Spatiotemporal fusion ConvNet

Closed weights Graz University of Technology,University of Oxford June 2016

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
Graz University of Technology,University of Oxford
Organisation type
Academia,Academia
Country
Austria, United Kingdom of Great Britain and Northern Ireland
Published
1 June 2016
Authors
Christoph Feichtenhofer, Axel Pinz, Andrew Zisserman

What it does

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

Domain
Video
Task
Video, Action recognition
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.

Training data
13,000 tokens

[SECONDS OF VIDEO] They use UCF101, whose paper says "We introduce UCF101 which is currently the largest dataset of human actions. It consists of 101 action classes, over 13k clips and 27 hours of video data"

How it is classified

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

Citations
2,538

Sources

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

Reference
Convolutional Two-Stream Network Fusion for Video Action Recognition
Last updated
28 November 2025

What the numbers mean

Where it came from

Spatiotemporal fusion ConvNet was published by Graz University of Technology,University of Oxford, in Austria, in June 2016. It comes out of academia,Academia.

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

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Around 13,000 tokens went into training it.

Answers

Spatiotemporal fusion ConvNet — common questions

01

What is Spatiotemporal fusion ConvNet used for?

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

02

What GPU do I need to run Spatiotemporal fusion ConvNet?

None. Spatiotemporal fusion ConvNet 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.

03

Is Spatiotemporal fusion ConvNet open source?

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

04

How many parameters does Spatiotemporal fusion ConvNet have?

No parameter count has been published for Spatiotemporal fusion ConvNet, which is why no memory or speed figure appears on this page.

05

Who created Spatiotemporal fusion ConvNet?

Spatiotemporal fusion ConvNet was published by Graz University of Technology,University of Oxford, based in Austria, categorised as academia,Academia.

06

When was Spatiotemporal fusion ConvNet released?

Spatiotemporal fusion ConvNet was published in June 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 28 November 2025

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.