Inventor
MARIOS SAVVIDES
Inventor
US
Overview
Patents· 29 as inventor
Public. Assignee & technology derived from the patent record. Each patent links to its LexDana page.
G06Vprimary
G06VImage or video recognition or understanding28%
G06NComputing arrangements based on specific computational models20%
G06FElectric digital data processing16%
G06TImage data processing or generation, in general14%
G06QInformation and communication technology [ict] specially adapted for administrative, commercial, financial, managerial or supervisory purposes10%
H04NPictorial communication, e.g. television5%
B65GTransport or storage devices, e.g. conveyors for loading or tipping, shop conveyor systems or pneumatic tube conveyors2%
G06KGraphical data reading2%
G09FDisplaying2%
PatentTitleYear
12,536,780System and method for detecting, reading and matching in a retail scene202612,536,418Perturbative neural network202612,536,769System and method for matching products and determining spreads and plugs202612,511,743System and method for detecting and classifying abnormal cells202512,505,663—202512,437,258System and method for identifying products in a shelf management system202512,327,338Methods for improving datasets for skeleton-based action detection202512,322,012System and method for scene rectification via homography estimation202512,266,156System and method for solving missing annotation object detection202512,243,004System and method for determining out-of-stock products202512,217,339Multiple hypothesis transformation matching for robust verification of object identification202512,189,714System and method for improved few-shot object detection using a dynamic semantic network202512,190,565System and method for domain-agnostic bias reduction with selected sampling for few-shot learning202512,182,707System and method for the discovering efficient random neural networks202412,165,068Convex feature normalization for face recognition202412,136,155System and method for photorealistic image synthesis using unsupervised semantic feature disentanglement202412,131,260Discriminative cosine embedding in machine learning202412,131,497Fast object search based on the cocktail party effect202412,118,506System and method for associating products and product labels202412,067,527System and method for identifying misplaced products in a shelf management system202412,026,226Few-shot object detection using semantic relation reasoning202411,989,933Polynomial convolutional neural network with late fan-out202411,954,175Feature pyramids for object detection202411,915,463System and method for the automatic enrollment of object images into a gallery202411,900,516System and method for pose tolerant feature extraction using generated pose-altered images202411,875,557Polynomial convolutional neural network with early fan-out202411,854,245Generative adversarial networks having ranking loss202311,748,853Method and architecture for blind image deconvolution202311,636,344Discriminative cosine embedding in machine learning2023Career & activity timeline
Assembled from patent assignee/location history and declaration credentials.
2023–2026Patents assigned to UNIV CARNEGIE MELLON (29)· patent assignee history
2023–2026Based in US· patent location history
2024–2025Patents assigned to BOSSA NOVA ROBOTICS (2)· patent assignee history
2024Patents assigned to HU KAI (1)· patent assignee history
2024Patents assigned to NALLAMOTHU SREENA (1)· patent assignee history
2025Patents assigned to ANYVISION INTERACTIVE TECH LTD (1)· patent assignee history
Inventor activity
Assignee and location history derived from the patent record.
Assignees
| Assignee | Patents | Span |
|---|---|---|
| UNIV CARNEGIE MELLON | 29 | 2023–2026 |
| BOSSA NOVA ROBOTICS | 2 | 2024–2025 |
| ANYVISION INTERACTIVE TECH LTD | 1 | 2025 |
| HU KAI | 1 | 2024 |
| NALLAMOTHU SREENA | 1 | 2024 |
Locations
| Location | Patents | Span |
|---|---|---|
| US | 29 | 2023–2026 |