公开(公告)号：US20220121705A1

公开(公告)日：2022-04-21

申请号：US17565816

申请日：2021-12-30

Applicant: Adobe Inc.

Inventor： Saeid Motiian ,  Zhe Lin ,  Samarth Gulati ,  Pramod Srinivasan ,  Jose Ignacio Echevarria Vallespi ,  Baldo Antonio Faieta

IPC: G06F16/583 ,  G06F17/16 ,  G06F16/55 ,  G06F16/532

Abstract: In implementations of multi-resolution color-based image search, an image search system determines a color vector for a query image based on a color histogram of the query image by concatenating two color histograms having different resolutions. The image search system can compute distance measures between the color vector of the query image and color vectors of candidate images. The image search system can select one or more of the candidate images to return based on the distance measures utilizing the distance measures as indication of color similarity of the candidate images to the query image.

公开(公告)号：US11302033B2

公开(公告)日：2022-04-12

申请号：US16518795

申请日：2019-07-22

Applicant: Adobe Inc.

Inventor： Zhihong Ding ,  Scott Cohen ,  Zhe Lin ,  Mingyang Ling

IPC: G06T7/90 ,  G06K9/32 ,  G06K9/62 ,  G06N3/02 ,  G06V10/20

Abstract: The present disclosure relates to a color classification system that accurately classifies objects in digital images based on color. In particular, in one or more embodiments, the color classification system utilizes a multidimensional color space and one or more color mappings to match objects to colors. Indeed, the color classification system can accurately and efficiently detect the color of an object utilizing one or more color similarity regions generated in the multidimensional color space.

公开(公告)号：US20220092108A1

公开(公告)日：2022-03-24

申请号：US17025041

申请日：2020-09-18

Applicant: Adobe Inc.

Inventor： John Collomosse ,  Zhe Lin ,  Saeid Motiian ,  Hailin Jin ,  Baldo Faieta ,  Alex Filipkowski

IPC: G06F16/583 ,  G06F16/535 ,  G06F16/532 ,  G06N3/08

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly identifying digital images with similar style to a query digital image using fine-grain style determination via weakly supervised style extraction neural networks. For example, the disclosed systems can extract a style embedding from a query digital image using a style extraction neural network such as a novel two-branch autoencoder architecture or a weakly supervised discriminative neural network. The disclosed systems can generate a combined style embedding by combining complementary style embeddings from different style extraction neural networks. Moreover, the disclosed systems can search a repository of digital images to identify digital images with similar style to the query digital image. The disclosed systems can also learn parameters for one or more style extraction neural network through weakly supervised training without a specifically labeled style ontology for sample digital images.

公开(公告)号：US11276150B2

公开(公告)日：2022-03-15

申请号：US16893505

申请日：2020-06-05

Applicant: Adobe Inc.

Inventor： Jonathan Eisenmann ,  Zhe Lin ,  Matthew Fisher

IPC: G06T5/00 ,  G06T5/50 ,  G06T15/10 ,  G06T3/00 ,  G06T11/00

Abstract: In some embodiments, an image manipulation application receives a two-dimensional background image and projects the background image onto a sphere to generate a sphere image. Based on the sphere image, an unfilled environment map containing a hole area lacking image content can be generated. A portion of the unfilled environment map can be projected to an unfilled projection image using a map projection. The unfilled projection image contains the hole area. A hole filling model is applied to the unfilled projection image to generate a filled projection image containing image content for the hole area. A filled environment map can be generated by applying an inverse projection of the map projection on the filled projection image and by combining the unfilled environment map with the generated image content for the hole area of the environment map.

公开(公告)号：US20220058390A1

公开(公告)日：2022-02-24

申请号：US16998876

申请日：2020-08-20

Applicant: Adobe Inc.

Inventor： Quan Hung Tran ,  Long Thanh Mai ,  Zhe Lin ,  Zhuowan Li

IPC: G06K9/00 ,  G06K9/62 ,  G06F40/205 ,  G06F16/535 ,  G06F16/55

Abstract: A group captioning system includes computing hardware, software, and/or firmware components in support of the enhanced group captioning contemplated herein. In operation, the system generates a target embedding for a group of target images, as well as a reference embedding for a group of reference images. The system identifies information in-common between the group of target images and the group of reference images and removes the joint information from the target embedding and the reference embedding. The result is a contrastive group embedding that includes a contrastive target embedding and a contrastive reference embedding with which to construct a contrastive group embedding, which is then input to a model to obtain a group caption for the target group of images.

