Patents Assigned to Adobe Inc.
-
Publication number: 20240362941Abstract: A corrective noise system receives an electronic version of a fillable form generated by a segmentation network and receives a correction to a segmentation error in the electronic version of the fillable form. The corrective noise system is trained to generate noise that represents the correction and superimpose the noise on the fillable form. The corrective noise system is further trained to identify regions in a corpus of forms that are semantically similar to a region that was subject to the correction. The generated noise is propagated to the semantically similar regions in the corpus of forms and the noisy corpus of forms is provided as input to the segmentation network. The noise causes the segmentation network to accurately identify fillable regions in the corpus of forms and output a segmented version of the corpus of forms having improved fidelity without retraining or otherwise modifying the segmentation network.Type: ApplicationFiled: April 27, 2023Publication date: October 31, 2024Applicant: Adobe Inc.Inventors: Silky Singh, Surgan Jandial, Shripad Vilasrao Deshmukh, Milan Aggarwal, Mausoom Sarkar, Balaji Krishnamurthy, Arneh Jain, Abhinav Java
-
Publication number: 20240364683Abstract: A plugin authorization workflow for web applications is described. A plugin makes a request for an authorization token. An authorization provider module receives the request and displays a user interface (UI) to receive an input for approving execution of the plugin. A target authorization system receives the approval and generates an authorization code which is communicated to the authorization provider module and back to the plugin. The plugin directly calls the target authorization system with the authorization code. In return, the target authorization system sends an authorization token back to the plugin allowing execution of the plugin.Type: ApplicationFiled: April 28, 2023Publication date: October 31, 2024Applicant: Adobe Inc.Inventors: Tarun Garg, Abhishek Das
-
Publication number: 20240362821Abstract: In implementations of systems for generating image metadata using a compact color space, a computing device implements a color system to receive input data describing pixels of a digital image and corresponding RGB values of the pixels. The color system assigns a color of a compact color space to each of the pixels based on the corresponding RGB values of the pixels. The compact color space includes a subset of colors included in an RGB color space. The color system computes a histogram of colors of the compact color space and determines a particular color of the compact color space based on the histogram. The color system generates color metadata for the digital image describing a natural language name of the particular color of the compact color space.Type: ApplicationFiled: April 27, 2023Publication date: October 31, 2024Applicant: Adobe Inc.Inventors: Nimish Srivastav, Shankar Venkitachalam, Satya Deep Maheshwari, Mihir Naware, Deepak Pai
-
Publication number: 20240362427Abstract: In implementations of systems for generating digital content, a computing device implements a generation system to receive a user input specifying a characteristic for digital content. The generation system generates input text based on the characteristic for processing by a first machine learning model. Output text generated by the first machine learning model based on processing the input text is received. The output text describes a digital content component. The generation system generates the digital content component by processing the output text using a second machine learning model. The generation system generates the digital content including the digital content component for display in a user interface based on the characteristic.Type: ApplicationFiled: April 28, 2023Publication date: October 31, 2024Applicant: Adobe Inc.Inventors: Mukul Gupta, Yaman Kumar, Rahul Gupta, Prerna Bothra, Mayur Hemani, Mayank Gupta, Gaurav Makkar
-
Patent number: 12130850Abstract: Techniques and systems are described for performing semantic text searches. A semantic text-searching solution uses a machine learning system (such as a deep learning system) to determine associations between the semantic meanings of words. These associations are not limited by the spelling, syntax, grammar, or even definition of words. Instead, the associations can be based on the context in which characters, words, and/or phrases are used in relation to one another. In response to detecting a request to locate text within an electronic document associated with a keyword, the semantic text-searching solution can return strings within the document that have matching and/or related semantic meanings or contexts, in addition to exact matches (e.g., string matches) within the document. The semantic text-searching solution can then output an indication of the matching strings.Type: GrantFiled: December 29, 2022Date of Patent: October 29, 2024Assignee: Adobe Inc.Inventors: Trung Bui, Yu Gong, Tushar Dublish, Sasha Spala, Sachin Soni, Nicholas Miller, Joon Kim, Franck Dernoncourt, Carl Dockhorn, Ajinkya Kale
