Patents Assigned to ARTIFICIAL INTELLIGENCE, LTD.
-
Publication number: 20250094482Abstract: Methods, systems, and techniques for image categorization using a visual language model. A set of images is clustered into clusters respectively corresponding to differently categorized objects. Names are respectively assigned to the clusters, and image captions are respectively generated for the clusters using the names. The image captions and respective images represent image-text pairs. Those image-text pairs are input to the visual language model as context for a query. The query is then input to the visual language model. The query includes a request to categorize a query image of a class represented in the context. In response to the query, the visual language model performs an open-ended generative categorization of the query image.Type: ApplicationFiled: September 20, 2023Publication date: March 20, 2025Applicant: INCEPTION INSTITUTE OF ARTIFICIAL INTELLIGENCE, LTD.Inventors: Ivona Najdenkoska, Mohammad Derakhshani, Yuki Asano, Cees Snoek, Marcel Worring
-
Patent number: 12223281Abstract: Systems, methods and non-transitory computer readable media for generating content using a generative model without relying on selected training examples are provided. An input indicative of a desire to generate a new content using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may be associated with a respective content. Further, an indication of a particular subgroup of at least one but not all of the plurality of training examples may be obtained. Based on the indication, the input and the generative model may be used to generate the new content, abstaining from basing the generation of the new content on any training example included in the particular subgroup. The new content may be provided.Type: GrantFiled: November 7, 2023Date of Patent: February 11, 2025Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Efrat Taig, Nimrod Sarid, Ron Mokady, Eyal Gutflaish
-
Patent number: 12190417Abstract: Systems, methods and non-transitory computer readable media for generating and orchestrating motion of visual contents are provided. A plurality of visual contents may be accessed. Data indicative of a layout of the plurality of visual contents in a user interface may be accessed. A sequence for the plurality of visual contents may be determined based on the layout. For each visual content of the plurality of visual contents, the visual content may be analyzed to generate a video clip including a motion of at least one object depicted in the visual content. A presentation of the plurality of visual contents in the user interface may be caused. The determined sequence for the plurality of visual contents may be used to orchestrate a series of playbacks of the generated video clips.Type: GrantFiled: November 4, 2021Date of Patent: January 7, 2025Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Gal Jacobi, Ori Feldstein, Eyal Gutflaish
-
Patent number: 12182910Abstract: Systems, methods and non-transitory computer readable media for propagating changes from one visual content to other visual contents are provided. A plurality of visual contents may be accessed. A first visual content and a modified version of the first visual content may be accessed. The first visual content and the modified version of the first visual content may be analyzed to determine a manipulation for the plurality of visual contents. The determined manipulation may be used to generate a manipulated visual content for each visual content of the plurality of visual contents. The generated manipulated visual contents may be provided.Type: GrantFiled: November 4, 2021Date of Patent: December 31, 2024Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Gal Jacobi, Efrat Taig, Bar Fingerman, Dvir Yerushalmi, Eyal Gutflaish
-
Patent number: 12142029Abstract: Systems, methods and non-transitory computer readable media for attributing generated visual content to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be associated with a plurality of training examples. Each training example may be associated with a visual content. Properties of the first visual content may be determined. Each visual content associated with a training example may be analyzed to determine properties of the visual content. The properties of the first visual content and the properties of the visual contents associated with the plurality of training examples may be used to attribute the first visual content to a subgroup of the plurality of training examples. The visual contents associated with the training examples of the subgroup may be associated with a source. A data-record associated with the source may be updated based on the attribution.Type: GrantFiled: November 14, 2022Date of Patent: November 12, 2024Assignee: BRIA ARTIFICIAL INTELLIGENCE LTDInventors: Yair Adato, Ran Achituv, Eyal Gutflaish, Dvir Yerushalmi
-
Patent number: 12080277Abstract: Systems, methods and non-transitory computer readable media for attributing generated audio contents to training examples are provided. A first audio content generated using a generative model may be received. The generative model may be a result of training a machine learning model using training examples. Each training example may be associated with a respective audio content. Properties of the first audio content may be determined. For each training example of the training examples, the respective audio content may be analyzed to determine properties of the respective audio content. The properties of the first audio content and the properties of the audio contents associated with the training examples may be used to attribute the first audio content to a subgroup of the training examples. A respective data-record associated with a source associated with the training examples of the subgroup may be updated based on the attribution.Type: GrantFiled: November 7, 2023Date of Patent: September 3, 2024Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Michael Feinstein, Nimrod Sarid, Ron Mokady, Eyal Gutflaish, Vered Horesh-Yaniv
-
Patent number: 12073605Abstract: Systems, methods and non-transitory computer readable media for attributing aspects of generated visual contents to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Properties of an aspect of the first visual content and properties of visual contents associated with the plurality of training examples may be used to attribute the aspect of the first visual content to a subgroup of the plurality of training examples. For each source of the sources associated with the visual contents associated with the training examples of the subgroup, a data-record associated with the source may be updated based on the attribution of the aspect of the first visual content.Type: GrantFiled: November 7, 2023Date of Patent: August 27, 2024Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Michael Feinstein, Nimrod Sarid, Ron Mokady, Eyal Gutflaish, Vered Horesh-Yaniv
