LRCN

Closed weights UT Austin,University of Massachusetts Lowell,University of California (UC) Berkeley 142.6M parameters November 2014

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
UT Austin,University of Massachusetts Lowell,University of California (UC) Berkeley
Organisation type
Academia,Academia,Academia
Country
United States of America
Published
7 November 2014
Authors
Jeff Donahue, Lisa Anne Hendricks, Marcus Rohrbach, Subhashini Venugopalan, Sergio Guadarrama, Kate Saenko, Trevor Darrell

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Video
Task
Video description
Approach
Reinforcement learning
Numerical format
FP32

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
142.6M

1st model: CaffeNet fc6 feature extractor (4096-length vectors) -> LSTM with 1024 hidden units 2nd model: CaffeNet fc6 feature extractor (4096-length vectors) -> 2 layer LSTM with 1000 hidden units 3rd mode: Like the second, but has encoder and decoder LSTMs (both with 2 layers) AlexNet (close relative to CaffeNet) has 61M params. LSTM RNN number of parameters is given by L*(n*m + n^2 + n) where L:= Number of layers, n:= hidden units, m:= input vector length

Training data
400,000 tokens

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Highly cited
Citations
6,380

Sources

Where this record came from and when it was last checked.

Reference
Long-term Recurrent Convolutional Networks for Visual Recognition and Description
Last updated
25 May 2026

What the numbers mean

About this model

LRCN was published by UT Austin,University of Massachusetts Lowell,University of California (UC) Berkeley, in United States of America, in November 2014. The organisation is categorised as academia,Academia,Academia.

It works in Video, and is recorded as doing video description.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

How it was trained

It was trained on about 400,000 tokens of text.

Its inclusion criterion is highly cited.

Answers

LRCN — common questions

01

How many parameters does LRCN have?

LRCN has 142.6M parameters. 1st model: CaffeNet fc6 feature extractor (4096-length vectors) -> LSTM with 1024 hidden units 2nd model: CaffeNet fc6 feature extractor (4096-length vectors) -> 2 layer LSTM with 1000 hidden units 3rd mode: Like the second, but has encoder and decoder LSTMs (both with 2 layers) AlexNet (close relative to CaffeNet) has 61M params. LSTM RNN number of parameters is given by L*(n*m + n^2 + n) where L:= Number of layers, n:= hidden units, m:= input vector length. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

02

Who created LRCN?

LRCN was published by UT Austin,University of Massachusetts Lowell,University of California (UC) Berkeley, based in United States of America, categorised as academia,Academia,Academia.

03

When was LRCN released?

LRCN was published in November 2014. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is LRCN used for?

LRCN works in Video, and is recorded as handling video description. These are the areas it was designed around; they describe intent rather than a hard boundary.

05

What GPU do I need to run LRCN?

None. LRCN is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

06

Is LRCN open source?

The licensing for LRCN was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

Source

Original publication

Record last updated 25 May 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.