Spatial Pyramid Matching

Closed weights INRIA,University of Illinois Urbana-Champaign (UIUC),Ecole Normale Supèrieure June 2006

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
INRIA,University of Illinois Urbana-Champaign (UIUC),Ecole Normale Supèrieure
Organisation type
Academia,Academia,Academia
Country
France, United States of America
Published
17 June 2006
Authors
S Lazebnik, C Schmid, J Ponce

What it does

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

Domain
Vision
Task
Image classification

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
3,030 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
Record confidence
Unknown
Citations
9,807

Sources

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

Reference
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Last updated
28 November 2025

What the numbers mean

Background

Spatial Pyramid Matching was published by INRIA,University of Illinois Urbana-Champaign (UIUC),Ecole Normale Supèrieure, in France, in June 2006. The organisation is categorised as academia,Academia,Academia.

It works in Vision, and is recorded as doing image classification.

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

What went into building it

Around 3,030 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: highly cited.

Answers

Spatial Pyramid Matching — common questions

01

What is Spatial Pyramid Matching used for?

Spatial Pyramid Matching works in Vision, and is recorded as handling image classification. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

02

What GPU do I need to run Spatial Pyramid Matching?

None. Spatial Pyramid Matching 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 Spatial Pyramid Matching open source?

The licensing for Spatial Pyramid Matching 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 Spatial Pyramid Matching have?

No parameter count has been published for Spatial Pyramid Matching, which is why no memory or speed figure appears on this page.

05

Who created Spatial Pyramid Matching?

Spatial Pyramid Matching was published by INRIA,University of Illinois Urbana-Champaign (UIUC),Ecole Normale Supèrieure, based in France, categorised as academia,Academia,Academia.

06

When was Spatial Pyramid Matching released?

Spatial Pyramid Matching was published in June 2006. 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.