-
Patent number: 12062205Abstract: Disclosed are camera pose determination methods and apparatuses. The method includes determining first pixels in a current image and second pixels in a previous image, determining second pixel points with the preconfigured semantics in a previous image frame before the current image frame, the first pixel points corresponding to at least a portion of the second pixel points, determining an error between the first pixel points and the second pixel points, and a camera pose change value of the current image frame relative to the previous image frame based on the error, and determining a camera pose of the current image based on a camera pose of the previous image and the camera pose change. Related devices and storage media are also disclosed.Type: GrantFiled: August 5, 2019Date of Patent: August 13, 2024Assignee: NANJING INSTITUTE OF ADVANCED ARTIFICIAL INTELLIGENCE, LTD.Inventor: Qinrui Yan
-
Patent number: 12033372Abstract: Systems, methods and non-transitory computer readable media for attributing generated visual content to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be associated with a plurality of training examples. Each training example may be associated with a visual content. Properties of the first visual content may be determined. Each visual content associated with a training example may be analyzed to determine properties of the visual content. The properties of the first visual content and the properties of the visual contents associated with the plurality of training examples may be used to attribute the first visual content to a subgroup of the plurality of training examples. The visual contents associated with the training examples of the subgroup may be associated with a source. A data-record associated with the source may be updated based on the attribution.Type: GrantFiled: December 6, 2023Date of Patent: July 9, 2024Assignee: BRIA ARTIFICIAL INTELLIGENCE LTDInventors: Yair Adato, Ran Achituv, Eyal Gutflaish, Dvir Yerushalmi
-
Patent number: 12014278Abstract: The group of inventions relates to technologies for automated prediction of user data: actions and features using a predictive model. The technical result is to increase the efficiency of predicting user data. A method for automated prediction of user data is proposed. The method comprises the step of obtaining, by at least one processing unit, user action features, represented as an array of first vectors. Further, the method comprises obtaining user features represented as an array of second user feature vectors. Also, training neural network model on said arrays of first vectors and second vectors of features using an error backpropagation method to obtain trained model the output of which generates first and second latent state feature vectors, wherein said trainable neural network model is configured to dynamically select an architecture depending on said first and second feature vectors.Type: GrantFiled: December 31, 2023Date of Patent: June 18, 2024Assignee: LEMON ARTIFICIAL INTELLIGENCE LTDInventor: Rodion Potemkin
-
Patent number: 11947922Abstract: Systems, methods and non-transitory computer readable media for prompt-based attribution of generated media contents to training examples are provided. In some examples, a first media content generated using a generative model in response to a first textual input may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may include a respective textual content and a respective media content. Properties of the first textual input and properties of the textual contents included in the plurality of training examples may be used to attribute the first media content to a first subgroup of the plurality of training examples. The training examples of the first subgroup may be associated with a source. Further, a data-record associated with the source may be updated based on the attribution.Type: GrantFiled: November 7, 2023Date of Patent: April 2, 2024Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Michael Feinstein, Efrat Taig, Dvir Yerushalmi, Ori Liberman
-
Patent number: 11934792Abstract: Systems, methods and non-transitory computer readable media for identifying prompts used for training of inference models are provided. In some examples, a specific textual prompt in a natural language may be received. Further, data based on at least one parameter of an inference model may be accessed. The inference model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may include a respective textual content and a respective media content. The data and the specific textual prompt may be analyzed to determine a likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples. A digital signal indicative of the likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples may be generated.Type: GrantFiled: November 7, 2023Date of Patent: March 19, 2024Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Michael Feinstein, Efrat Taig, Dvir Yerushalmi, Ori Liberman
-
Patent number: 11915348Abstract: Systems, methods and non-transitory computer readable media for optimizing visual contents are provided. A particular mathematical object corresponding to a particular visual content in a mathematical space including a plurality of mathematical objects corresponding to visual contents may be determined. The mathematical space and the particular mathematical object may be used to obtain first and second mathematical objects of the plurality of mathematical objects. The visual content corresponding to the first mathematical object may be used in a communication with a first user and the visual content corresponding to the second mathematical object may be used in a communication with a second user. Indications of the reactions of the first and second users to the communications may be received. A third visual content may be obtained based on the reactions. The third visual content may be used in a communication with a third user.Type: GrantFiled: November 4, 2021Date of Patent: February 27, 2024Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Gal Jacobi, Ori Feldstein, Bar Fingerman
-
