Inventor · San Jose, CA, US

Trung Bui

58Patents
5h-index
85Co-inventors
67Inventor score

Filing activity: Jan 20, 2016 → May 3, 2023

Most-cited inventions

PatentTitleAreaCited byStatus
US10817713B2 Generating modified digital images utilizing a multimodal selection model based on verbal and gesture input Physics 28 Active
US10861456B2 Generating dialogue responses in end-to-end dialogue systems utilizing a context-dependent additive recurrent neural network Physics 9 Active
US11113479B2 Utilizing a gated self-attention memory network model for predicting a candidate answer match to a query Physics 9 Active
US10334202B1 Ambient audio generation based on visual information Electricity 7 Active
US11100917B2 Generating ground truth annotations corresponding to digital image editing dialogues for training state tracking models Physics 7 Active
US11170158B2 Abstractive summarization of long documents using deep learning Physics 5 Active
US10372821B2 Identification of reading order text segments with a probabilistic language model Physics 5 Active
US12210800B2 Modifying digital images using combinations of direct interactions with the digital images and context-informing speech input Physics 5 Active
US11271876B2 Utilizing a graph neural network to identify supporting text phrases and generate digital query responses Physics 3 Active
US10055403B2 Rule-based dialog state tracking Physics 3 Active
US11537950B2 Utilizing a joint-learning self-distillation framework for improving text sequential labeling machine-learning models Physics 3 Active
US11205444B2 Utilizing bi-directional recurrent encoders with multi-hop attention for speech emotion recognition Physics 3 Active
US10453455B2 Multiple turn conversational task assistance Physics 3 Active
US10713519B2 Automated workflows for identification of reading order from text segments using probabilistic language models Physics 2 Active
US11670023B2 Artificial intelligence techniques for performing image editing operations inferred from natural language requests Physics 2 Active
US10579737B2 Natural language image editing annotation framework Physics 2 Active
US11676060B2 Digital content interaction prediction and training that addresses imbalanced classes Physics 2 Active
US11113323B2 Answer selection using a compare-aggregate model with language model and condensed similarity information from latent clustering Physics 1 Active
US11195048B2 Generating descriptions of image relationships Physics 1 Active
US10642887B2 Multi-modal image ranking using neural networks Physics 1 Active
US11567981B2 Model-based semantic text searching Physics 1 Active
US11561969B2 Utilizing logical-form dialogue generation for multi-turn construction of paired natural language queries and query-language representations Physics 1 Active
US11610584B2 Methods and systems for determining characteristics of a dialog between a computer and a user Physics 1 Active
US12182524B2 Intent detection Physics 1 Active
US10586528B2 Domain-specific speech recognizers in a digital medium environment Physics 1 Active

Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.