相关论文: EMMA: Extracting Multiple physical parameters from…

We introduce a method for constructing reduced-order models directly from videos of dynamical systems. The method uses a non-intrusive tracking to isolate the motion of a user-selected part in the video of an autonomous dynamical system. In…

A common practice in metric learning is to train and test an embedding model for each dataset. This dataset-specific approach fails to simulate real-world scenarios that involve multiple heterogeneous distributions of data. In this regard,…

We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, our model has precise control over object dynamics, ego-agent…

We introduce physics-informed multimodal autoencoders (PIMA) - a variational inference framework for discovering shared information in multimodal scientific datasets representative of high-throughput testing. Individual modalities are…

Precise video retrieval requires multi-modal correlations to handle unseen vocabulary and scenes, becoming more complex for lengthy videos where models must perform effectively without prior training on a specific dataset. We introduce a…

Multimodal foundation models that can holistically process text alongside images, video, audio, and other sensory modalities are increasingly used in a variety of real-world applications. However, it is challenging to characterize and study…

Dynamical systems form the foundation of scientific discovery, traditionally modeled with predefined state variables such as the angle and angular velocity, and differential equations such as the equation of motion for a single pendulum. We…

Inferring dynamics from time series is an important objective in data analysis. In particular, it is challenging to infer stochastic dynamics given incomplete data. We propose an expectation maximization (EM) algorithm that iterates between…

Multimodal Deep Learning enhances decision-making by integrating diverse information sources, such as texts, images, audio, and videos. To develop trustworthy multimodal approaches, it is essential to understand how uncertainty impacts…

EEG-based recognition of activities and states involves the use of prior neuroscience knowledge to generate quantitative EEG features, which may limit BCI performance. Although neural network-based methods can effectively extract features,…

Turbulence mitigation (TM) is highly ill-posed due to the stochastic nature of atmospheric turbulence. Most methods rely on multiple frames recorded by conventional cameras to capture stable patterns in natural scenarios. However, they…

We present MAMMA, a markerless motion-capture pipeline that accurately recovers SMPL-X parameters from multi-view video of two-person interaction sequences. Traditional motion-capture systems rely on physical markers. Although they offer…

The current paper implements a methodology for automatically detecting vehicle maneuvers from vehicle telemetry data under naturalistic driving settings. Previous approaches have treated vehicle maneuver detection as a classification…

Recently, action recognition has been dominated by transformer-based methods, thanks to their spatiotemporal contextual aggregation capacities. However, despite the significant progress achieved on scene-related datasets, they do not…

Dynamical systems are ubiquitous within science and engineering, from turbulent flow across aircraft wings to structural variability of proteins. Although some systems are well understood and simulated, scientific imaging often confronts…

Gesture recognition is a much studied research area which has myriad real-world applications including robotics and human-machine interaction. Current gesture recognition methods have focused on recognising isolated gestures, and existing…

Large Language Models (LLMs) have allowed recent LLM-based approaches to achieve excellent performance on long-video understanding benchmarks. We investigate how extensive world knowledge and strong reasoning skills of underlying LLMs…

In this article, we introduce a modular hybrid analysis and modeling (HAM) approach to account for hidden physics in reduced order modeling (ROM) of parameterized systems relevant to fluid dynamics. The hybrid ROM framework is based on…

In autonomous driving, relying solely on frame-based cameras can lead to inaccuracies caused by factors like long exposure times, high-speed motion, and challenging lighting conditions. To address these issues, we introduce a bio-inspired…

In e-commerce, accurately extracting product attribute values from multimodal data is crucial for improving user experience and operational efficiency of retailers. However, previous approaches to multimodal attribute value extraction often…