公开(公告)号：US11138257B2

公开(公告)日：2021-10-05

申请号：US16745143

申请日：2020-01-16

Applicant: Adobe Inc.

Inventor： Midhun Harikumar ,  Zhe Lin ,  Pramod Srinivasan ,  Jianming Zhang ,  Daniel David Miranda ,  Baldo Antonio Faieta

IPC: G06F16/532 ,  G06F3/0484 ,  G06T7/11 ,  G06F16/538 ,  G06F16/587 ,  G06T7/70

Abstract: Object search techniques for digital images are described. In the techniques described herein, semantic features are extracted on a per-object basis form a digital image. This supports location of objects within digital images and is not limited to semantic features of an entirety of the digital image as involved in conventional image similarity search techniques. This may be combined with indications a location of the object globally with respect to the digital image through use of a global segmentation mask, use of a local segmentation mask to capture post and characteristics of the object itself, and so on.

公开(公告)号：US11126890B2

公开(公告)日：2021-09-21

申请号：US16388115

申请日：2019-04-18

Applicant: ADOBE INC.

Inventor： Zhe Lin ,  Mingyang Ling ,  Jianming Zhang ,  Jason Kuen ,  Federico Perazzi ,  Brett Butterfield ,  Baldo Faieta

IPC: G06K9/62 ,  G06K9/34 ,  G06N3/08

Abstract: Systems and methods are described for object detection within a digital image using a hierarchical softmax function. The method may include applying a first softmax function of a softmax hierarchy on a digital image based on a first set of object classes that are children of a root node of a class hierarchy, then apply a second (and subsequent) softmax functions to the digital image based on a second (and subsequent) set of object classes, where the second (and subsequent) object classes are children nodes of an object class from the first (or parent) object classes. The methods may then include generating an object recognition output using a convolutional neural network (CNN) based at least in part on applying the first and second (and subsequent) softmax functions. In some cases, the hierarchical softmax function is the loss function for the CNN.

公开(公告)号：US20210263962A1

公开(公告)日：2021-08-26

申请号：US16800415

申请日：2020-02-25

Applicant: Adobe Inc.

Inventor： Walter Wei Tuh Chang ,  Khoi Pham ,  Scott Cohen ,  Zhe Lin ,  Zhihong Ding

IPC: G06F16/532 ,  G06T11/60 ,  G06K9/62 ,  G06F40/279 ,  G06F40/247 ,  G06F40/30 ,  G06F16/583 ,  G06F16/242 ,  G06F16/28 ,  G06F16/538 ,  G06N20/00

Abstract: The present disclosure relates to an object selection system that automatically detects and selects objects in a digital image based on natural language-based inputs. For instance, the object selection system can utilize natural language processing tools to detect objects and their corresponding relationships within natural language object selection queries. For example, the object selection system can determine alternative object terms for unrecognized objects in a natural language object selection query. As another example, the object selection system can determine multiple types of relationships between objects in a natural language object selection query and utilize different object relationship models to select the requested query object.

公开(公告)号：US20210232850A1

公开(公告)日：2021-07-29

申请号：US16750478

申请日：2020-01-23

Applicant: Adobe Inc.

Inventor： Trung Huu Bui ,  Zhe Lin ,  Hao Tan ,  Franck Dernoncourt ,  Mohit Bansal

IPC: G06K9/62 ,  G06K9/46 ,  G06F40/10

Abstract: In implementations of generating descriptions of image relationships, a computing device implements a description system which receives a source digital image and a target digital image. The description system generates a source feature sequence from the source digital image and a target feature sequence from the target digital image. A visual relationship between the source digital image and the target digital image is determined by using cross-attention between the source feature sequence and the target feature sequence. The system generates a description of a visual transformation between the source digital image and the target digital image based on the visual relationship.

公开(公告)号：US20210224312A1

公开(公告)日：2021-07-22

申请号：US16745143

申请日：2020-01-16

Applicant: Adobe Inc.

Inventor： Midhun Harikumar ,  Zhe Lin ,  Pramod Srinivasan ,  Jianming Zhang ,  Daniel David Miranda ,  Baldo Antonio Faieta

IPC: G06F16/532 ,  G06F3/0484 ,  G06T7/11 ,  G06T7/70 ,  G06F16/538 ,  G06F16/587

Abstract: Object search techniques for digital images are described. In the techniques described herein, semantic features are extracted on a per-object basis form a digital image. This supports location of objects within digital images and is not limited to semantic features of an entirety of the digital image as involved in conventional image similarity search techniques. This may be combined with indications a location of the object globally with respect to the digital image through use of a global segmentation mask, use of a local segmentation mask to capture post and characteristics of the object itself, and so on.

