Related papers: Improving Sparse IMU-based Motion Capture with Mot…

Human motion analysis is used in many different fields and applications. Currently, existing systems either focus on one single limb or one single class of movements. Many proposed systems are designed to be used in an indoor controlled…

Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled…

Multi-label learning is concerned with the classification of data with multiple class labels. This is in contrast to the traditional classification problem where every data instance has a single label. Due to the exponential size of output…

Depth completion is an important vision task, and many efforts have been made to enhance the quality of depth maps from sparse depth measurements. Despite significant advances, training these models to recover dense depth from sparse…

In this paper, we present a novel yet simple homotopy proximal mapping algorithm for compressive sensing. The algorithm adopts a simple proximal mapping of the $\ell_1$ norm at each iteration and gradually reduces the regularization…

The paper presents a direct visual-inertial odometry system. In particular, a tightly coupled nonlinear optimization based method is proposed by integrating the recent advances in direct dense tracking and Inertial Measurement Unit (IMU)…

Many industrial applications use Metric Learning as a way to circumvent scalability issues when designing systems with a high number of classes. Because of this, this field of research is attracting a lot of interest from the academic and…

Spatial sampling is traditionally studied in a static setting where static sensors scattered around space take measurements of the spatial field at their locations. In this paper we study the emerging paradigm of sampling and reconstructing…

Estimating full-body human motion via sparse tracking signals from head-mounted displays and hand controllers in 3D scenes is crucial to applications in AR/VR. One of the biggest challenges to this task is the one-to-many mapping from…

A variety of modern applications exhibit multi-view multi-label learning, where each sample has multi-view features, and multiple labels are correlated via common views. Current methods usually fail to directly deal with the setting where…

Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to…

In large-scale supervised learning, penalized logistic regression (PLR) effectively mitigates overfitting through regularization, yet its performance critically depends on robust variable selection. This paper demonstrates that label noise…

Temporal 3D human pose estimation from monocular videos is a challenging task in human-centered computer vision due to the depth ambiguity of 2D-to-3D lifting. To improve accuracy and address occlusion issues, inertial sensor has been…

Back pain is a pervasive issue affecting a significant portion of the population, often worsened by certain movements of the lower back. Assessing these movements is important for helping clinicians prescribe appropriate physical therapy.…

Simultaneous localization and mapping (SLAM) plays a vital role in mapping unknown spaces and aiding autonomous navigation. Virtually all state-of-the-art solutions today for 2D SLAM are designed for dense and accurate sensors such as laser…

Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models.…

Compared with visual signals, Inertial Measurement Units (IMUs) placed on human limbs can capture accurate motion signals while being robust to lighting variation and occlusion. While these characteristics are intuitively valuable to help…

We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to…

This paper proposes a novel data-driven approach for inertial navigation, which learns to estimate trajectories of natural human motions just from an inertial measurement unit (IMU) in every smartphone. The key observation is that human…

The emerging Internet of Things (IoT) applications, such as driverless cars, have a growing demand for high-precision positioning and navigation. Nowadays, LiDAR inertial odometry becomes increasingly prevalent in robotics and autonomous…