-
Patent number: 12130876Abstract: Systems and methods for dynamic user profile projection are provided. One or more aspects of the systems and methods includes computing, by a prediction component, a predicted number of lookups for a future time period based on a lookup history of a user profile using a lookup prediction model; comparing, by the prediction component, the predicted number of lookups to a lookup threshold; and transmitting, by a projection component, the user profile to an edge server based on the comparison.Type: GrantFiled: October 24, 2022Date of Patent: October 29, 2024Assignee: ADOBE INC.Inventors: Nathan Ng, Tung Mai, Thomas Greger, Kelly Quinn Nicholes, Antonio Cuevas, Saayan Mitra, Somdeb Sarkhel, Anup Bandigadi Rao, Ryan A. Rossi, Viswanathan Swaminathan, Shivakumar Vaithyanathan
-
Patent number: 12131421Abstract: A method for generating a volume for three-dimensional rendering extracts a plurality of images from a source image input, normalizes the extracted images to have a common pixel size, and determines a notional camera placement for each normalized image to obtain a plurality of annotated normalized images, each annotated with a respective point of view through the view frustum of the notional camera. From the annotated normalized images, the method generates a first volume encompassing a first three-dimensional representation of the target object and selects a smaller subspace within the first volume that encompasses the first three-dimensional representation of the target object. The method generates, from the annotated normalized images, a second volume overlapping the first volume, encompassing a second three-dimensional representation of the target object and having a plurality of voxels, and crops the second volume to limit the second volume to the subspace.Type: GrantFiled: December 19, 2022Date of Patent: October 29, 2024Assignee: Adobe Inc.Inventors: Kowsheek Mahmood, Kevin Roan, David McKinley Cardwell
-
Patent number: 12130841Abstract: A single unified machine learning model (e.g., a neural network) is trained to perform both supervised event predictions and unsupervised time-varying clustering for a sequence of events (e.g., a sequence representing a user behavior) using sequences of events for multiple users using a combined loss function. The unified model can then be used for, given a sequence of events as input, predict a next event to occur after the last event in the sequence and generate a clustering result by performing a clustering operation on the sequence of events. As part of predicting the next event, the unified model is trained to predict an event type for the next event and a time of occurrence for the next event. In certain embodiments, the unified model is a neural network comprising a recurrent neural network (RNN) such as an Long Short Term Memory (LSTM) network.Type: GrantFiled: July 20, 2020Date of Patent: October 29, 2024Assignee: Adobe Inc.Inventors: Karan Aggarwal, Georgios Theocharous, Anup Rao
-
Patent number: 12131350Abstract: Techniques are disclosed for real-time bidding (e.g., for dynamic online content placement) using an optimized final bid. The final bid is determined based on a predicted clearing price and an initial bid. The initial bid represents a value to a prospective content provider, and may be computed based on campaign information. The predicted clearing price is a predicted amount paid, and may be predicted using a model trained using historical winning bids data. The clearing price may be predicted using a quantile regression model, where the quantile can be selected to control bid aggressiveness. In some cases, the quantile is determined based on pacing in an overall campaign. Once the initial bid and the predicted clearing price are calculated, the final bid is computed based on the initial bid and the predicted clearing price.Type: GrantFiled: August 16, 2021Date of Patent: October 29, 2024Assignee: Adobe Inc.Inventors: Somdeb Sarkhel, Saayan Mitra, Jiatong Xie, Alok Kothari
-
