Pavlo Molchanov
25Patents
5h-index
33Co-inventors
65Inventor score
Filing activity: Apr 26, 2007 → Oct 31, 2022
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US10157309B2 | Online detection and classification of dynamic gestures with recurrent convolutional neural networks | Physics | 12 | Active |
| US10929654B2 | Three-dimensional (3D) pose estimation from a monocular camera | Physics | 10 | Active |
| US11049018B2 | Transforming convolutional neural networks for visual sequence learning | Physics | 10 | Active |
| US10402697B2 | Fusing multilayer and multimodal deep neural networks for video classification | Physics | 9 | Active |
| US10481696B2 | Radar based user interface | Physics | 8 | Active |
| US10783394B2 | Equivariant landmark transformation for landmark localization | Physics | 5 | Active |
| US11315018B2 | Systems and methods for pruning neural networks for resource efficient inference | Physics | 4 | Active |
| US10168785B2 | Multi-sensor based user interface | Physics | 3 | Active |
| US9811884B2 | Methods and systems for suppressing atmospheric turbulence in images | Physics | 2 | Active |
| US10783393B2 | Semi-supervised learning for landmark localization | Physics | 2 | Active |
| US11487968B2 | Neural network based facial analysis using facial landmarks and associated confidence values | Physics | 2 | Active |
| US11361507B1 | Articulated body mesh estimation using three-dimensional (3D) body keypoints | Physics | 1 | Active |
| US10509479B2 | Multi-sensor based user interface | Physics | 1 | Active |
| US11934955B2 | Neural network based facial analysis using facial landmarks and associated confidence values | Physics | 1 | Active |
| US11748887B2 | Segmentation using an unsupervised neural network training technique | Physics | 1 | Active |
| US12100113B2 | Performing occlusion-aware global 3D pose and shape estimation of articulated objects | Physics | 0 | Active |
| US10860859B2 | Budget-aware method for detecting activity in video | Physics | 0 | Active |
| US11488418B2 | Three-dimensional (3D) pose estimation from a monocular camera | Physics | 0 | Active |
| US7687992B2 | Gating large area hybrid photomultiplier tube | Electricity | 0 | Active |
| US11593661B2 | Few-shot training of a neural network | Physics | 0 | Active |
| US12431965B2 | Multi-beam multi-band protected communication system | Electricity | 0 | Active |
| US11645530B2 | Transforming convolutional neural networks for visual sequence learning | Physics | 0 | Active |
| US11417011B2 | 3D human body pose estimation using a model trained from unlabeled multi-view data | Physics | 0 | Active |
| US7667399B2 | Large area hybrid photomultiplier tube | Electricity | 0 | Active |
| US12406023B1 | Neural network training method | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.