Inventor

MIN RENQIANG

US42 patents

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

MIN RENQIANG

NEC LAB AMERICA INC

System failure prediction using long short-term memory neural networks

Accelerating deep neural network training with inconsistent stochastic gradient descent

Video retrieval system using adaptive spatiotemporal convolution feature representation with dynamic abstraction for video to language translation

Large margin high-order deep learning with auxiliary tasks for video-based anomaly detection

Fast distributed nonnegative matrix factorization and completion for big data analytics

Deep 3D attention long short-term memory for video-based action recognition

Large margin high-order deep learning with auxiliary tasks for video-based anomaly detection

Unsupervised neighbor-preserving embedding for image stream visualization and anomaly detection

Unsupervised image-based anomaly detection using multi-scale context-dependent deep autoencoding gaussian mixture model

Memory efficient scalable deep learning with model parallelization

Translating video to language using adaptive spatiotemporal convolution feature representation with dynamic abstraction

Word embedding system

Controlled text generation with supervised representation disentanglement and mutual information minimization

Binding peptide generation for MHC class I proteins with deep reinforcement learning for immunotherapy decision making

Binding peptide generation for MHC class I proteins with deep reinforcement learning utilizing encoding methods of a blosum matrix

Binding peptide generation for MHC class I proteins with deep reinforcement learning for immunotherapy decision making

Binding peptide generation for MHC class I proteins with deep reinforcement learning

Contextual text generation for question answering and text summarization with supervised representation disentanglement and mutual information minimization

Network reparameterization for new class categorization

Learning orthogonal factorization in GAN latent space

Self-supervised sequential variational autoencoder for disentangled data generation

False alarm reduction system for automatic manufacturing quality control

Machine learning of spatio-temporal manifolds for source-free video domain adaptation

Cross-domain few-shot video classification with optical-flow semantics

Multi-hop transformer for spatio-temporal reasoning and localization

Peptide based vaccine generation system with dual projection generative adversarial networks

Peptide based vaccine generation system with dual projection generative adversarial networks

Convolutional neural network architecture with adaptive filters

Electronic message classification and delivery using a neural network architecture

Learning ordinal representations for deep reinforcement learning based object localization

Multi-scale text filter conditioned generative adversarial networks

Source-free cross domain detection method with strong data augmentation and self-trained mean teacher modeling

Deep group disentangled embedding and network weight generation for visual inspection

Mobile phone with system failure prediction using long short-term memory neural networks

System and method for fault-tolerant parallel learning over non-iid data

Weakly supervised action localization

Few-shot video classification

Context-aware attention-based neural network for interactive question answering

T-cell receptor repertoire selection prediction with physical model augmented pseudo-labeling for personalized medicine decision making

Corrected mean-covariance RBMs and general high-order semi-RBMs for large-scale collaborative filtering and prediction

Sparse higher-order Markov random field

NEC CORP

Surveillance system using adaptive spatiotemporal convolution feature representation with dynamic abstraction for video to language translation