Visual Geometry Group
E366100
The Visual Geometry Group is a renowned computer vision research group at the University of Oxford known for pioneering deep convolutional neural network architectures such as VGGNet.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Visual Geometry Group canonical | 2 |
How this entity was disambiguated
This entity first appeared as the object of triple T3520344 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Visual Geometry Group Context triple: [VGG, developedBy, Visual Geometry Group]
-
A.
Learning to See by Moving
"Learning to See by Moving" is a research work in computer vision that explores how visual understanding can emerge from an agent’s own movement and interaction with the environment, rather than from static images alone.
-
B.
Scene Completion Using Millions of Photographs
"Scene Completion Using Millions of Photographs" is a seminal computer vision and graphics paper that introduced a data-driven method for automatically filling in missing regions of images by searching a massive online photo collection for visually compatible patches.
-
C.
Data-Driven Hallucination of Different Views
"Data-Driven Hallucination of Different Views" is a computer vision research work by Alexei Efros that uses data-driven techniques to synthesize plausible novel viewpoints of a scene from a single or limited set of images.
-
D.
Visual Component Library
Visual Component Library is Delphi’s native GUI framework that provides a rich set of reusable visual and non-visual components for building Windows applications.
-
E.
Max Planck Institute for Intelligent Systems
The Max Planck Institute for Intelligent Systems is a leading German research institute focused on advancing the understanding and development of intelligent systems, including machine learning, robotics, and related fields.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Visual Geometry Group Target entity description: The Visual Geometry Group is a renowned computer vision research group at the University of Oxford known for pioneering deep convolutional neural network architectures such as VGGNet.
-
A.
Learning to See by Moving
"Learning to See by Moving" is a research work in computer vision that explores how visual understanding can emerge from an agent’s own movement and interaction with the environment, rather than from static images alone.
-
B.
Scene Completion Using Millions of Photographs
"Scene Completion Using Millions of Photographs" is a seminal computer vision and graphics paper that introduced a data-driven method for automatically filling in missing regions of images by searching a massive online photo collection for visually compatible patches.
-
C.
Data-Driven Hallucination of Different Views
"Data-Driven Hallucination of Different Views" is a computer vision research work by Alexei Efros that uses data-driven techniques to synthesize plausible novel viewpoints of a scene from a single or limited set of images.
-
D.
Visual Component Library
Visual Component Library is Delphi’s native GUI framework that provides a rich set of reusable visual and non-visual components for building Windows applications.
-
E.
Max Planck Institute for Intelligent Systems
The Max Planck Institute for Intelligent Systems is a leading German research institute focused on advancing the understanding and development of intelligent systems, including machine learning, robotics, and related fields.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
academic research group
ⓘ
computer vision research group ⓘ research group ⓘ |
| abbreviation | VGG ⓘ |
| affiliation | University of Oxford ⓘ |
| city | Oxford ⓘ |
| collaboratesWith |
DeepMind
ⓘ
Google Research ⓘ Microsoft Research ⓘ |
| country | United Kingdom ⓘ |
| field |
artificial intelligence
ⓘ
computer vision ⓘ machine learning ⓘ |
| focus |
developing state-of-the-art vision algorithms
ⓘ
fundamental visual recognition problems ⓘ |
| hasMember |
Andrea Vedaldi
ⓘ
Andrew Zisserman ⓘ James Philbin ⓘ João F. Henriques ⓘ Karen Simonyan ⓘ Maxime Oquab ⓘ Oisin Mac Aodha ⓘ
linked to:
Mac Aoidh
Relja Arandjelović ⓘ Will Maddern ⓘ |
| knownFor |
ImageNet classification models
ⓘ
VGG-16 ⓘ
linked to:
VGG
VGG-19 ⓘ
linked to:
VGG
VGGNet ⓘ
linked to:
VGG
deep convolutional neural networks ⓘ large-scale image recognition ⓘ visual geometry methods ⓘ |
| language | English ⓘ |
| notableWork | Very Deep Convolutional Networks for Large-Scale Image Recognition ⓘ |
| partOf | Department of Engineering Science, University of Oxford ⓘ |
| publishesIn |
CVPR
ⓘ
ECCV ⓘ
linked to:
European Conference on Computer Vision
ICCV ⓘ ICLR ⓘ IJCV ⓘ NeurIPS ⓘ PAMI ⓘ |
| researchArea |
3D vision
ⓘ
deep learning ⓘ image classification ⓘ image segmentation ⓘ object detection ⓘ representation learning ⓘ |
| sector | higher education ⓘ |
| website | https://www.robots.ox.ac.uk/~vgg/ ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Visual Geometry Group Description of subject: The Visual Geometry Group is a renowned computer vision research group at the University of Oxford known for pioneering deep convolutional neural network architectures such as VGGNet.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.