Related papers: LaDy: Lagrangian-Dynamic Informed Network for Skel…
The Sparse Identification of Nonlinear Dynamics (SINDy) framework has been frequently used to discover parsimonious differential equations governing natural and physical systems. This includes recent extensions to SINDy that enable the…
Effectively modeling discriminative spatio-temporal information is essential for segmenting activities in long action sequences. However, we observe that existing methods are limited in weak spatio-temporal modeling capability due to two…
In recent years, there has been renewed interest in developing methods for skeleton-based human action recognition. A skeleton sequence can be naturally represented as a high-order tensor time series. In this paper, we model and analyze…
Exploring the intersection of deterministic and stochastic dynamics, this paper delves into Lagrangian discovery for conservative and non-conservative systems under stochastic excitation. Traditional Lagrangian frameworks, adept at…
Solving stiff ordinary differential equations (StODEs) requires sophisticated numerical solvers, which are often computationally expensive. In general, traditional explicit time integration schemes with restricted time step sizes are not…
To assist surgeons in the operating theatre, surgical phase recognition is critical for developing computer-assisted surgical systems, which requires comprehensive understanding of surgical videos. Although existing studies made great…
Robot-mediated human-human (dyadic) interactions enable therapists to provide physical therapy remotely, yet an accurate perception of patient stiffness remains challenging due to network-induced haptic delays. Conventional stiffness…
Hybrid dynamical systems, which include continuous flow and discrete mode switching, can model robotics tasks like legged robot locomotion. Model-based methods usually depend on predefined gaits, while model-free approaches lack explicit…
Event cameras record luminance changes with microsecond resolution, but converting their sparse, asynchronous output into dense tensors that neural networks can exploit remains a core challenge. Conventional histograms or globally-decayed…
Current state-of-the-art methods for skeleton-based temporal action segmentation are predominantly supervised and require annotated data, which is expensive to collect. In contrast, existing unsupervised temporal action segmentation methods…
As a network-based functional approximator, we have proposed a "Lagrangian Density Space-Time Deep Neural Networks" (LDDNN) topology. It is qualified for unsupervised training and learning to predict the dynamics of underlying physical…
Data-driven discovery of governing equations from data remains a fundamental challenge in nonlinear dynamics. Although sparse regression techniques have advanced system identification, they struggle with rational functions and noise…
Group Activity Understanding is predominantly studied as Group Activity Recognition (GAR) task. However, existing GAR benchmarks suffer from coarse-grained activity vocabularies and the only data form in single-view, which hinder the…
Effective and Efficient spatio-temporal modeling is essential for action recognition. Existing methods suffer from the trade-off between model performance and model complexity. In this paper, we present a novel Spatio-Temporal Hybrid…
We propose a new loss function that we call Laplacian loss, based on spatio-temporal Laplacian representation of the motion as a graph. This loss function is intended to be used in training models for motion reconstruction through 3D human…
Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS methodologies face challenges of limited inter-class…
Lagrangian descriptors reveal the dynamical skeleton governing transport mechanisms of a generic flow. In doing so, they unveil geometrical structures in the phase space that separate regions with different qualitative behavior. This work…
Oceanic surface flows are dominated by finite-time Lagrangian coherent structures that separate regions of qualitatively different dynamical behavior. Among these, eddy boundaries are of particular interest. Their exact identification is…
Learning interpretable representations of neural dynamics at a population level is a crucial first step to understanding how observed neural activity relates to perception and behavior. Models of neural dynamics often focus on either…
Commonly, SLAM algorithms are focused on a static environment, however, there are several scenes where dynamic objects are present. This work presents the STDyn-SLAM an image feature-based SLAM system working on dynamic environments using a…