting with the font graph. The font graph is dynamically redefined based on the selection.
Abstract translation: 字体图被定义为具有表示字体的有限的节点集合和表示字体之间的相似性的无向边的有限集合。 字体图使用户能够浏览和识别类似的字体。 可以提供与连接的节点之间的相似程度相对应的指示。 从与字体图形交互的用户接收与期望字体的一个或多个属性相关联的期望字体或特征的选择。 基于选择动态地重新定义字体图。
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.017 seconds)
