Related papers: PAINET: A Principled Efficient Transformer for 3D …

Tracking the 6D pose of objects in video sequences is important for robot manipulation. This task, however, introduces multiple challenges: (i) robot manipulation involves significant occlusions; (ii) data and annotations are troublesome…

Let us rethink the real-world scenarios that require human motion prediction techniques, such as human-robot collaboration. Current works simplify the task of predicting human motions into a one-off process of forecasting a short future…

Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of human skeleton representations. To address this issue, we…

Transformer architecture has emerged to be successful in a number of natural language processing tasks. However, its applications to medical vision remain largely unexplored. In this study, we present UTNet, a simple yet powerful hybrid…

Accurate modeling of personalized cardiovascular dynamics is crucial for non-invasive monitoring and therapy planning. State-of-the-art physics-informed neural network (PINN) approaches employ deep, multi-branch architectures with…

Manipulating deformable objects is a ubiquitous task in household environments, demanding adequate representation and accurate dynamics prediction due to the objects' infinite degrees of freedom. This work proposes DeformNet, which utilizes…

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied…

Solving Partial Differential Equations (PDEs) is the core of many fields of science and engineering. While classical approaches are often prohibitively slow, machine learning models often fail to incorporate complete system information.…

Existing view-based methods excel at recognizing 3D objects from predefined viewpoints, but their exploration of recognition under arbitrary views is limited. This is a challenging and realistic setting because each object has different…

Simulation and optimization are crucial for advancing the engineering design of complex systems and processes. Traditional optimization methods require substantial computational time and effort due to their reliance on resource-intensive…

In real-world robotics applications, accurate models of robot dynamics are critical for safe and stable control in rapidly changing operational conditions. This motivates the use of machine learning techniques to approximate robot dynamics…

Automated segmentation of diabetic foot ulcers (DFUs) plays a critical role in clinical diagnosis, therapeutic planning, and longitudinal wound monitoring. However, this task remains challenging due to the heterogeneous appearance,…

SO(3) equivariant graph neural networks have become the dominant paradigm for atomistic foundation models, achieving high accuracy and data efficiency by building rotational symmetry directly into the architecture. Yet the computational…

Message passing neural networks have become a method of choice for learning on graphs, in particular the prediction of chemical properties and the acceleration of molecular dynamics studies. While they readily scale to large training data…

Antibody design is valuable for therapeutic usage and biological research. Existing deep-learning-based methods encounter several key issues: 1) incomplete context for Complementarity-Determining Regions (CDRs) generation; 2) incapability…

Deep learning models tend to underperform in the presence of domain shifts. Domain transfer has recently emerged as a promising approach wherein images exhibiting a domain shift are transformed into other domains for augmentation or…

Machine Learning surrogates for Computational Fluid Dynamics (CFD), particularly Graph Neural Networks (GNNs) and Transformers, have become a new important approach for accelerating physics simulations. However, we identify a critical…

Imitation learning, e.g., diffusion policy, has been proven effective in various robotic manipulation tasks. However, extensive demonstrations are required for policy robustness and generalization. To reduce the demonstration reliance, we…

We introduce PhysXNet, a learning-based approach to predict the dynamics of deformable clothes given 3D skeleton motion sequences of humans wearing these clothes. The proposed model is adaptable to a large variety of garments and changing…

Dance improvisation is an active research topic in the arts. Motion analysis of improvised dance can be challenging due to its unique dynamics. Data-driven dance motion analysis, including recognition and generation, is often limited to…