Related papers: Improving Robustness for Pose Estimation via Stabl…

Group robustness strategies aim to mitigate learned biases in deep learning models that arise from spurious correlations present in their training datasets. However, most existing methods rely on the access to the label distribution of the…

We propose a new semi-supervised learning design for human pose estimation that revisits the popular dual-student framework and enhances it two ways. First, we introduce a denoising scheme to generate reliable pseudo-heatmaps as targets for…

Precise 6D pose estimation of rigid objects from RGB images is a critical but challenging task in robotics, augmented reality and human-computer interaction. To address this problem, we propose DeepRM, a novel recurrent network architecture…

The solution of linear inverse problems arising, for example, in signal and image processing is a challenging problem since the ill-conditioning amplifies, in the solution, the noise present in the data. Recently introduced algorithms based…

Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications. However, due to the black box nature of deep learning, the best method may fail in some situations. Thus…

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that…

Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss…

Traditionally, monocular 3D human pose estimation employs a machine learning model to predict the most likely 3D pose for a given input image. However, a single image can be highly ambiguous and induces multiple plausible solutions for the…

Despite recent success on 2D human pose estimation, 3D human pose estimation still remains an open problem. A key challenge is the ill-posed depth ambiguity nature. This paper presents a novel intermediate feature representation named…

Knowledge about the locations of keypoints of an object in an image can assist in fine-grained classification and identification tasks, particularly for the case of objects that exhibit large variations in poses that greatly influence their…

Estimating camera pose in dynamic environments is a critical challenge, as most visual SLAM and SfM methods assume static scenes. While recent dynamic-aware methods exist, they are often not unified: semantic-based approaches are brittle,…

The 2D human pose estimation (HPE) is a basic visual problem. However, its supervised learning requires massive keypoint labels, which is labor-intensive to collect. Thus, we aim at boosting a pose estimator by excavating extra unlabeled…

Heatmap regression based face alignment has achieved prominent performance on static images. However, the stability and accuracy are remarkably discounted when applying the existing methods on dynamic videos. We attribute the degradation to…

Human pose estimation (i.e., locating the body parts / joints of a person) is a fundamental problem in human-computer interaction and multimedia applications. Significant progress has been made based on the development of depth sensors,…

Human pose estimation has achieved significant progress on images with high imaging resolution. However, low-resolution imagery data bring nontrivial challenges which are still under-studied. To fill this gap, we start with investigating…

In this paper, we propose an end-to-end trainable regression approach for human pose estimation from still images. We use the proposed Soft-argmax function to convert feature maps directly to joint coordinates, resulting in a fully…

This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without…

While being the de facto standard coordinate representation in human pose estimation, heatmap is never systematically investigated in the literature, to our best knowledge. This work fills this gap by studying the coordinate representation…

Deep neural networks have shown impressive performance for image-based disease detection. Performance is commonly evaluated through clinical validation on independent test sets to demonstrate clinically acceptable accuracy. Reporting good…

Modern technologies are producing datasets with complex intrinsic structures, and they can be naturally represented as matrices instead of vectors. To preserve the latent data structures during processing, modern regression approaches…