3 papers
cs.CV2026
Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification
Francisco Mena, Dino Ienco, Roberto Interdonato +2
Multi-modal classification leverages complementary information across diverse data sources to enhance predictive performance. However, real-world scenarios subject to operational c…
cs.CV2026
Biomazon: A Multimodal Dataset for 3D Forest Structure and Biomass Modeling in the Amazon Basin
Sayan Mandal, Rocco Sedona, Simon Besnard +4
Accurate, spatially explicit characterization of tropical forest structure is essential for carbon accounting and ecosystem monitoring, yet most ML pipelines predict canopy-top hei…
cs.CV2025
HyBiomass: Global Hyperspectral Imagery Benchmark Dataset for Evaluating Geospatial Foundation Models in Forest Aboveground Biomass Estimation
Aaron Banze, Timothée Stassin, Nassim Ait Ali Braham +3
Comprehensive evaluation of geospatial foundation models (Geo-FMs) requires benchmarking across diverse tasks, sensors, and geographic regions. However, most existing benchmark dat…