Search Results for author:
Found 8 papers, 3 papers with code
A Horse with no Labels: Self-Supervised Horse Pose Estimation from Unlabelled Images and Synthetic Prior
We demonstrate that it is possible to learn accurate animal poses even with as few assumptions as unlabelled images and a small set of 2D poses generated from synthetic data.
Of Mice and Pose: 2D Mouse Pose Estimation from Unlabelled Data and Synthetic Prior
To address this, we propose an approach for estimating 2D mouse body pose from unlabelled images using a synthetically generated empirical pose prior.
Self-supervised 3D Human Pose Estimation from a Single Image
Despite the reduced requirement for annotated data, we show that the method outperforms on Human3. 6M and matches performance on MPI-INF-3DHP.
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold.
Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM
In this paper, we propose a novel method for video anomaly detection motivated by an existing architecture for sequence-to-sequence prediction and reconstruction using a spatio-temporal convolutional Long Short-Term Memory (convLSTM).
Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
In this paper, we examine the robustness of state-of-the-art action recognizers against adversarial attack, which has been rarely investigated so far.
SMART: Skeletal Motion Action Recognition aTtack
In this paper, we propose a method, SMART, to attack action recognizers which rely on 3D skeletal motions.
Personalizing Human Video Pose Estimation
The outcome is a substantial improvement in the pose estimates for the target video using the personalized ConvNet compared to the original generic ConvNet.
