CMS-RCNN
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
- IEEE
- Organisation type
- Industry
- Country
- Multinational
- Published
- 17 June 2016
- Authors
- Chenchen Zhu, Yutong Zheng, Khoa Luu, M. Savvides
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Face detection
- Approach
- Supervised
- Base model
- VGG16
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
- 138M
- Training data
- tokens
Based on VGG16 architecture, actual parameter count is slightly larger since the model contains some small added layers which are not described in detail.
159,424 annotated faces collected in 12,880 images
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
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
- SOTA improvement
- Record confidence
- Likely
https://paperswithcode.com/sota/face-detection-on-wider-face-medium "The experimental results show that our proposed approach trained on WIDER FACE Dataset outperforms strong baselines on WIDER FACE Dataset by a large margin, and consistently achieves competitive results on FDDB against the recent state-of-the-art face detection methods."
Sources
Where this record came from and when it was last checked.
- Reference
- CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
CMS-RCNN was published by IEEE, in the country recorded as Multinational, during June 2016. The publishing organisation is categorised as industry.
It works in the domain of Vision, and is recorded as performing the task of face detection.
Rather than being trained from scratch, it is derived from VGG16. That is the usual way a specialised model is produced.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
CMS-RCNN — common questions
CMS-RCNN— who created it?
It was published by IEEE, based in Multinational, an organisation categorised as industry.
CMS-RCNN— when was it released?
It 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.
CMS-RCNN— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of face detection. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
CMS-RCNN— what GPU do I need to run it?
None. This 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.
CMS-RCNN— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
CMS-RCNN— how many parameters does it have?
It has a parameter count of 138M. Based on VGG16 architecture, actual parameter count is slightly larger since the model contains some small added layers which are not described in detail. 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.
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.