Patents by Inventor Baldo Antonio Faieta
Baldo Antonio Faieta has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240095277Abstract: Systems and methods for image exploration are provided. One aspect of the systems and methods includes identifying a set of images; reducing the set of images to obtain a representative set of images that is distributed throughout the set of images by removing a neighbor image based on a proximity of the neighbor image to an image of the representative set of images; arranging the representative set of images in a grid structure using a self-sorting map (SSM) algorithm; and displaying a portion of the representative set of images based on the grid structure.Type: ApplicationFiled: September 16, 2022Publication date: March 21, 2024Inventors: Sachin Madhav Kelkar, Ajinkya Gorakhnath Kale, Alvin Ghouas, Baldo Antonio Faieta
-
Patent number: 11934448Abstract: Keyword localization digital image search techniques are described. These techniques support an ability to indicate “where” a corresponding keyword is to be expressed with respect to a layout in a respective digital image resulting from a search query. The search query may also include an indication of a size of the keyword as expressed in the digital image, a number of instances of the keyword, and so forth. Additionally, the techniques and systems as described herein support real time search through use of keyword signatures.Type: GrantFiled: April 18, 2023Date of Patent: March 19, 2024Assignee: Adobe Inc.Inventors: Pramod Srinivasan, Zhe Lin, Samarth Gulati, Saeid Motiian, Midhun Harikumar, Baldo Antonio Faieta, Alex C. Filipkowski
-
Patent number: 11853348Abstract: Multidimensional digital content search techniques are described that support an ability of a computing device to perform search with increased granularity and flexibility over conventional techniques. In one example, a control is implemented by a computing device that defines a multidimensional (e.g., two-dimensional) continuous space. Locations in the multidimensional continuous space are usable to different search criteria through different weights applied to the criteria associated with the axes. Therefore, user interaction with this control may be used to define a location and corresponding coordinates that may act as weights to the search criteria in order to perform a search of digital content through use of a single user input.Type: GrantFiled: June 24, 2020Date of Patent: December 26, 2023Assignee: Adobe Inc.Inventors: Akhilesh Kumar, Zhe Lin, Ratheesh Kalarot, Jinrong Xie, Jianming Zhang, Baldo Antonio Faieta, Alex Charles Filipkowski
-
Publication number: 20230360299Abstract: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.Type: ApplicationFiled: July 21, 2023Publication date: November 9, 2023Applicant: Adobe Inc.Inventors: Yang Yang, Zhixin Shu, Shabnam Ghadar, Jingwan Lu, Jakub Fiser, Elya Schechtman, Cameron Y. Smith, Baldo Antonio Faieta, Alex Charles Filipkowski
-
Patent number: 11775578Abstract: 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.Type: GrantFiled: August 10, 2021Date of Patent: October 3, 2023Assignee: Adobe Inc.Inventors: Pranav Vineet Aggarwal, Zhe Lin, Baldo Antonio Faieta, Saeid Motiian
-
Patent number: 11748928Abstract: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.Type: GrantFiled: November 10, 2020Date of Patent: September 5, 2023Assignee: Adobe Inc.Inventors: Yang Yang, Zhixin Shu, Shabnam Ghadar, Jingwan Lu, Jakub Fiser, Elya Schechtman, Cameron Y. Smith, Baldo Antonio Faieta, Alex Charles Filipkowski
-
Publication number: 20230252071Abstract: Keyword localization digital image search techniques are described. These techniques support an ability to indicate “where” a corresponding keyword is to be expressed with respect to a layout in a respective digital image resulting from a search query. The search query may also include an indication of a size of the keyword as expressed in the digital image, a number of instances of the keyword, and so forth. Additionally, the techniques and systems as described herein support real time search through use of keyword signatures.Type: ApplicationFiled: April 18, 2023Publication date: August 10, 2023Applicant: Adobe Inc.Inventors: Pramod Srinivasan, Zhe Lin, Samarth Gulati, Saeid Motiian, Midhun Harikumar, Baldo Antonio Faieta, Alex C. Filipkowski
-
Publication number: 20230185844Abstract: Visually guided machine-learning language model and embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. In one example, a model is trained to support a visually guided machine-learning embedding space that supports visual intuition as to “what” is represented by text. The visually guided language embedding space supported by the model, once trained, may then be used to support visual intuition as part of a variety of functionality. In one such example, the visually guided language embedding space as implemented by the model may be leveraged as part of a multi-modal differential search to support search of digital images and other digital content with real-time focus adaptation which overcomes the challenges of conventional techniques.Type: ApplicationFiled: February 2, 2023Publication date: June 15, 2023Applicant: Adobe Inc.Inventors: Pranav Vineet Aggarwal, Zhe Lin, Baldo Antonio Faieta, Saeid Antonio Motiian
-
Patent number: 11669566Abstract: 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.Type: GrantFiled: December 30, 2021Date of Patent: June 6, 2023Assignee: Adobe Inc.Inventors: Saeid Motiian, Zhe Lin, Samarth Gulati, Pramod Srinivasan, Jose Ignacio Echevarria Vallespi, Baldo Antonio Faieta
-
Patent number: 11663264Abstract: Keyword localization digital image search techniques are described. These techniques support an ability to indicate “where” a corresponding keyword is to be expressed with respect to a layout in a respective digital image resulting from a search query. The search query may also include an indication of a size of the keyword as expressed in the digital image, a number of instances of the keyword, and so forth. Additionally, the techniques and systems as described herein support real time search through use of keyword signatures.Type: GrantFiled: February 7, 2020Date of Patent: May 30, 2023Assignee: Adobe Inc.Inventors: Pramod Srinivasan, Zhe Lin, Samarth Gulati, Saeid Motiian, Midhun Harikumar, Baldo Antonio Faieta, Alex C. Filipkowski
