Search Results for author:
Found 6 papers, 3 papers with code
Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation
Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data.
Ranked #50 on
3D Human Pose Estimation
on Human3.6M
Image Aesthetics Assessment Using Graph Attention Network
Second, we propose a graph neural network architecture that takes this feature-graph and captures the semantic relationship between the different regions of the input image using visual attention.
Frequency Domain Loss Function for Deep Exposure Correction of Dark Images
We address the problem of exposure correction of dark, blurry and noisy images captured in low-light conditions in the wild.
A Geometry-Sensitive Approach for Photographic Style Classification
We further introduce a two-column CNN architecture that performs better than the state-of-the-art (SoA) in photographic style classification.
STaDA: Style Transfer as Data Augmentation
The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data.
Aesthetic Image Captioning From Weakly-Labelled Photographs
Aesthetic image captioning (AIC) refers to the multi-modal task of generating critical textual feedbacks for photographs.
