Inventor

Bui Trung

US36 patents

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

Bui Trung

ADOBE INC

Generating modified digital images utilizing a multimodal selection model based on verbal and gesture input

Utilizing a graph neural network to identify supporting text phrases and generate digital query responses

Utilizing a gated self-attention memory network model for predicting a candidate answer match to a query

Generating dialogue responses in end-to-end dialogue systems utilizing a context-dependent additive recurrent neural network

Generating ground truth annotations corresponding to digital image editing dialogues for training state tracking models

Identification of reading order text segments with a probabilistic language model

Modifying digital images using combinations of direct interactions with the digital images and context-informing speech input

Utilizing bi-directional recurrent encoders with multi-hop attention for speech emotion recognition

Artificial intelligence techniques for performing image editing operations inferred from natural language requests

Scene graph modification based on natural language commands

Methods and systems for determining characteristics of a dialog between a computer and a user

Generating hyper-parameters for machine learning models using modified Bayesian optimization based on accuracy and training efficiency

Utilizing a joint-learning self-distillation framework for improving text sequential labeling machine-learning models

Music driven human dancing video synthesis

Reader-retriever approach for question answering

Utilizing logical-form dialogue generation for multi-turn construction of paired natural language queries and query-language representations

Generating digital annotations for evaluating and training automatic electronic document annotation models

Natural language image editing annotation framework

Perturbation robust metric for evaluating image captions

Performing global image editing using editing operations determined from natural language requests

Generating dialogue responses utilizing an independent context-dependent additive recurrent neural network

Methods and systems for determining characteristics of a dialog between a computer and a user

Generating modified digital images utilizing a dispersed multimodal selection model

Model-based semantic text searching

Model-based semantic text searching

Bi-directional recurrent encoders with multi-hop attention for speech emotion recognition

Multilingual semantic search utilizing meta-distillation learning

Propagating multi-term contextual tags to digital content

Interpretable label-attentive encoder-decoder parser

Generating contextual tags for digital content

Multimodal video summarization

Generating and utilizing classification and query-specific models to generate digital responses to queries from client device

Determining topic chapters for digital videos utilizing a sliding window and video segmentation machine learning models

Semantic reasoning for tabular question answering

Content presentation based on a multi-task neural network

VINBRAIN JOINT STOCK COMPANY

System and method for performing distance metric learning using proxies