Patent number: 12131418Abstract: Graphics processing unit instancing control techniques are described that overcome conventional challenges to expand functionality made available via a graphics processing unit. In one example, these techniques support ordering of primitives within respective instances of a single draw call made to a graphics processing unit. This is performed by ordering primitives within respective instances that correspond to polygons for rendering. The ordering of the primitives overcomes limitations of conventional techniques and reduces visual artifacts through support of correct overlaps and z-ordering of instances.Type: GrantFiled: May 11, 2022Date of Patent: October 29, 2024Assignee: Adobe Inc.Inventor: Harish Kumar
-
Patent number: 12131451Abstract: In implementations of systems for spatially coherent UV packing, a computing device implements a packing system to identify pairs of boundary vertices of different two-dimensional islands included in a set of two-dimensional islands. A first boundary vertex and a second boundary vertex of the pairs of boundary vertices both correspond to a same three-dimensional coordinate of a three-dimensional mesh. The packing system determines transformations for two-dimensional islands included in the set of two-dimensional islands based on distances between the first boundary vertex and the second boundary vertex of the pairs of boundary vertices. A three-dimensional object is generated for display in a user interface based on the transformations and the three-dimensional mesh.Type: GrantFiled: July 25, 2022Date of Patent: October 29, 2024Assignee: Adobe Inc.Inventors: Artem Bishev, Jean-François El Hajjar
-
Publication number: 20240354994Abstract: In implementation of automated colorimetry techniques supporting color classification, a computing device implements a color coordination system to receive a digital image depicting a person. The color coordination system then identifies a color classification for the person based on the digital image, the color classification associated with a color recommendation that is represented as a color distribution. The color coordination system identifies an item associated with a color of the color recommendation by identifying a point of the color distribution associated with a color of the item that is within a threshold distance from a point associated with the color of the color recommendation. Then, the color coordination system displays a recommendation that includes the item in a user interface.Type: ApplicationFiled: April 20, 2023Publication date: October 24, 2024Applicant: Adobe Inc.Inventors: Jose Ignacio Echevarria Vallespi, Michelle Mee-June Lee, Jacob Benjamin Hanson-regalado, Irgelkha Mejia
-
Publication number: 20240354331Abstract: Digital image hash search techniques are described. These techniques leverage clusters formed from digital image hashes that overcome limitations and computational resource consumption of conventional clustering techniques used to implement a digital image search. In an example, search techniques employ two search stages. In a first stage, clusters are identified based on the cluster centers using a distance measure. The second stage involves a comparison of cluster hashes within the identified cluster with the search query hash until the distance measure is reached.Type: ApplicationFiled: April 19, 2023Publication date: October 24, 2024Applicant: Adobe Inc.Inventor: Martin Schmitz
-
Publication number: 20240355020Abstract: In implementations of systems for digital content analysis, a computing device implements an analysis system to extract a first content component and a second content component from digital content to be analyzed based on content metrics. The analysis system generates first embeddings using a first machine learning model and second embedding using a second machine learning model. The first embeddings and the second embeddings are combined as concatenated embeddings. The analysis system generates an indication of a content metric for display in a user interface using a third machine learning model based on the concatenated embeddings.Type: ApplicationFiled: April 21, 2023Publication date: October 24, 2024Applicant: Adobe Inc.Inventors: Yaman Kumar, Somesh Singh, Seoyoung Park, Pranjal Prasoon, Nithyakala Sainath, Nisarg Shailesh Joshi, Nikitha Srikanth, Nikaash Puri, Milan Aggarwal, Jayakumar Subramanian, Ganesh Palwe, Balaji Krishnamurthy, Matthew William Rozen, Mihir Naware, Hyman Chung
-
