Inventor

MOLCHANOV PAVLO

US28 patents

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

MOLCHANOV PAVLO

NVIDIA CORP

Radar based user interface

Three-dimensional (3D) pose estimation from a monocular camera

Transforming convolutional neural networks for visual sequence learning

Fusing multilayer and multimodal deep neural networks for video classification

Systems and methods for pruning neural networks for resource efficient inference

Multi-sensor based user interface

Articulated body mesh estimation using three-dimensional (3D) body keypoints

Online detection and classification of dynamic gestures with recurrent convolutional neural networks

Equivariant landmark transformation for landmark localization

Segmentation using an unsupervised neural network training technique

Budget-aware method for detecting activity in video

Neural network based facial analysis using facial landmarks and associated confidence values

Neural network based facial analysis using facial landmarks and associated confidence values

Semi-supervised learning for landmark localization

Neural network training method

Neural network-based noise synthesis

Segmentation using an unsupervised neural network training technique

Performing occlusion-aware global 3D pose and shape estimation of articulated objects

Transforming convolutional neural networks for visual sequence learning

3D human body pose estimation using a model trained from unlabeled multi-view data

Few-shot training of a neural network

Three-dimensional (3D) pose estimation from a monocular camera

Pruning a vision transformer

Camera and articulated object motion estimation from video

US NAVY

Gating large area hybrid photomultiplier tube

Large area hybrid photomultiplier tube

MOLCHANOV PAVLO

Multi-sensor based user interface

FLIR SYSTEMS

Methods and systems for suppressing atmospheric turbulence in images