# TUGraz-TUT Face Verification Challenge — Data

来源：https://www.kaggle.com/competitions/face-verification2/data

采集时间：2026-10-19T09:37:01Z

File descriptions
train.zip
- the training set containing several images per person.
test.zip
- images used for your verification submission (see pairs.csv)
pairs.zip
- a list of image pairs for your submission.
The training database consists of a set of folders, where each folder contains pictures of a single person. You are free to sample pairs of same / different persons and learn to distinguish between the two cases. Also any other training data is allowed (but not mandatory) for this purpose (e.g.
[LFW](http://vis-www.cs.umass.edu/lfw/)
or
[YTF](http://www.cs.tau.ac.il/~wolf/ytfaces/)
datasets). The training database also contains the following readily calculated data for each image:
<image_name>_bbox.csv
- the coordinates of the bounding box around the face. Contains four numbers:
x, y, width, height
with (
x,y
) the upper left corner.
<image_name>_deepfeatures.csv
- Deep neural network features computed at the last hidden layer of
AlexNet.
<image_name>_landmarks_small.csv
- Five landmark coordinates extracted from the image:
left eye, right eye, nose, left corner of mouth, right corner of mouth.
<image_name>_landmarks_big.csv
- 68 landmark coordinates extracted from the image.
The test database consists of images similar to those in the training database. However, the identities are not given. Instead, a list of image pairs (the third file) is provided, and competitors are required to determine whether each pair is a match (1) or non-match (0).
Note:
The data was re-uploaded on October 28th, because the deep features were incorrectly computed. Please reload train.zip and test.zip.