Patent number: 12124497Abstract: Form structure similarity detection techniques are described. A content processing system, for instance, receives a query snippet that depicts a query form structure. The content processing system generates a query layout string that includes semantic indicators to represent the query form structure and generates candidate layout strings that represent form structures from a target document. The content processing system calculates similarity scores between the query layout string and the candidate layout strings. Based on the similarity scores, the content processing system generates a target snippet for display that depicts a form structure that is structurally similar to the query form structure. The content processing system is further operable to generate a training dataset that includes image pairs of snippets depicting form structures that are structurally similar.Type: GrantFiled: March 27, 2023Date of Patent: October 22, 2024Assignee: Adobe Inc.Inventors: Abhinav Java, Surgan Jandial, Shripad Vilasrao Deshmukh, Milan Aggarwal, Mausoom Sarkar, Balaji Krishnamurthy, Arneh Jain
-
Patent number: 12124539Abstract: 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.Type: GrantFiled: June 23, 2023Date of Patent: October 22, 2024Assignee: Adobe Inc.Inventors: Arshiya Aggarwal, Sanjeev Tagra, Sachin Soni, Ryan Rozich, Prasenjit Mondal, Jonathan Roeder, Ajay Jain
-
Patent number: 12124508Abstract: Systems and methods for intent discovery and video summarization are described. Embodiments of the present disclosure receive a video and a transcript of the video, encode the video to obtain a sequence of video encodings, encode the transcript to obtain a sequence of text encodings, apply a visual gate to the sequence of text encodings based on the sequence of video encodings to obtain gated text encodings, and generate an intent label for the transcript based on the gated text encodings.Type: GrantFiled: July 12, 2022Date of Patent: October 22, 2024Assignee: ADOBE INC.Inventors: Adyasha Maharana, Quan Hung Tran, Seunghyun Yoon, Franck Dernoncourt, Trung Huu Bui, Walter W. Chang
-
Patent number: 12125138Abstract: Embodiments are disclosed for optimizing a material graph for replicating a material of the target image. Embodiments include receiving a target image and a material graph to be optimized for replicating a material of the target image. Embodiments include identifying a non-differentiable node of the material graph, the non-differentiable node including a set of input parameters. Embodiments include selecting a differentiable proxy from a library of the selected differentiable proxy is trained to replicate an output of the identified non-differentiable node. Embodiments include generating an optimized input parameters for the identified non-differentiable node using the corresponding trained neural network and the target image. Embodiments include replacing the set of input parameters of the non-differentiable node of the material graph with the optimized input parameters.Type: GrantFiled: July 14, 2022Date of Patent: October 22, 2024Assignee: Adobe Inc.Inventors: Valentin Deschaintre, Yiwei Hu, Paul Guerrero, Milos Hasan
-
Patent number: 12124565Abstract: Techniques are provided for detecting executable application that is subjected to tampering or unauthorized modification. A checksum for a portion of the executable application is computed at a run time of the executable application by a tamper detection module encoded in the executable application. The tamper detection module compares the checksum to a pre-determined hash value for the portion of the executable application. If the checksum is different from the hash value, the executable application has been tampered with or otherwise modified. The tamper detection module can then cause an alert to be sent to the user and/or the software vendor indicating that the executable application is not genuine.Type: GrantFiled: March 19, 2021Date of Patent: October 22, 2024Assignee: Adobe Inc.Inventors: Pratuish Ayanour Veettikattil, Vikrant Pundir, Vinu C. Warrier
-
Patent number: 12124948Abstract: In some embodiments, a computing system computes, with a state prediction model, probabilities of transitioning from a click state represented by interaction data to various predicted next states. The computing system computes an interface experience metric for the click with an experience valuation model. To do so, the computing system identifies base values for the click state and the predicted next states. The computing system computes value differentials for between the click state's base value and each predicted next state's base value. Value differentials indicate qualities of interface experience. The computing system determines the interface experience metric from a summation that includes the current click state's base value and the value differentials weighted with the predicted next states' probabilities.Type: GrantFiled: April 21, 2021Date of Patent: October 22, 2024Assignee: ADOBE INC.Inventors: Atanu R. Sinha, Deepali Jain, Nikhil Sheoran, Deepali Gupta, Sopan Khosla