公开(公告)号：US11232147B2

公开(公告)日：2022-01-25

申请号：US16525366

申请日：2019-07-29

Applicant: Adobe Inc.

Inventor： Ajinkya Kale ,  Baldo Faieta ,  Benjamin Leviant ,  Fengbin Chen ,  Francois Guerin ,  Kate Sousa ,  Trung Bui ,  Venkat Barakam ,  Zhe Lin

IPC: G06F16/20 ,  G06F16/48 ,  G06K9/62 ,  G06F16/2457 ,  G06F16/43

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

公开(公告)号：US20210392278A1

公开(公告)日：2021-12-16

申请号：US16900435

申请日：2020-06-12

Applicant: ADOBE INC.

Inventor： Lu Zhang ,  Jianming Zhang ,  Zhe Lin ,  Radomir Mech

IPC: H04N5/262 ,  G06K9/46 ,  G06K9/00 ,  G11B27/031

Abstract: Systems and methods provide reframing operations in a smart editing system that may generate a focal point within a mask of an object for each frame of a video segment and perform editing effects on the frames of the video segment to quickly provide users with natural video editing effects. A reframing engine may processes video clips using a segmentation and hotspot module to determine a salient region of an object, generate a mask of the object, and track the trajectory of an object in the video clips. The reframing engine may then receive reframing parameters from a crop suggestion module and a user interface. Based on the determined trajectory of an object in a video clip and reframing parameters, the reframing engine may use reframing logic to produce temporally consistent reframing effects relative to an object for the video clip.

公开(公告)号：US20210390710A1

公开(公告)日：2021-12-16

申请号：US16900483

申请日：2020-06-12

Applicant: Adobe Inc.

Inventor： Lu Zhang ,  Jianming Zhang ,  Zhe Lin ,  Radomir Mech

IPC: G06T7/20 ,  G06T7/00 ,  G06T11/60 ,  G06F3/01 ,  G06F3/0484 ,  G06N3/02

Abstract: Systems and methods provide editing operations in a smart editing system that may generate a focal point within a mask of an object for each frame of a video segment and perform editing effects on the frames of the video segment to quickly provide users with natural video editing effects. An eye-gaze network may produce a hotspot map of predicted focal points in a video frame. These predicted focal points may then be used by a gaze-to-mask network to determine objects in the image and generate an object mask for each of the detected objects. This process may then be repeated to effectively track the trajectory of objects and object focal points in videos. Based on the determined trajectory of an object in a video clip and editing parameters, the editing engine may produce editing effects relative to an object for the video clip.

公开(公告)号：US20210365727A1

公开(公告)日：2021-11-25

申请号：US17398317

申请日：2021-08-10

Applicant: Adobe Inc.

Inventor： Pranav Vineet Aggarwal ,  Zhe Lin ,  Baldo Antonio Faieta ,  Saeid Motiian

IPC: G06K9/62 ,  G06F16/535 ,  G06N20/00 ,  G06K9/72

Abstract: Text-to-visual machine learning embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. These techniques include use of query-based training data which may expand availability and types of training data usable to train a model. Generation of negative digital image samples is also described that may increase accuracy in training the model using machine learning. A loss function is also described that also supports increased accuracy and computational efficiency by losses separately, e.g., between positive or negative sample embeddings a text embedding.

公开(公告)号：US11144784B2

公开(公告)日：2021-10-12

申请号：US16426264

申请日：2019-05-30

Applicant: Adobe Inc.

Inventor： Pranav Vineet Aggarwal ,  Zhe Lin ,  Baldo Antonio Faieta ,  Saeid Motiian

IPC: G06K9/62 ,  G06K9/72 ,  G06F16/535 ,  G06N20/00 ,  G06F3/0482

Abstract: Text-to-visual machine learning embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. These techniques include use of query-based training data which may expand availability and types of training data usable to train a model. Generation of negative digital image samples is also described that may increase accuracy in training the model using machine learning. A loss function is also described that also supports increased accuracy and computational efficiency by losses separately, e.g., between positive or negative sample embeddings a text embedding.