Efstratios GAVVES
16Patents
4h-index
13Co-inventors
49Inventor score
Filing activity: Jun 24, 2016 → Mar 18, 2021
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US10733755B2 | Learning geometric differentials for matching 3D models to objects in a 2D image | Physics | 37 | Active |
| US9830709B2 | Video analysis with convolutional attention recurrent neural networks | Physics | 24 | Active |
| US10019631B2 | Adapting to appearance variations when tracking a target object in video sequence | Physics | 15 | Active |
| US10049279B2 | Recurrent networks with motion-based attention for video understanding | Physics | 5 | Active |
| US10902615B2 | Hybrid and self-aware long-term object tracking | Physics | 4 | Active |
| US10496885B2 | Unified embedding with metric learning for zero-exemplar event detection | Physics | 2 | Active |
| US11270425B2 | Coordinate estimation on n-spheres with spherical regression | Physics | 1 | Active |
| US10438068B2 | Adapting to appearance variations of a target object when tracking the target object in a video sequence | Physics | 1 | Active |
| US12380689B2 | Managing occlusion in Siamese tracking using structured dropouts | Physics | 0 | Active |
| US11481576B2 | Subject-object interaction recognition model | Physics | 0 | Active |
| US12333811B2 | Permutation invariant convolution (PIC) for recognizing long-range activities, generating global representation of input streams and classifying activity based on global representation | Physics | 0 | Active |
| US10691952B2 | Adapting to appearance variations when tracking a target object in video sequence | Physics | 0 | Active |
| US11443514B2 | Recognizing minutes-long activities in videos | Physics | 0 | Active |
| US10846593B2 | System and method for siamese instance search tracker with a recurrent neural network | Physics | 0 | Active |
| US12249138B2 | Context-driven learning of human-object interactions | Physics | 0 | Active |
| US11842279B2 | Combinatorial Bayesian optimization using a graph cartesian product | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.