Patents by Inventor Balaji Krishnamurthy

Balaji Krishnamurthy 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: 20220309093
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group).
    Type: Application
    Filed: June 14, 2022
    Publication date: September 29, 2022
    Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
  • Publication number: 20220292356
    Abstract: Embodiments disclosed herein describe systems, methods, and products that generate trained neural networks that are robust against adversarial attacks. During a training phase, an illustrative computer may iteratively optimize a loss function that may include a penalty for ill-conditioned weight matrices in addition to a penalty for classification errors. Therefore, after the training phase, the trained neural network may include one or more well-conditioned weight matrices. The one or more well-conditioned weight matrices may minimize the effect of perturbations within an adversarial input thereby increasing the accuracy of classification of the adversarial input. By contrast, conventional training approaches may merely reduce the classification errors using backpropagation, and, as a result, any perturbation in an input is prone to generate a large effect on the output.
    Type: Application
    Filed: June 3, 2022
    Publication date: September 15, 2022
    Inventors: Mayank SINGH, Abhishek SINHA, Balaji KRISHNAMURTHY
  • Publication number: 20220245141
    Abstract: An interactive search session is implemented using an artificial intelligence model. For example, when the artificial intelligence model receives a search query from a user, the model selects an action from a plurality of actions based on the search query. The selected action queries the user for more contextual cues about the search query (e.g., may enquire about use of the search results, may request to refine the search query, or otherwise engage the user in conversation to better understand the intent of the search). The interactive search session may be in the form, for example, of a chat session between the user and the system, and the chat session may be displayed along with the search results (e.g., in a separate section of display). The interactive search session may enable the system to better understand the user's search needs, and accordingly may help provide more focused search results.
    Type: Application
    Filed: March 28, 2022
    Publication date: August 4, 2022
    Applicant: Adobe Inc.
    Inventors: Milan Aggarwal, Balaji Krishnamurthy
  • Publication number: 20220230369
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate interactive visual shape representation of digital datasets. For example, the disclosed systems can generate an augmented nearest neighbor network graph from a sampled subset of digital data points using a nearest neighbor model and witness complex model. The disclosed system can further generate a landmark network graph based on the augmented nearest neighbor network graph utilizing a plurality of random walks. The disclosed systems can also generate a loop-augmented spanning network graph based on a partition of the landmark network graph by adding community edges between communities of landmark groups based on modularity and to complete community loops. Based on the loop-augmented spanning network graph, the disclosed systems can generate an interactive visual shape representation for display on a client device.
    Type: Application
    Filed: March 30, 2022
    Publication date: July 21, 2022
    Inventors: Nupur Kumari, Piyush Gupta, Akash Rupela, Siddarth R, Balaji Krishnamurthy
  • Publication number: 20220224680
    Abstract: Local data can be made available in a cloud computing environment. A persistent remote connection may be established between a processor and a server. The server may receive a request for data from an external device through a network. The request for data may be sent through the persistent remote connection from the server to a first executable process of the processor. The processor may obtain the data from an application being executed by the processor separately from the first executable process. The data may be sent through the persistent remote connection from the processor to the server. The server may send the data to the external device through the network in response to the request. The persistent remote connection may be maintained in an open state regardless of a status of the request for data.
    Type: Application
    Filed: January 8, 2021
    Publication date: July 14, 2022
    Applicant: INTUIT INC.
    Inventors: Punam Goswami, Reetesh Agrawal, Bharath Raj Holenarasipura Rajanna, Deep George Zachariah, Hitesh Gaba, Amrut Anegundi, Amudhavani Haridoss, Balaji Krishnamurthy
  • Patent number: 11386144
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for generating tags for an object portrayed in a digital image based on predicted attributes of the object. For example, the disclosed systems can utilize interleaved neural network layers of alternating inception layers and dilated convolution layers to generate a localization feature vector. Based on the localization feature vector, the disclosed systems can generate attribute localization feature embeddings, for example, using some pooling layer such as a global average pooling layer. The disclosed systems can then apply the attribute localization feature embeddings to corresponding attribute group classifiers to generate tags based on predicted attributes. In particular, attribute group classifiers can predict attributes as associated with a query image (e.g., based on a scoring comparison with other potential attributes of an attribute group).
    Type: Grant
    Filed: September 9, 2019
    Date of Patent: July 12, 2022
    Assignee: Adobe Inc.
    Inventors: Ayush Chopra, Mausoom Sarkar, Jonas Dahl, Hiresh Gupta, Balaji Krishnamurthy, Abhishek Sinha
  • Publication number: 20220198717
    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.
