Related papers: SeisBind: Physics-Aware Tri-Modal Representation B…

LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent…

Incorporating spatial information, particularly those influenced by climate, weather, and demographic factors, is crucial for improving underwriting precision and enhancing risk management in insurance. However, spatial data are often…

We consider the problem of 3D seismic inversion from pre-stack data using a very small number of seismic sources. The proposed solution is based on a combination of compressed-sensing and machine learning frameworks, known as…

Seismic exploration remains the most critical method for characterizing subsurface structures in geophysics. However, complex surface conditions often cause a non-uniform distribution of seismic receivers along survey lines, leading to…

Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. However, most previous works assumed that each view is complete and aligned. This leads to an inevitable deterioration in…

In remote sensing, we are interested in modeling various modalities for some geographic location. Several works have focused on learning the relationship between a location and type of landscape, habitability, audio, textual descriptions,…

Multimodal models have been proven to outperform text-based models on learning semantic word representations. Almost all previous multimodal models typically treat the representations from different modalities equally. However, it is…

Contrastive learning methods, such as CLIP, leverage naturally paired data-for example, images and their corresponding text captions-to learn general representations that transfer efficiently to downstream tasks. While such approaches are…

Image-based object pose estimation sounds amazing because in real applications the shape of object is oftentimes not available or not easy to take like photos. Although it is an advantage to some extent, un-explored shape information in 3D…

With the advancement of artificial intelligence and computer vision technologies, multimodal emotion recognition has become a prominent research topic. However, existing methods face challenges such as heterogeneous data fusion and the…

Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient…

Deploying depth estimation networks in the real world requires high-level robustness against various adverse conditions to ensure safe and reliable autonomy. For this purpose, many autonomous vehicles employ multi-modal sensor systems,…

The excavation process in mechanized tunneling can be improved by reconnaissance of the geology ahead. A nondestructive exploration can be achieved in means of seismic imaging. A full waveform inversion approach, which works in the…

As medical diagnoses increasingly leverage multimodal data, machine learning models are expected to effectively fuse heterogeneous information while remaining robust to missing modalities. In this work, we propose a novel multimodal…

Recent advances in vision language models (VLM) have been driven by contrastive models such as CLIP, which learn to associate visual information with their corresponding text descriptions. However, these models have limitations in…

Deep learning can extract rich data representations if provided sufficient quantities of labeled training data. For many tasks however, annotating data has significant costs in terms of time and money, owing to the high standards of subject…

Multimodal representation alignment is pivotal for large language models and robotics. Traditional methods are often hindered by cross-modal information discrepancies and data scarcity, leading to suboptimal alignment spaces that overlook…

The problem of learning from seismic recordings has been studied for years. There is a growing interest in developing automatic mechanisms for identifying the properties of a seismic event. One main motivation is the ability have a reliable…

Multimodal Sentiment Analysis leverages multimodal signals to detect the sentiment of a speaker. Previous approaches concentrate on performing multimodal fusion and representation learning based on general knowledge obtained from pretrained…

3D visual grounding aims to automatically locate the 3D region of the specified object given the corresponding textual description. Existing works fail to distinguish similar objects especially when multiple referred objects are involved in…