公开(公告)号：US11562234B2

公开(公告)日：2023-01-24

申请号：US16751755

申请日：2020-01-24

Applicant: Adobe Inc.

Inventor： Yikun Xian ,  Tak Yeon Lee ,  Sungchul Kim ,  Ryan Rossi ,  Handong Zhao

IPC: G06N3/08

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for dynamically determining schema labels for columns regardless of information availability within the columns. For example, the disclosed systems can identify a column that contains an arbitrary amount of information (e.g., a header-only column, a cell-only column, or a whole column). Additionally, the disclosed systems can generate a vector embedding for an arbitrary input column by selectively using a header neural network and/or a cell neural network based on whether the column includes a header label and/or whether the column includes a populated column cell. Furthermore, the disclosed systems can compare the column vector embedding to schema vector embeddings of candidate schema labels in a d-dimensional space to determine a schema label for the column.

公开(公告)号：US11544503B2

公开(公告)日：2023-01-03

申请号：US16885168

申请日：2020-05-27

Applicant: Adobe Inc.

Inventor： Christopher Tensmeyer ,  Vlad Ion Morariu ,  Varun Manjunatha ,  Tong Sun ,  Nikolaos Barmpalios ,  Kai Li ,  Handong Zhao ,  Curtis Wigington

IPC: G06K9/00 ,  G06K9/62 ,  G06N5/04 ,  G06V30/40

Abstract: A domain alignment technique for cross-domain object detection tasks is introduced. During a preliminary pretraining phase, an object detection model is pretrained to detect objects in images associated with a source domain using a source dataset of images associated with the source domain. After completing the pretraining phase, a domain adaptation phase is performed using the source dataset and a target dataset to adapt the pretrained object detection model to detect objects in images associated with the target domain. The domain adaptation phase may involve the use of various domain alignment modules that, for example, perform multi-scale pixel/path alignment based on input feature maps or perform instance-level alignment based on input region proposals.

公开(公告)号：US20220391768A1

公开(公告)日：2022-12-08

申请号：US17883811

申请日：2022-08-09

Applicant: Adobe Inc.

Inventor： Kai Li ,  Christopher Alan Tensmeyer ,  Curtis Michael Wigington ,  Handong Zhao ,  Nikolaos Barmpalios ,  Tong Sun ,  Varun Manjunatha ,  Vlad Ion Morariu

IPC: G06N20/00 ,  G06N3/04

Abstract: Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

公开(公告)号：US20220309762A1

公开(公告)日：2022-09-29

申请号：US17805289

申请日：2022-06-03

Applicant: Adobe Inc.

Inventor： Handong Zhao ,  Zhe Lin ,  Sheng Li ,  Mingyang Ling ,  Jiuxiang Gu

IPC: G06V10/26 ,  G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06V10/426

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating semantic scene graphs for digital images using an external knowledgebase for feature refinement. For example, the disclosed system can determine object proposals and subgraph proposals for a digital image to indicate candidate relationships between objects in the digital image. The disclosed system can then extract relationships from an external knowledgebase for refining features of the object proposals and the subgraph proposals. Additionally, the disclosed system can generate a semantic scene graph for the digital image based on the refined features of the object/subgraph proposals. Furthermore, the disclosed system can update/train a semantic scene graph generation network based on the generated semantic scene graph. The disclosed system can also reconstruct the image using object labels based on the refined features to further update/train the semantic scene graph generation network.

公开(公告)号：US20220295149A1

公开(公告)日：2022-09-15

申请号：US17200691

申请日：2021-03-12

Applicant: Adobe Inc.

Inventor： Handong Zhao ,  Zhankui He ,  Zhe Lin ,  Zhaowen Wang ,  Ajinkya Gorakhnath Kale

IPC: H04N21/466 ,  H04N21/4722 ,  H04N21/45 ,  G06N3/08

Abstract: A multimodal recommendation identification system analyzes data describing a sequence of past content item interactions to generate a recommendation for a content item for a user. An indication of the recommended content item is provided to a website hosting system or recommendation system so that the recommended content item is displayed or otherwise presented to the user. The multimodal recommendation identification system identifies a content item to recommend to the user by generating an encoding that encodes identifiers of the sequence of content items the user has interacted with and generating encodings that encode multimodal information for content items in the sequence of content items the user has interacted with. An aggregated information encoding for a user based on these encodings and a system analyzes the content item sequence encoding and interaction between the content item sequence encoding and the multiple modality encodings to generate the aggregated information encoding.

公开(公告)号：US20220237682A1

公开(公告)日：2022-07-28

申请号：US17159554

申请日：2021-01-27

Applicant: ADOBE INC.

Inventor： Handong Zhao ,  Zhankui He ,  Zhaowen Wang ,  Zhe Lin ,  Ajinkya Kale ,  Fengbin Chen

IPC: G06Q30/06 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62

Abstract: Systems and methods for item recommendation are described. Embodiments identify a sequence of items selected by a user, embed each item of the sequence of items to produce item embeddings having a reduced number of dimensions, predict a next item based on the item embeddings using a recommendation network, wherein the recommendation network includes a sequential encoder trained based at least in part on a sampled softmax classifier, and wherein predicting the next item represents a prediction that the user will interact with the next item, and provide a recommendation to the user, wherein the recommendation includes the next item.

公开(公告)号：US20220036127A1

公开(公告)日：2022-02-03

申请号：US16943511

申请日：2020-07-30

Applicant: Adobe Inc.

Inventor： Zhe Lin ,  Xihui Liu ,  Quan Hung Tran ,  Jianming Zhang ,  Handong Zhao

IPC: G06K9/62 ,  G06T11/00 ,  G06K9/46

Abstract: The technology described herein is directed to a reinforcement learning based framework for training a natural media agent to learn a rendering policy without human supervision or labeled datasets. The reinforcement learning based framework feeds the natural media agent a training dataset to implicitly learn the rendering policy by exploring a canvas and minimizing a loss function. Once trained, the natural media agent can be applied to any reference image to generate a series (or sequence) of continuous-valued primitive graphic actions, e.g., sequence of painting strokes, that when rendered by a synthetic rendering environment on a canvas, reproduce an identical or transformed version of the reference image subject to limitations of an action space and the learned rendering policy.

公开(公告)号：US20200327446A1

公开(公告)日：2020-10-15

申请号：US16380566

申请日：2019-04-10

Applicant: Adobe Inc.

Inventor： Xiaowei Jia ,  Sheng Li ,  Handong Zhao ,  Sungchul Kim

IPC: G06N20/00

Abstract: Techniques are disclosed for the generation of adversarial training data through sequence perturbation, for a deep learning network to perform event sequence analysis. A methodology implementing the techniques according to an embodiment includes applying a long short-term memory attention model to an input data sequence to generate discriminative sequence periods and attention weights associated with the discriminative sequence periods. The attention weights are generated to indicate the relative importance of data in those discriminative sequence periods. The method further includes generating perturbed data sequences based on the discriminative sequence periods and the attention weights. The generation of the perturbed data sequences employs selective filtering or conservative adversarial training, to preserve perceptual similarity between the input data sequence and the perturbed data sequences. The input data sequence may be created by vectorizing a temporal input data stream comprising words, symbols, and the like, into a multidimensional vectorized numerical data sequence format.