Related papers: Self-Correctable and Adaptable Inference for Gener…
We address the problem of camera pose estimation in visual localization. Current regression-based methods for pose estimation are trained and evaluated scene-wise. They depend on the coordinate frame of the training dataset and show a low…
We propose a new 2D pose refinement network that learns to predict the human bias in the estimated 2D pose. There are biases in 2D pose estimations that are due to differences between annotations of 2D joint locations based on annotators'…
Big neural networks trained on large datasets have advanced the state-of-the-art for a large variety of challenging problems, improving performance by a large margin. However, under low memory and limited computational power constraints,…
We propose a personalized ConvNet pose estimator that automatically adapts itself to the uniqueness of a person's appearance to improve pose estimation in long videos. We make the following contributions: (i) we show that given a few…
In AI-assisted decision-making, it is crucial but challenging for humans to appropriately rely on AI, especially in high-stakes domains such as finance and healthcare. This paper addresses this problem from a human-centered perspective by…
AI predictive systems are increasingly embedded in decision making pipelines, shaping high stakes choices once made solely by humans. Yet robust decisions under uncertainty still rely on capabilities that current AI lacks: domain knowledge…
3D human pose estimation from a single image is still a challenging problem despite the large amount of work that has been performed in this field. Generally, most methods directly use neural networks and ignore certain constraints (e.g.,…
Amortized Bayesian Inference (ABI) enables efficient posterior estimation using generative neural networks trained on simulated data, but often suffers from performance degradation under model misspecification. While self-consistency (SC)…
We propose to personalize a human pose estimator given a set of test images of a person without using any manual annotations. While there is a significant advancement in human pose estimation, it is still very challenging for a model to…
Online test-time adaptation addresses the train-test domain gap by adapting the model on unlabeled streaming test inputs before making the final prediction. However, online adaptation for 3D human pose estimation suffers from error…
Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such…
We address the problem of estimating the relative 6D pose, i.e., position and orientation, of a target spacecraft, from a monocular image, a key capability for future autonomous Rendezvous and Proximity Operations. Due to the difficulty of…
We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…
We address the challenging problem of RGB image-based head pose estimation. We first reformulate head pose representation learning to constrain it to a bounded space. Head pose represented as vector projection or vector angles shows helpful…
For human pose estimation in monocular images, joint occlusions and overlapping upon human bodies often result in deviated pose predictions. Under these circumstances, biologically implausible pose predictions may be produced. In contrast,…
Most image restoration problems are ill-conditioned or ill-posed and hence involve significant uncertainty. Quantifying this uncertainty is crucial for reliably interpreting experimental results, particularly when reconstructed images…
Human pose estimation is the task of localizing body keypoints from still images. The state-of-the-art methods suffer from insufficient examples of challenging cases such as symmetric appearance, heavy occlusion and nearby person. To…
We propose a generic framework to calibrate accuracy and confidence of a prediction in deep neural networks through stochastic inferences. We interpret stochastic regularization using a Bayesian model, and analyze the relation between…
Smooth and seamless robot navigation while interacting with humans depends on predicting human movements. Forecasting such human dynamics often involves modeling human trajectories (global motion) or detailed body joint movements (local…
This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which…