-
公开(公告)号：US20240054991A1
公开(公告)日：2024-02-15
申请号：US17887959
申请日：2022-08-15
Applicant: Adobe Inc.
Inventor： Ajay Jain , Sanjeev Tagra , Sachin Soni , Ryan Rozich , Nikaash Puri , Jonathan Roeder
IPC: G10L15/06 , G06V10/774 , G10L15/183 , G06F40/284 , G06F40/30 , G06F3/16 , G10L15/22 , G06F16/532
CPC classification number: G10L15/063 , G06V10/7747 , G10L15/183 , G06F40/284 , G06F40/30 , G06F3/167 , G10L15/22 , G06F16/532
Abstract: An image search system uses a multi-modal model to determine relevance of images to a spoken query. The multi-modal model includes a spoken language model that extracts features from spoken query and a language processing model that extract features from an image. The multi-model model determines a relevance score for the image and the spoken query based on the extracted features. The multi-modal model is trained using a curriculum approach that includes training the spoken language model using audio data. Subsequently, a training dataset comprising a plurality of spoken queries and one or more images associated with each spoken query is used to jointly train the spoken language model and an image processing model to provide a trained multi-modal model.
-
公开(公告)号：US20230334121A1
公开(公告)日：2023-10-19
申请号：US18213641
申请日：2023-06-23
Applicant: Adobe Inc.
Inventor： Arshiya Aggarwal , Sanjeev Tagra , Sachin Soni , Ryan Rozich , Prasenjit Mondal , Jonathan Roeder , Ajay Jain
IPC: G06F18/22 , G06N5/04 , G06T5/50 , G06V10/40 , G06F18/2113
CPC classification number: G06F18/22 , G06N5/04 , G06T5/50 , G06V10/40 , G06F18/2113 , G06T2207/20081 , G06T2207/20084
Abstract: An image differentiation system receives input feature vectors for multiple input images and reference feature vectors for multiple reference images. In some cases, the feature vectors are extracted by an image feature extraction module trained based on training image triplets. A differentiability scoring module determines a differentiability score for each input image based on a distance between the input feature vectors and the reference feature vectors. The distance for each reference feature vector is modified by a weighting factor based on interaction metrics associated with the corresponding reference image. In some cases, an input image is identified as a differentiated image based on the corresponding differentiability score. Additionally or alternatively, an image modification module determines an image modification that increases the differentiability score of the input image. The image modification module generates a recommended image by applying the image modification to the input image.
-
公开(公告)号：US12254498B2
公开(公告)日：2025-03-18
申请号：US17817699
申请日：2022-08-05
Applicant: Adobe Inc.
Inventor： Sanjeev Tagra , Sachin Soni , Ryan Rozich , Nitish Maurya , Jonathan Roeder , Ajay Jain , Ajay Bedi
IPC: G06Q30/0601 , G06F3/0482 , G06F3/0484 , G06F3/04842 , G06F18/214 , G06F18/22 , G06F18/23 , G06N3/045 , G06N3/0464 , G06N3/08 , G06N3/09
Abstract: Techniques are disclosed for generating image recommendations to facilitate the sale of a product. An example methodology includes identifying a product category associated with an image of the product provided by the seller, and a product sub-category associated with the product image. The method further includes retrieving one or more images of for-sale items. The retrieval is based on a search of for-sale listings using the identified product category and the identified product sub-category. The method further includes clustering the retrieved images of for-sale items into groups, each group associated with a perspective viewpoint of the for-sale item. The method further includes providing a selected image from each group as an image recommendation. The selection is based on a value score associated with each of the images of the for-sale items. A graphical status indicating completeness of the seller's image set is updated in response to recommended images being adopted.
-
公开(公告)号：US20220383369A1
公开(公告)日：2022-12-01
申请号：US17817699
申请日：2022-08-05
Applicant: Adobe Inc.
Inventor： Sanjeev Tagra , Sachin Soni , Ryan Rozich , Nitish Maurya , Jonathan Roeder , Ajay Jain , Ajay Bedi
IPC: G06Q30/06 , G06K9/62 , G06N3/04 , G06F3/0484 , G06N3/08
Abstract: Techniques are disclosed for generating image recommendations to facilitate the sale of a product. An example methodology includes identifying a product category associated with an image of the product provided by the seller, and a product sub-category associated with the product image. The method further includes retrieving one or more images of for-sale items. The retrieval is based on a search of for-sale listings using the identified product category and the identified product sub-category. The method further includes clustering the retrieved images of for-sale items into groups, each group associated with a perspective viewpoint of the for-sale item. The method further includes providing a selected image from each group as an image recommendation. The selection is based on a value score associated with each of the images of the for-sale items. A graphical status indicating completeness of the seller's image set is updated in response to recommended images being adopted.
-
公开(公告)号：US20220121839A1
公开(公告)日：2022-04-21
申请号：US17076002
申请日：2020-10-21
Applicant: ADOBE INC.
Inventor： Sanjeev Tagra , Sachin Soni , Ajay Jain , Ryan Rozich , Jonathan Roeder , Arshiya Aggarwal , Prasenjit Mondal
Abstract: Methods, apparatus, and systems are provided for obfuscating facial identity in images by synthesizing a new facial image for an input image. A base face is detected from or selected for an input image. Facial images that are similar to the base face are selected and combined to create a new facial image. The new facial image is added to the input image such that the input image includes a combination of the base face and the new facial image. Where no base face is detected in the input image, a base face is selected from reference facial images based at least on pose keypoints identified in the input image. After a new facial image is generated based on the selected base face, a combination of the new facial image and the base facial image are added to the input image by aligning one or more pose keypoints.
