no code implementations • 7 Aug 2023 • Jose Sosa, David Hogg
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.
no code implementations • 25 Jul 2023 • Jose Sosa, Sharn Perry, Jane Alty, David Hogg
To address this, we propose an approach for estimating 2D mouse body pose from unlabelled images using a synthetically generated empirical pose prior.
no code implementations • 5 Apr 2023 • Jose Sosa, David Hogg
Despite the reduced requirement for annotated data, we show that the method outperforms on Human3. 6M and matches performance on MPI-INF-3DHP.
4 code implementations • 21 Nov 2022 • Yunfeng Diao, He Wang, Tianjia Shao, Yong-Liang Yang, Kun Zhou, David Hogg
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.
1 code implementation • 18 May 2022 • Hanh Thi Minh Tran, David Hogg
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).
1 code implementation • CVPR 2021 • He Wang, Feixiang He, Zhexi Peng, Tianjia Shao, Yong-Liang Yang, Kun Zhou, David Hogg
In this paper, we examine the robustness of state-of-the-art action recognizers against adversarial attack, which has been rarely investigated so far.
no code implementations • 16 Nov 2019 • He Wang, Feixiang He, Zhexi Peng, Yong-Liang Yang, Tianjia Shao, Kun Zhou, David Hogg
In this paper, we propose a method, SMART, to attack action recognizers which rely on 3D skeletal motions.
no code implementations • CVPR 2016 • James Charles, Tomas Pfister, Derek Magee, David Hogg, Andrew Zisserman
The outcome is a substantial improvement in the pose estimates for the target video using the personalized ConvNet compared to the original generic ConvNet.