Balaji Krishnamurthy

DIGITAL CONTENT ANALYSIS

CONTENT RELEVANCE BASED TABLE QUERY ANSWERING

CONTENT RELEVANCE BASED TABLE QUERY ANSWERING

PERSONALIZED FORM ERROR CORRECTION PROPAGATION

GENERATING ALTERNATIVE EXAMPLES FOR CONTENT

GENERATING IMAGE OBJECT SEGMENTATIONS UTILIZING GRAPH-CUT PARTITIONING IN SELF-SUPERVISED OBJECT DISCOVERY

MIX AND MATCH HUMAN IMAGE GENERATION

DIGITAL IMAGE REPOSING BASED ON MULTIPLE INPUT VIEWS

ONE-SHOT DOCUMENT SNIPPET SEARCH

DIGITAL IMAGE REPOSING TECHNIQUES

TRAJECTORY-BASED EXPLAINABILITY FRAMEWORK FOR REINFORCEMENT LEARNING MODELS

UTILIZING IMPLICIT NEURAL REPRESENTATIONS TO PARSE VISUAL COMPONENTS OF SUBJECTS DEPICTED WITHIN VISUAL CONTENT

PERSONALIZED FORM ERROR CORRECTION PROPAGATION

DIGITAL CONTENT ANALYSIS

Content analytics as part of content creation

Form structure similarity detection

SYSTEMS AND METHODS FOR MACHINE LEARNING TRANSFERABILITY

KNOWLEDGE DISTILLATION USING CONTEXTUAL SEMANTIC NOISE

NON-ADVERSARIAL IMAGE GENERATION USING TRANSFER LEARNING

SYSTEMS AND METHODS FOR DATA AUGMENTATION

ATTENTION AWARE MULTI-MODAL MODEL FOR CONTENT UNDERSTANDING

Language model with external knowledge base

REGULARIZING TARGETS IN MODEL DISTILLATION UTILIZING PAST STATE KNOWLEDGE TO IMPROVE TEACHER-STUDENT MACHINE LEARNING MODELS

Content analytics as part of content creation

Optimal sequential decision making with changing action space

Generating images for virtual try-on and pose transfer

VISUAL SPEECH RECOGNITION FOR DIGITAL VIDEOS UTILIZING GENERATIVE ADVERSARIAL LEARNING

System and methods for neural topic modeling using topic attention networks

Generating trained neural networks with increased robustness against adversarial attacks

Systems and methods of training neural networks against adversarial attacks

Identifying digital attributes from multiple attribute groups utilizing a deep cognitive attribution neural network

Systems and methods of training neural networks against adversarial attacks

Interactive search experience using machine learning

Generating a data visualization graph utilizing modularity-based manifold tearing

Compressing digital images utilizing deep perceptual similarity

Image generation and editing with latent transformation detection

Compressing digital images utilizing deep learning-based perceptual similarity

Providing insights and suggestions for journeys

Similarity propagation for one-shot and few-shot image segmentation

Generating varied-scale visualizations of multi-dimensional data

Generating a high-dimensional network graph for data visualization utilizing landmark data points and modularity-based manifold tearing

Machine-learning based multi-step engagement strategy modification

Model training with retrospective loss

Accurately generating virtual try-on images utilizing a unified neural network framework

Cloth warping using multi-scale patch adversarial loss

Classifying digital images in few-shot tasks based on neural networks trained using manifold mixup regularization and self-supervision

Generating combined feature embedding for minority class upsampling in training machine learning models with imbalanced samples

Identifying digital attributes from multiple attribute groups within target digital images utilizing a deep cognitive attribution neural network

Computer storage media, method, and system for exploring and recommending matching products across categories

Interactive search experience using machine learning

Personalized dynamic content via content tagging and transfer learning

Generating varied-scale topological visualizations of multi-dimensional data

Classifying structural features of a digital document by feature type using machine learning

Generating trained neural networks with increased robustness against adversarial attacks

Graphical interface for presentation of interaction data across multiple webpage configurations

Machine learning-based generation of target segments

Machine-learning based multi-step engagement strategy generation and visualization

Machine-learning based multi-step engagement strategy generation and visualization

Machine-learning based multi-step engagement strategy modification

Generating a shoppable video

USING NATURAL LANGUAGE PROCESSING AND DEEP LEARNING FOR MAPPING ANY SCHEMA DATA TO A HIERARCHICAL STANDARD DATA MODEL (XDM)

Caption association techniques

Using deep learning techniques to determine the contextual reading order in a form document

Machine learning model interpretation

Rule determination for black-box machine-learning models

Behavioral prediction for targeted end users

Global vector recommendations based on implicit interaction and profile data

DIGITAL EXPERIENCE TARGETING USING BAYESIAN APPROACH

Form structure extraction network

Classification training techniques to map datasets to a standardized data model

Automated digital asset tagging using multiple vocabulary sets

Introspection network for training neural networks

Facilitating machine-learning and data analysis by computing user-session representation vectors

Deep-learning network architecture for object detection

Clustering product media files

Learning vector-space representations of items for recommendations using word embedding models

Deep-learning network architecture for object detection

Deconstructed video units

Method and apparatus for clustering product media files

Behavioral prediction for targeted end users

Generating a shoppable video

Method and apparatus for indexing a video stream

Refinement of depth maps by fusion of multiple estimates

Robust fitting of surfaces from noisy data

Method and apparatus for normalizing perceptual quality in media compression

Method and system to generate a compressed image utilizing custom probability tables

Transferring the look of an image

Method and apparatus for predicting the size of a compressed signal