    Type: Application
    Filed: March 11, 2022
    Publication date: June 23, 2022
    Inventors: Meet Patel, Mayur Hemani, Karanjeet Singh, Amit Gupta, Apoorva Gupta, Balaji Krishnamurthy
  • Patent number: 11367271
    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for one-shot and few-shot image segmentation on classes of objects that were not represented during training. In some embodiments, a dual prediction scheme may be applied in which query and support masks are jointly predicted using a shared decoder, which aids in similarity propagation between the query and support features. Additionally or alternatively, foreground and background attentive fusion may be applied to utilize cues from foreground and background feature similarities between the query and support images. Finally, to prevent overfitting on class-conditional similarities across training classes, input channel averaging may be applied for the query image during training. Accordingly, the techniques described herein may be used to achieve state-of-the-art performance for both one-shot and few-shot segmentation tasks.
    Type: Grant
    Filed: June 19, 2020
    Date of Patent: June 21, 2022
    Assignee: Adobe Inc.
    Inventors: Mayur Hemani, Siddhartha Gairola, Ayush Chopra, Balaji Krishnamurthy, Jonas Dahl
  • Patent number: 11354590
    Abstract: Rule determination for black-box machine-learning models (BBMLMs) is described. These rules are determined by an interpretation system to describe operation of a BBMLM to associate inputs to the BBMLM with observed outputs of the BBMLM and without knowledge of the logic used in operation by the BBMLM to make these associations. To determine these rules, the interpretation system initially generates a proxy black-box model to imitate the behavior of the BBMLM based solely on data indicative of the inputs and observed outputs—since the logic actually used is not available to the system. The interpretation system generates rules describing the operation of the BBMLM by combining conditions—identified based on output of the proxy black-box model—using a genetic algorithm. These rules are output as if-then statements configured with an if-portion formed as a list of the conditions and a then-portion having an indication of the associated observed output.
    Type: Grant
    Filed: November 14, 2017
    Date of Patent: June 7, 2022
    Assignee: Adobe Inc.
    Inventors: Piyush Gupta, Sukriti Verma, Pratiksha Agarwal, Nikaash Puri, Balaji Krishnamurthy
  • Patent number: 11335033
    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.
    Type: Grant
    Filed: September 25, 2020
    Date of Patent: May 17, 2022
    Assignee: Adobe Inc.
    Inventors: Meet Patel, Mayur Hemani, Karanjeet Singh, Amit Gupta, Apoorva Gupta, Balaji Krishnamurthy
  • Publication number: 20220138897
    Abstract: This disclosure includes technologies for image processing, particularly for image generation and editing in a configurable semantic direction. A generative adversarial network is trained with an auxiliary network with an auxiliary task that is designed to disentangle the latent space of the generative adversarial network. Resultantly, a new type of GAN is created to improve image generation or editing in both conditional and unconditional settings.
    Type: Application
    Filed: November 3, 2020
    Publication date: May 5, 2022
    Inventors: Mayank Singh, Parth Patel, Nupur Kumari, Balaji Krishnamurthy
  • Patent number: 11308353
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for training a classification neural network to classify digital images in few-shot tasks based on self-supervision and manifold mixup. For example, the disclosed systems can train a feature extractor as part of a base neural network utilizing self-supervision and manifold mixup. Indeed, the disclosed systems can apply manifold mixup regularization over a feature manifold learned via self-supervised training such as rotation training or exemplar training. Based on training the feature extractor, the disclosed systems can also train a classifier to classify digital images into novel classes not present within the base classes used to train the feature extractor.
    Type: Grant
    Filed: October 23, 2019
    Date of Patent: April 19, 2022
    Assignee: Adobe Inc.
    Inventors: Mayank Singh, Puneet Mangla, Nupur Kumari, Balaji Krishnamurthy, Abhishek Sinha
  • Patent number: 11301506
    Abstract: Automated digital asset tagging techniques and systems are described that support use of multiple vocabulary sets. In one example, a plurality of digital assets are obtained having first-vocabulary tags taken from a first-vocabulary set. Second-vocabulary tags taken from a second-vocabulary set are assigned to the plurality of digital assets through machine learning. A determination is made that at least one first-vocabulary tag includes a plurality of visual classes based on the assignment of at least one second-vocabulary tag. Digital assets are collected from the plurality of digital assets that correspond to one visual class of the plurality of visual classes. The model is generated using machine learning based on the collected digital assets.
    Type: Grant
    Filed: June 29, 2017
    Date of Patent: April 12, 2022
    Assignee: Adobe Inc.
    Inventors: Mayur Hemani, Balaji Krishnamurthy
  • Patent number: 11301761
    Abstract: Behavioral prediction for targeted end users is described. In one or more example embodiments, a computer-readable storage medium has multiple instructions that cause one or more processors to perform multiple operations. Targeted selectstream data is obtained from one or more indications of data object requests corresponding to a targeted end user. A targeted directed graph is constructed based on the targeted selectstream data. A targeted graph feature vector is computed based on one or more invariant features associated with the targeted directed graph. A behavioral prediction is produced for the targeted end user by applying a prediction model to the targeted graph feature vector. In one or more example embodiments, the prediction model is generated based on multiple graph feature vectors respectively corresponding to multiple end users. In one or more example embodiments, a tailored opportunity is determined responsive to the behavioral prediction and issued to the targeted end user.
