Furthermore, we provide the code to evaluate HPE networks with [mAPK metric](#evaluation), our keypoint-centered metric.
Furthermore, we provide the code to evaluate HPE networks with [mAPK metric](#evaluation), our keypoint-centered metric.
# Dataset
# Dataset
DriPE dataset can be found [here](). We provide the 10k images,
DriPE dataset can be found [here](http://dionysos.univ-lyon2.fr/~ccrispim/DriPE/DriPE.zip). We provide the 10k images,
along with keypoint annotations, split as:
along with keypoint annotations, split as:
* 6.4k for training
* 6.4k for training
* 1.3k for validation
* 1.3k for validation
...
@@ -51,7 +51,7 @@ We used in our study three architectures:
...
@@ -51,7 +51,7 @@ We used in our study three architectures:
* __RSN__: Learning Delicate Local Representations for Multi-Person Pose Estimation (Cai 2020) [GitHub](https://github.com/caiyuanhao1998/RSN)
* __RSN__: Learning Delicate Local Representations for Multi-Person Pose Estimation (Cai 2020) [GitHub](https://github.com/caiyuanhao1998/RSN)
We used for training and for inference the code provided by the authors in the three linked repositories.
We used for training and for inference the code provided by the authors in the three linked repositories.
Weights of the trained model evaluated in our study can be found [here]().
Weights of the trained model evaluated in our study can be found [here](http://dionysos.univ-lyon2.fr/~ccrispim/DriPE/models).
More details about the training can be found in our [paper](https://openaccess.thecvf.com/content/ICCV2021W/AVVision/papers/Guesdon_DriPE_A_Dataset_for_Human_Pose_Estimation_in_Real-World_Driving_ICCVW_2021_paper.pdf).
More details about the training can be found in our [paper](https://openaccess.thecvf.com/content/ICCV2021W/AVVision/papers/Guesdon_DriPE_A_Dataset_for_Human_Pose_Estimation_in_Real-World_Driving_ICCVW_2021_paper.pdf).
