Related papers: GeoViSTA: Geospatial Vision-Tabular Transformer fo…
Thermal imaging is crucial for scene understanding, particularly in low-light and nighttime conditions. However, collecting large thermal datasets is costly and labor-intensive due to the specialized equipment required for infrared image…
This thesis focuses on data that has complex spatio-temporal structure and on probabilistic graphical models that learn the structure in an interpretable and scalable manner. We target two research areas of interest: Gaussian graphical…
Table structure recognition aims to extract the logical and physical structure of unstructured table images into a machine-readable format. The latest end-to-end image-to-text approaches simultaneously predict the two structures by two…
Multi-view camera-based 3D detection is a challenging problem in computer vision. Recent works leverage a pretrained LiDAR detection model to transfer knowledge to a camera-based student network. However, we argue that there is a major…
Real-world multimodal agents solve multi-step workflows grounded in visual evidence. For example, an agent can troubleshoot a device by linking a wiring photo to a schematic and validating the fix with online documentation, or plan a trip…
Visual place recognition is a challenging task for applications such as autonomous driving navigation and mobile robot localization. Distracting elements presenting in complex scenes often lead to deviations in the perception of visual…
Foundation models have made rapid advances in many domains including Earth observation, where Geospatial Foundation Models (GFMs) can help address global challenges such as climate change, agriculture, and disaster response. Previous work…
Geovisualizations are powerful tools for exploratory spatial analysis, enabling sighted users to discern patterns, trends, and relationships within geographic data. However, these visual tools have remained largely inaccessible to…
Multi-camera 3D object detection for autonomous driving is a challenging problem that has garnered notable attention from both academia and industry. An obstacle encountered in vision-based techniques involves the precise extraction of…
Geovisualizations are powerful tools for communicating spatial information, but are inaccessible to screen-reader users. To address this limitation, we present GeoVisA11y, an LLM-based question-answering system that makes geovisualizations…
We present a multi-modal foundation model for astrophysical galaxy data, designed to map between simulation- and observation-based galactic features. Our encoder-only transformer flexibly ingests scalar quantities (e.g., redshifts, galaxy…
Self-supervised vision models have achieved notable success in digital pathology. However, their domain-agnostic transformer architectures are not originally designed to account for fundamental biological elements of histopathology images,…
Precise spatial understanding in Earth Observation is essential for translating raw aerial imagery into actionable insights for critical applications like urban planning, environmental monitoring and disaster management. However, Multimodal…
Recent self-supervised learning (SSL) methods have demonstrated impressive results in learning visual representations from unlabeled remote sensing images. However, most remote sensing images predominantly consist of scenographic scenes…
With a large amount of open satellite multispectral imagery (e.g., Sentinel-2 and Landsat-8), considerable attention has been paid to global multispectral land cover classification. However, its limited spectral information hinders further…
Learning inter-image similarity is crucial for 3D medical images self-supervised pre-training, due to their sharing of numerous same semantic regions. However, the lack of the semantic prior in metrics and the semantic-independent variation…
Vision-Language-Action (VLA) models have shown strong potential for general-purpose robot manipulation by unifying perception and action. However, existing VLA systems primarily rely on textual instructions and struggle to resolve spatial…
To overcome the restriction of identical distribution assumption, invariant representation learning for unsupervised domain adaptation (UDA) has made significant advances in computer vision and pattern recognition communities. In UDA…
Conventional Vision Transformer simplifies visual modeling by standardizing input resolutions, often disregarding the variability of natural visual data and compromising spatial-contextual fidelity. While preliminary explorations have…
Spatial-temporal graph learning has emerged as a promising solution for modeling structured spatial-temporal data and learning region representations for various urban sensing tasks such as crime forecasting and traffic flow prediction.…