collaborators

8 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…