Face Behind Makeup
Authors: Shuyang Wang, Yun Fu
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results have demonstrated the effectiveness of DL-based method on makeup detection. The proposed LC-CDL shows very promising performance on makeup removal regarding on the structure similarity. |
| Researcher Affiliation | Academia | 1Department of Electrical & Computer Engineering, 2College of Computer & Information Science, Northeastern University, Boston, MA, USA {shuyangwang, yunfu}@ece.neu.edu |
| Pseudocode | Yes | Algorithm 1 Updating coefficients Am |
| Open Source Code | No | The paper does not provide an unambiguous statement or link for the open-source code for the methodology described in this paper. It mentions external toolkits and datasets. |
| Open Datasets | Yes | We utilize the databases2 introduced by Dantcheva et al. and Chen et al. (Dantcheva, Chen, and Ross 2012; Chen, Dantcheva, and Ross 2013) which are You Tube Make Up (YMU) database, Virtual Make Up (VMU) database and Makeup in the wild database (MIW). ... we assembled a face dataset with stepwise makeup labeled for every sub-regions makeup status (SMU)3. ... 2,3The detailed information refers to http://antitza.com/makeupdatasets.html, and http://www.northeastern.edu/smilelab/. |
| Dataset Splits | Yes | A 5-fold cross-validation scheme is employed to evaluate the performance of the proposed makeup detection algorithm. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions using "Face++ Research Toolkit" and applying codes from other methods, but it does not specify version numbers for any software dependencies. |
| Experiment Setup | Yes | All face images with the size of 150 × 130 are automatically aligned with 83 facial landmarks extracted through Face++1 (Inc. 2013). ...where γ, δ and λP are regularization parameters to balance the terms in the energy function and dm,i, dn,i are the atoms of Dm and Dn. N is the number of samples. |