11 datasets found

The BeautyGlow dataset is used for training the BeautyGlow model.

The Makeup-Wild dataset contains facial images with various poses and expressions as well as complex backgrounds to test methods in the real-world environment.

Facial Expression Recognition (FER) is a classification task that points to face variants. Hence, there are certain affinity features between facial expressions, receiving lit-

CelebAMask-HQ provides the parsing map of images in CelebA-HQ down-sampled to 512 × 512, where pixel-level annotation of 19 classes, including facial components and accessories,...

The ETH-XGaze dataset provides 80 subjects (i.e., 756,540 images) that consist of various illumination conditions, gaze and head pose ranges.

Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model.

The dataset used in the paper is VGGFace2, which is a dataset for face recognition tasks.

The Bollywood dataset is a collection of images of Bollywood celebrities with varying body mass indexes (BMIs). The dataset is used for face-to-BMI prediction.

Face-to-bmi: Using computer vision to infer body mass index on social media.

Three publicly available BMI annotated facial image datasets assembled from social media, namely, VisualBMI, VIP-Attributes, and Bollywood datasets.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...