CCL
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
- SenseTime,Chinese University of Hong Kong (CUHK),Chinese Academy of Sciences
- Organisation type
- Industry,Academia,Academia
- Country
- Hong Kong, China
- Published
- 27 June 2016
- Authors
- Shizhan Zhu, Cheng Li, Chen Change Loy, Xiaoou Tang
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
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
- 20,000 tokens
[images] Table 1
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
- Training code
- Unreleased
project page (no code or weights are released): https://mmlab.ie.cuhk.edu.hk/projects/compositional.html
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
- Confident
https://paperswithcode.com/sota/face-alignment-on-aflw-19
Sources
Where this record came from and when it was last checked.
- Reference
- Unconstrained Face Alignment via Cascaded Compositional Learning
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
CCL was published by SenseTime,Chinese University of Hong Kong (CUHK),Chinese Academy of Sciences, in Hong Kong, in June 2016. It comes out of industry,Academia,Academia.
It works in Vision, and is recorded as doing face detection.
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
The training set ran to roughly 20,000 tokens.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
CCL — common questions
Is CCL open source?
No. CCL has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does CCL have?
No parameter count has been published for CCL, which is why no memory or speed figure appears on this page.
Who created CCL?
CCL was published by SenseTime,Chinese University of Hong Kong (CUHK),Chinese Academy of Sciences, based in Hong Kong, categorised as industry,Academia,Academia.
When was CCL released?
CCL 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.
What is CCL used for?
CCL works in Vision, and is recorded as handling face detection. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run CCL?
None. CCL 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.
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.