    Type: Grant
    Filed: January 7, 2019
    Date of Patent: April 12, 2022
    Assignee: Adobe Inc.
    Inventors: Balaji Krishnamurthy, Tushar Singla
  • Patent number: 11295491
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate interactive visual shape representation of digital datasets. For example, the disclosed systems can generate an augmented nearest neighbor network graph from a sampled subset of digital data points using a nearest neighbor model and witness complex model. The disclosed system can further generate a landmark network graph based on the augmented nearest neighbor network graph utilizing a plurality of random walks. The disclosed systems can also generate a loop-augmented spanning network graph based on a partition of the landmark network graph by adding community edges between communities of landmark groups based on modularity and to complete community loops. Based on the loop-augmented spanning network graph, the disclosed systems can generate an interactive visual shape representation for display on a client device.
    Type: Grant
    Filed: April 16, 2020
    Date of Patent: April 5, 2022
    Assignee: Adobe Inc.
    Inventors: Nupur Kumari, Piyush Gupta, Akash Rupela, Siddarth R, Balaji Krishnamurthy
  • Patent number: 11294891
    Abstract: Techniques are disclosed for providing an interactive search session. The interactive search session is implemented using an artificial intelligence model. For example, when the artificial intelligence model receives a search query from a user, the model selects an action from a plurality of actions based on the search query. The selected action queries the user for more contextual cues about the search query (e.g., may enquire about use of the search results, may request to refine the search query, or otherwise engage the user in conversation to better understand the intent of the search). The interactive search session may be in the form, for example, of a chat session between the user and the system, and the chat session may be displayed along with the search results (e.g., in a separate section of display). The interactive search session may enable the system to better understand the user's search needs, and accordingly may help provide more focused search results.
    Type: Grant
    Filed: April 25, 2019
    Date of Patent: April 5, 2022
    Assignee: Adobe Inc.
    Inventors: Milan Aggarwal, Balaji Krishnamurthy
  • Publication number: 20220101564
    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.
    Type: Application
    Filed: September 25, 2020
    Publication date: March 31, 2022
    Inventors: Meet Patel, Mayur Hemani, Karanjeet Singh, Amit Gupta, Apoorva Gupta, Balaji Krishnamurthy
  • Publication number: 20220012530
    Abstract: Embodiments are disclosed for training a neural network classifier to learn to more closely align an input image with its attribution map. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a training image comprising a representation of one or more objects, the training image associated with at least one label for the representation of the one or more objects, generating a perturbed training image based on the training image using a neural network, and training the neural network using the perturbed training image by minimizing a combination of classification loss and attribution loss to learn to align an image with its corresponding attribution map.
    Type: Application
    Filed: July 10, 2020
    Publication date: January 13, 2022
    Inventors: Mayank SINGH, Balaji Krishnamurthy, Nupur KUMARI, Puneet MANGLA
  • Publication number: 20210406935
    Abstract: Methods and systems are provided for generating and providing insights associated with a journey. In embodiments described herein, journey data associated with a journey is obtained. A journey can include journey paths indicating workflows through which audience members can traverse. The journey data can include audience member attributes (e.g., demographics) and labels indicating journey paths traversed by audience members. A set of audience segments are determined that describe a set of audience members traversing a particular journey path. The set of audience segments can be determined using the journey data to train a segmentation model and, thereafter, analyzing the segmentation model to identify patterns that indicate audience segments associated with the particular journey path. An indication of the set of audience segments that describe the set of audience members traversing the particular journey path can be provided for display.
    Type: Application
    Filed: June 24, 2020
    Publication date: December 30, 2021
    Inventors: Pankhri SINGHAI, Piyush GUPTA, Balaji KRISHNAMURTHY, Jayakumar SUBRAMANIAN, Nikaash PURI
  • Publication number: 20210397876
    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for one-shot and few-shot image segmentation on classes of objects that were not represented during training. In some embodiments, a dual prediction scheme may be applied in which query and support masks are jointly predicted using a shared decoder, which aids in similarity propagation between the query and support features. Additionally or alternatively, foreground and background attentive fusion may be applied to utilize cues from foreground and background feature similarities between the query and support images. Finally, to prevent overfitting on class-conditional similarities across training classes, input channel averaging may be applied for the query image during training. Accordingly, the techniques described herein may be used to achieve state-of-the-art performance for both one-shot and few-shot segmentation tasks.
    Type: Application
    Filed: June 19, 2020
    Publication date: December 23, 2021
    Inventors: Mayur Hemani, Siddhartha Gairola, Ayush Chopra, Balaji Krishnamurthy, Jonas Dahl