We apply the method to a challenging subset of the something-something dataset and achieve a more robust performance against neural network baselines on challenging activities.
We present ALADIN (All Layer AdaIN); a novel architecture for searching images based on the similarity of their artistic style.
We expand these 'coarse' genre labels by identifying 'fine-grained' semantic information within the multi-modal content of movies.
We present a neural architecture search (NAS) technique to enhance the performance of unsupervised image de-noising, in-painting and super-resolution under the recently proposed Deep Image Prior (DIP).
Treating the problem as a landmark detection problem, we propose a modified U-Net CNN architecture to generate heatmaps of likely coordinate locations.
We analyze example images that fall outside of our proposed classes to show our confidence metric can prevent many misclassifications.
We aim to simultaneously estimate the 3D articulated pose and high fidelity volumetric occupancy of human performance, from multiple viewpoint video (MVV) with as few as two views.
Ranked #32 on 3D Human Pose Estimation on Human3.6M
We present a convolutional autoencoder that enables high fidelity volumetric reconstructions of human performance to be captured from multi-view video comprising only a small set of camera views.
We present a method for simultaneously estimating 3D human pose and body shape from a sparse set of wide-baseline camera views.
Ranked #5 on 3D Human Pose Estimation on Total Capture
Content-aware image completion or in-painting is a fundamental tool for the correction of defects or removal of objects in images.
We incorporate this model within a dual stream network integrating pose embeddings derived from MVV and a forward kinematic solve of the IMU data.
Ranked #7 on 3D Human Pose Estimation on Total Capture
On the UCF11 video dataset, the accuracy is 86. 7% despite using only 90 labelled examples from a dataset of over 1200 videos, instead of the standard 1122 training videos.