8 papers
BigEarthNet.txt: A Large-Scale Multi-Sensor Image-Text Dataset and Benchmark for Earth Observation
Johann-Ludwig Herzog, Mathis Jürgen Adler, Leonard Hackel +5
Vision-langugage models (VLMs) have shown strong performance in computer vision (CV), yet their performance on remote sensing (RS) data remains limited due to the lack of large-sca…
TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation
Yan Shu, Bin Ren, Zhitong Xiong +4
Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex spatial reasoning in precise pixel-level vis…
ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
Tom Burgert, Oliver Stoll, Paolo Rota +1
The hypothesis that Convolutional Neural Networks (CNNs) are inherently texture-biased has shaped much of the discourse on feature use in deep learning. We revisit this hypothesis…
Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery
Tom Burgert, Leonard Hackel, Paolo Rota +1
Self-supervised learning (SSL) has become a powerful paradigm for learning from large, unlabeled datasets, particularly in computer vision (CV). However, applying SSL to multispect…
Dense Motion Captioning
Shiyao Xu, Benedetta Liberatori, Gül Varol +1
Recent advances in 3D human motion and language integration have primarily focused on text-to-motion generation, leaving the task of motion understanding relatively unexplored. We…
EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM
Yan Shu, Bin Ren, Zhitong Xiong +5
Earth Observation (EO) data analysis is vital for monitoring environmental and human dynamics. Recent Multimodal Large Language Models (MLLMs) show potential in EO understanding bu…