Inventor

XIONG CAIMING

US141 patents

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

XIONG CAIMING

SALESFORCE COM INC

Systems and methods for unifying question answering and text classification via span extraction

Adaptive attention model for image captioning

Sentinel gate for modulating auxiliary information in a long short-term memory (LSTM) neural network

Spatial attention model for image captioning

Training a neural network using augmented training datasets

Training a neural network using augmented training datasets

Three-dimensional (3D) convolution with 3D batch normalization

Systems and methods for unifying question answering and text classification via span extraction

Joint many-task neural network model for multiple natural language processing (NLP) tasks

Natural language processing using context specific word vectors

Multitask learning as question answering

Natural language processing using a neural network

End-to-end speech recognition with policy learning

Spatial attention model for image captioning

Unsupervised non-parallel speech domain adaptation using a multi-discriminator adversarial network

Dense video captioning

Abstraction of text summarization

Interpretable counting in visual question answering

Pointer sentinel mixture architecture

Structured text translation

Dynamic memory network

Multi-task knowledge distillation for language model

Multitask learning as question answering

Multitask learning as question answering

Dynamic coattention network for question answering

Dialogue state tracking using a global-local encoder

Two-stage online detection of action start in untrimmed videos

Question answering from minimal context over documents

Training a joint many-task neural network model using successive regularization

Dense video captioning

Systems and methods for distilled BERT-based training model for text classification

Training a joint many-task neural network model using successive regularization

Bridging textual and tabular data for cross domain text-to-query language semantic parsing with a pre-trained transformer language encoder and anchor text

Efficient off-policy credit assignment

Efficient determination of user intent for natural language expressions based on machine learning

Global-to-local memory pointer networks for task-oriented dialogue

Learning dialogue state tracking with limited labeled data

Two-stage online detection of action start in untrimmed videos

Deep neural network model for processing data through multiple linguistic task hierarchies

End-to-end speech recognition with policy learning

Parameter utilization for language pre-training

Entity resolution for chatbot conversations

Neural network based translation of natural language queries to database queries

Template-based key-value extraction for inferring OCR key values within form images

SALESFORCE INC

Systems and methods for partially supervised online action detection in untrimmed videos

Systems and methods for multi-scale pre-training with densely connected transformer

Systems and methods for safe policy improvement for task oriented dialogues

Systems and methods for a collaborative reading assistance tool

Systems and methods for long document summarization

SALESFORCECOM INC

Neural network based translation of natural language queries to database queries