-
Patent number: 11604822Abstract: Multi-modal differential search with real-time focus adaptation techniques are described that overcome the challenges of conventional techniques in a variety of ways. In one example, a model is trained to support a visually guided machine-learning embedding space that supports visual intuition as to “what” is represented by text. The visually guided language embedding space supported by the model, once trained, may then be used to support visual intuition as part of a variety of functionality. In one such example, the visually guided language embedding space as implemented by the model may be leveraged as part of a multi-modal differential search to support search of digital images and other digital content with real-time focus adaptation which overcomes the challenges of conventional techniques.Type: GrantFiled: May 30, 2019Date of Patent: March 14, 2023Assignee: Adobe Inc.Inventors: Pranav Vineet Aggarwal, Zhe Lin, Baldo Antonio Faieta, Saeid Motiian
-
Patent number: 11605019Abstract: Visually guided machine-learning language model and embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. In one example, a model is trained to support a visually guided machine-learning embedding space that supports visual intuition as to “what” is represented by text. The visually guided language embedding space supported by the model, once trained, may then be used to support visual intuition as part of a variety of functionality. In one such example, the visually guided language embedding space as implemented by the model may be leveraged as part of a multi-modal differential search to support search of digital images and other digital content with real-time focus adaptation which overcomes the challenges of conventional techniques.Type: GrantFiled: May 30, 2019Date of Patent: March 14, 2023Assignee: Adobe Inc.Inventors: Pranav Vineet Aggarwal, Zhe Lin, Baldo Antonio Faieta, Saeid Motiian
-
Publication number: 20220148243Abstract: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.Type: ApplicationFiled: November 10, 2020Publication date: May 12, 2022Applicant: Adobe Inc.Inventors: Yang Yang, Zhixin Shu, Shabnam Ghadar, Jingwan Lu, Jakub Fiser, Elya Schechtman, Cameron Y. Smith, Baldo Antonio Faieta, Alex Charles Filipkowski
-
Publication number: 20220121705Abstract: 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.Type: ApplicationFiled: December 30, 2021Publication date: April 21, 2022Applicant: Adobe Inc.Inventors: Saeid Motiian, Zhe Lin, Samarth Gulati, Pramod Srinivasan, Jose Ignacio Echevarria Vallespi, Baldo Antonio Faieta
-
Patent number: 11288727Abstract: Content creation suggestion techniques are described. In one or more implementations, techniques are implemented to generate suggestions that are usable to guide creative professionals in the creation of content such as images, video, sound, multimedia, and so forth. A variety of techniques are usable to generate suggestions for the content professionals. In a first such example, suggestions are based on shared characteristics of images obtained by users of a content sharing service, e.g., licensed by the users. In another example, suggestions are generated by the content sharing service based on keywords used to locate the images. In a further example, suggestions are generated based on data described communications performed using social network services. In yet another example, recognition of failure of search is used to generate suggestions. A variety of other examples are also contemplated and described herein.Type: GrantFiled: November 4, 2019Date of Patent: March 29, 2022Assignee: Adobe Inc.Inventors: Zeke Koch, Baldo Antonio Faieta, Jen-Chan Chien, Mark M. Randall, Olivier Sirven, Philipp Koch, Dennis G. Nicholson
-
Patent number: 11216505Abstract: 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.Type: GrantFiled: September 5, 2019Date of Patent: January 4, 2022Assignee: Adobe Inc.Inventors: Saeid Motiian, Zhe Lin, Samarth Gulati, Pramod Srinivasan, Jose Ignacio Echevarria Vallespi, Baldo Antonio Faieta
-
Publication number: 20210406302Abstract: Multidimensional digital content search techniques are described that support an ability of a computing device to perform search with increased granularity and flexibility over conventional techniques. In one example, a control is implemented by a computing device that defines a multidimensional (e.g., two-dimensional) continuous space. Locations in the multidimensional continuous space are usable to different search criteria through different weights applied to the criteria associated with the axes. Therefore, user interaction with this control may be used to define a location and corresponding coordinates that may act as weights to the search criteria in order to perform a search of digital content through use of a single user input.Type: ApplicationFiled: June 24, 2020Publication date: December 30, 2021Applicant: Adobe Inc.Inventors: Akhilesh Kumar, Zhe Lin, Ratheesh Kalarot, Jinrong Xie, Jianming Zhang, Baldo Antonio Faieta, Alex Charles Filipkowski
-
Publication number: 20210365727Abstract: 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.Type: ApplicationFiled: August 10, 2021Publication date: November 25, 2021Applicant: Adobe Inc.Inventors: Pranav Vineet Aggarwal, Zhe Lin, Baldo Antonio Faieta, Saeid Motiian
-
Patent number: 11144784Abstract: 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.Type: GrantFiled: May 30, 2019Date of Patent: October 12, 2021Assignee: Adobe Inc.Inventors: Pranav Vineet Aggarwal, Zhe Lin, Baldo Antonio Faieta, Saeid Motiian
-
Patent number: 11138257Abstract: 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.Type: GrantFiled: January 16, 2020Date of Patent: October 5, 2021Assignee: Adobe Inc.Inventors: Midhun Harikumar, Zhe Lin, Pramod Srinivasan, Jianming Zhang, Daniel David Miranda, Baldo Antonio Faieta