公开(公告)号：US20210027471A1

公开(公告)日：2021-01-28

申请号：US16518880

申请日：2019-07-22

Applicant: Adobe Inc.

Inventor： Scott Cohen ,  Zhe Lin ,  Mingyang Ling

IPC: G06T7/11 ,  G06T7/90 ,  G06F16/33 ,  G06K9/46 ,  G06K9/62 ,  G10L15/22 ,  G06N3/04

Abstract: The present disclosure relates to an object selection system that accurately detects and automatically selects user-requested objects (e.g., query objects) in a digital image. For example, the object selection system builds and utilizes an object selection pipeline to determine which object detection neural network to utilize to detect a query object based on analyzing the object class of the query object. In addition, the object selection system can add, update, or replace portions of the object selection pipeline to improve overall accuracy and efficiency of automatic object selection within an image.

公开(公告)号：US20210004576A1

公开(公告)日：2021-01-07

申请号：US17025477

申请日：2020-09-18

Applicant: Adobe Inc.

Inventor： Trung Bui ,  Zhe Lin ,  Walter Chang ,  Nham Le ,  Franck Dernoncourt

IPC: G06K9/00 ,  G06N3/04 ,  G10L15/26 ,  G10L15/25

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified digital images based on verbal and/or gesture input by utilizing a natural language processing neural network and one or more computer vision neural networks. The disclosed systems can receive verbal input together with gesture input. The disclosed systems can further utilize a natural language processing neural network to generate a verbal command based on verbal input. The disclosed systems can select a particular computer vision neural network based on the verbal input and/or the gesture input. The disclosed systems can apply the selected computer vision neural network to identify pixels within a digital image that correspond to an object indicated by the verbal input and/or gesture input. Utilizing the identified pixels, the disclosed systems can generate a modified digital image by performing one or more editing actions indicated by the verbal input and/or gesture input.

公开(公告)号：US10853700B2

公开(公告)日：2020-12-01

申请号：US16928949

申请日：2020-07-14

Applicant: Adobe Inc.

Inventor： Jayant Kumar ,  Zhe Lin ,  Vipulkumar C. Dalal

IPC: G06K9/62

Abstract: There is described a computing device and method in a digital medium environment for custom auto tagging of multiple objects. The computing device includes an object detection network and multiple image classification networks. An image is received at the object detection network and includes multiple visual objects. First feature maps are applied to the image at the object detection network and generate object regions associated with the visual objects. The object regions are assigned to the multiple image classification networks, and each image classification network is assigned to a particular object region. The second feature maps are applied to each object region at each image classification network, and each image classification network outputs one or more classes associated with a visual object corresponding to each object region.

公开(公告)号：US20200372622A1

公开(公告)日：2020-11-26

申请号：US16984992

申请日：2020-08-04

Applicant: Adobe Inc.

Inventor： Yilin Wang ,  Zhe Lin ,  Zhaowen Wang ,  Xin Lu ,  Xiaohui Shen ,  Chih-Yao Hsieh

IPC: G06T5/50

Abstract: The present disclosure relates to training and utilizing an image exposure transformation network to generate a long-exposure image from a single short-exposure image (e.g., still image). In various embodiments, the image exposure transformation network is trained using adversarial learning, long-exposure ground truth images, and a multi-term loss function. In some embodiments, the image exposure transformation network includes an optical flow prediction network and/or an appearance guided attention network. Trained embodiments of the image exposure transformation network generate realistic long-exposure images from single short- exposure images without additional information.

公开(公告)号：US10832036B2

公开(公告)日：2020-11-10

申请号：US16036757

申请日：2018-07-16

Applicant: ADOBE INC.

Inventor： Haoxiang Li ,  Zhe Lin ,  Muhammad Abdullah Jamal

IPC: G06K9/00 ,  G06N3/08

Abstract: Methods and systems are provided for generating a facial recognition system. A facial recognition system can be implemented using a meta-model based on a trained neural network. A neural network can be trained as multiple classifiers that identify individuals using a small number of images of the individual's face. A meta-model can learn from the neural networks to be capable to identify an individual based on a small number of images. In this way, the facial recognition system uses the meta-model that learns from the neural network trained to identify an individual based on a small number of images. Such a facial recognition system is tested to determine any misidentification for fine-tuning the system. A facial recognition system implemented using such a meta-model is capable of adapting the model to learn identities entered into the system using only a small number of images to enroll an identity into the system.