Patent number: 11880917Abstract: Systems, methods and non-transitory computer readable media for generating and modifying synthetic visual content using textual input are provided. One or more keywords may be received from a user. The one or more keywords may be used to generate a plurality of textual descriptions. Each generated textual description may correspond to a possible visual content. The generated plurality of textual descriptions may be presented to the user through a user interface that enables the user to modify the presented textual descriptions. A modification to at least one of the plurality of textual descriptions may be received from the user, therefore obtaining a modified plurality of textual descriptions. A selection of one textual description of the modified plurality of textual descriptions may be received from the user. A plurality of visual contents corresponding to the selected textual description may be presented to the user.Type: GrantFiled: November 4, 2021Date of Patent: January 23, 2024Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Gal Jacobi
-
Patent number: 11854129Abstract: Systems, methods and non-transitory computer readable media for generating visual content consistent with aspects of a visual brand language are provided. An indication of at least one aspect of a visual brand language may be received. Further, an indication of a desired visual content may be received. A new visual content consistent with the visual brand language and corresponding to the desired visual content may be generated based on the indication of the at least one aspect of the visual brand language and the indication of the desired visual content. The new visual content may be provided in a format ready for presentation.Type: GrantFiled: November 4, 2021Date of Patent: December 26, 2023Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Gal Jacobi
-
Patent number: 11769283Abstract: Systems, methods and non-transitory computer readable media for generating looped video clips are provided. A still image may be received. The still image may be analyzed to generate a series of images. The series of images may include at least first, middle and last images. The first image may be substantially visually similar to the last image, and the middle image may be visually different from the first and last images. The series of images may be provided. Playing the series of images in a video clip that starts with the first image and finishes with the last image, and repeating the video clip from the first image immediately after completing the playing of the video clip with the last image may create visually smooth transaction in which the transition from the last image to the first image is visually indistinguishable from the transactions between frames within the video clip.Type: GrantFiled: November 4, 2021Date of Patent: September 26, 2023Assignee: BRIA ARTIFICIAL INTELLIGENCE LTD.Inventors: Yair Adato, Gal Jacobi, Dvir Yerushalmi, Efrat Taig
-
Patent number: 11556581Abstract: This disclosure relates to improved sketch-based image retrieval (SBIR) techniques. The SBIR techniques utilize a neural network architecture to train a domain migration function and a hashing function. The domain migration function is configured to transform sketches into synthetic images, and the hashing function is configured to generate hash codes from synthetic images and authentic images in a manner that preserves semantic consistency across the sketch and image domains. The hash codes generated from the synthetic images can be used for accurately identifying and retrieving authentic images corresponding to sketch queries, or vice versa.Type: GrantFiled: September 4, 2018Date of Patent: January 17, 2023Assignee: INCEPTION INSTITUTE OF ARTIFICIAL INTELLIGENCE, LTD.Inventors: Jingyi Zhang, Fumin Shen, Li Liu, Fan Zhu, Mengyang Yu, Ling Shao, Heng Tao Shen
-
Patent number: 11294623Abstract: Systems and methods for personalized quality assurance of inference models are provided. For example, data items associated with a group of devices may be obtained, results of applying the data items to inference models may be obtained, the results of applying the data items to a first inference model may be compared with the results of applying the data items to a second inference model, and the compatibility of the second inference model to the group of devices may be assessed, for example based on the comparison results. In some examples, when the second inference model is found compatible, the second inference model may be utilized in tasks associated with the group of devices. In some examples, when the second inference model is found incompatible, the system may forgo the usage of the second inference model in one or more tasks associated with the group of devices.Type: GrantFiled: July 30, 2018Date of Patent: April 5, 2022Assignee: ALLERO ARTIFICIAL INTELLIGENCE LTDInventors: Moshe Guttmann, Ariel Yossef Biller, Dan Iosef Malowany
-
Publication number: 20220083868Abstract: A neural network training method comprises: inputting training data into trained first neural network and second neural network to be trained; determining first feature map output by a preset layer of the first neural network and second feature map output by the second neural network at the preset layer; determining a first loss function value of the second neural network on the basis of the first feature map and the second feature map; updating parameters of the second neural network on the basis of the first loss function value and a second loss function value of the second neural network; and taking the updated parameters of the second neural network as initial parameters of the second neural network to be trained, updating the parameters of the second neural network in an iterative manner, and if the updated second neural network meets a preset condition, obtaining final trained second neural network.Type: ApplicationFiled: August 16, 2019Publication date: March 17, 2022Applicant: NANJING INSTITUTE OF ADVANCED ARTIFICIAL INTELLIGENCE, LTD.Inventors: Helong ZHOU, Qian ZHANG, Chang HUANG
-
Publication number: 20220012909Abstract: Disclosed are camera pose determination methods and apparatuses. The method includes determining first pixels in a current image and second pixels in a previous image, determining second pixel points with the preconfigured semantics in a previous image frame before the current image frame, the first pixel points corresponding to at least a portion of the second pixel points, determining an error between the first pixel points and the second pixel points, and a camera pose change value of the current image frame relative to the previous image frame based on the error, and determining a camera pose of the current image based on a camera pose of the previous image and the camera pose change. Related devices and storage media are also disclosed.Type: ApplicationFiled: August 5, 2019Publication date: January 13, 2022Applicant: NANJING INSTITUTE OF ADVANCED ARTIFICIAL INTELLIGENCE, LTD.Inventor: Qinrui Yan