Inventor

KRISHNAMURTHY BALAJI

IN91 patents

⚠️ This page may combine multiple inventors who share the name “KRISHNAMURTHY BALAJI”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

KRISHNAMURTHY BALAJI

ADOBE INC

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

Systems and methods of training neural networks against adversarial attacks

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

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

Global vector recommendations based on implicit interaction and profile data

Form structure extraction network

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

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

Form structure extraction by predicting associations

Image generation and editing with latent transformation detection

Using intrinsic multimodal features of image for domain generalized

Interactive search experience using machine learning

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

Interactive search experience using machine learning

Generating commonsense context for text using knowledge graphs

Language model with external knowledge base

Attributionally robust training for weakly supervised localization and segmentation

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

Machine-learning based multi-step engagement strategy modification

Cloth warping using multi-scale patch adversarial loss

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

Classification training techniques to map datasets to a standardized data model

Generating a shoppable video

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

Content analytics as part of content creation

Rule determination for black-box machine-learning models

Behavioral prediction for targeted end users

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

Caption association techniques

Introspection network for training neural networks

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

Content analytics as part of content creation

Conversational agent for search

Form structure extraction by predicting associations

Systems and methods of training neural networks against adversarial attacks

Machine learning model interpretation

Automated digital asset tagging using multiple vocabulary sets

Attributionally robust training for weakly supervised localization and segmentation

Clustering product media files

Non-adversarial image generation using transfer learning

Utilizing implicit neural representations to parse visual components of subjects depicted within visual content

ADOBE SYSTEMS INC

Deep-learning network architecture for object detection

Behavioral prediction for targeted end users

Deep-learning network architecture for object detection

Identifying significant anomalous segments of a metrics dataset

RASTOGI ANUBHA

Refinement of depth maps by fusion of multiple estimates

Method and apparatus for normalizing perceptual quality in media compression

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

KRISHNAMURTHY BALAJI

Method and apparatus for indexing a video stream

TEXACO INC

Vaporizer and methods relating to same