-
Patent Agency Ranking
公开(公告)号：US11069034B2
公开(公告)日：2021-07-20
申请号：US16563315
申请日：2019-09-06
Applicant: ADOBE INC.
Inventor： Sanjeev Tagra , Sachin Soni , Ajay Jain , Ryan Rozich , Prasenjit Mondal , Jonathan Roeder
Abstract: The present disclosure relates to a computer-implemented method for generating an enhanced image from an original image, the method including segmenting the original image into a segmented image using an artificial neural network; curve fitting the segmented image to determine boundary artifacts; removing the determined boundary artifacts to generate a smoothed boundary image; and generating the enhanced image from the original image and the smoothed boundary image. The image maybe enhanced further by correcting for glare and adding artificial light.
-
公开(公告)号：US20210042993A1
公开(公告)日：2021-02-11
申请号：US16535780
申请日：2019-08-08
Applicant: Adobe Inc.
Inventor： Sanjeev Tagra , Sachin Soni , Ajay Jain , Ryan Rozich , Prasenjit Mondal , Jonathan Roeder
Abstract: Certain embodiments involve visually augmenting images of three-dimensional containers with virtual elements that fill one or more empty regions of the three-dimensional containers. For instance, a computing system receives a first image that depicts a storage container and identify sub-containers within the storage container. The computing system selects, from a virtual object library, a plurality of virtual objects that are semantically related to the sub-container. The computing system determines an arrangement of the virtual objects within the sub-container based on semantics associated with the sub-container and the plurality of virtual objects. The computing system generates a second image that depicts the arrangement of the plurality of virtual objects within the storage container and sub-containers. The computing system generates, for display, the second image depicting the storage container and the arrangement of the virtual objects.
-
公开(公告)号：US12288549B2
公开(公告)日：2025-04-29
申请号：US17887959
申请日：2022-08-15
Applicant: Adobe Inc.
Inventor： Ajay Jain , Sanjeev Tagra , Sachin Soni , Ryan Rozich , Nikaash Puri , Jonathan Roeder
IPC: G10L15/06 , G06F3/16 , G06F16/532 , G06F40/284 , G06F40/30 , G06V10/774 , G10L15/183 , G10L15/22
Abstract: An image search system uses a multi-modal model to determine relevance of images to a spoken query. The multi-modal model includes a spoken language model that extracts features from spoken query and a language processing model that extract features from an image. The multi-model model determines a relevance score for the image and the spoken query based on the extracted features. The multi-modal model is trained using a curriculum approach that includes training the spoken language model using audio data. Subsequently, a training dataset comprising a plurality of spoken queries and one or more images associated with each spoken query is used to jointly train the spoken language model and an image processing model to provide a trained multi-modal model.
-
公开(公告)号：US12124539B2
公开(公告)日：2024-10-22
申请号：US18213641
申请日：2023-06-23
Applicant: Adobe Inc.
Inventor： Arshiya Aggarwal , Sanjeev Tagra , Sachin Soni , Ryan Rozich , Prasenjit Mondal , Jonathan Roeder , Ajay Jain
IPC: G06F18/22 , G06F18/2113 , G06N5/04 , G06T5/50 , G06V10/40
CPC classification number: G06F18/22 , G06F18/2113 , G06N5/04 , G06T5/50 , G06V10/40 , G06T2207/20081 , G06T2207/20084
Abstract: An image differentiation system receives input feature vectors for multiple input images and reference feature vectors for multiple reference images. In some cases, the feature vectors are extracted by an image feature extraction module trained based on training image triplets. A differentiability scoring module determines a differentiability score for each input image based on a distance between the input feature vectors and the reference feature vectors. The distance for each reference feature vector is modified by a weighting factor based on interaction metrics associated with the corresponding reference image. In some cases, an input image is identified as a differentiated image based on the corresponding differentiability score. Additionally or alternatively, an image modification module determines an image modification that increases the differentiability score of the input image. The image modification module generates a recommended image by applying the image modification to the input image.
-
公开(公告)号：US11482041B2
公开(公告)日：2022-10-25
申请号：US17076002
申请日：2020-10-21
Applicant: ADOBE INC.
Inventor： Sanjeev Tagra , Sachin Soni , Ajay Jain , Ryan Rozich , Jonathan Roeder , Arshiya Aggarwal , Prasenjit Mondal
Abstract: Methods, apparatus, and systems are provided for obfuscating facial identity in images by synthesizing a new facial image for an input image. A base face is detected from or selected for an input image. Facial images that are similar to the base face are selected and combined to create a new facial image. The new facial image is added to the input image such that the input image includes a combination of the base face and the new facial image. Where no base face is detected in the input image, a base face is selected from reference facial images based at least on pose keypoints identified in the input image. After a new facial image is generated based on the selected base face, a combination of the new facial image and the base facial image are added to the input image by aligning one or more pose keypoints.
-
-
-
-
-
-
-
-
-
Search Results
18
records
(took 0.02 seconds)
