LINEAiGE
AI HISTORY

Very Deep Convolutional Networks for Large-Scale Image Recognition

Karen Simonyan and Andrew Zisserman submitted Very Deep Convolutional Networks for Large-Scale Image Recognition to arXiv on September 4, 2014. The paper evaluates convolutional-network depth for large-scale image recognition, using very small 3x3 convolution filters and reporting networks with 16 to 19 weight layers.

September 4, 2014AI HISTORYVERIFIED

Historical classification

This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.

Why it matters

A documented deep-convolutional-network milestone associated with the very-deep VGG family and the authors' ImageNet Challenge 2014 work.

People, organizations & technologies

PEOPLE
Karen Simonyan, Andrew Zisserman

ORGANIZATIONS
University of Oxford

TECHNOLOGIES
Deep convolutional neural networks, 3x3 convolution filters, VGG

Evidence & verification

STATE
verified

CONFIDENCE
high

LAST VERIFIED
2026-09-11T23:02:33+08:00

The arXiv record establishes the title, authors, September 4 2014 first-submission date, use of very small 3x3 convolution filters, and evaluation of networks up to 16-19 weight layers. The University of Oxford Visual Geometry Group publication record and author-hosted conference paper corroborate the title, authors, University of Oxford affiliation, technical claims, and later ICLR 2015 publication. The day-precision date is attached only to the documented arXiv submission milestone. University of Oxford is recorded only as the explicit author affiliation; no broader geography, ancestry, influence, causality, or relationships are inferred.

Sources

SOURCE 1 · PRIMARY · CLAIM-EVIDENCE

Very Deep Convolutional Networks for Large-Scale Image Recognition

arXiv

PUBLISHED
2014-09-04

SOURCE 2 · PRIMARY · CORROBORATION

Very Deep Convolutional Networks for Large-Scale Image Recognition

Visual Geometry Group, University of Oxford

Trace the chronology

Record identity

LINEAiGE ID
vggnet-2014