EarthDial: Turning Multi-sensory Earth Observations to Interactive DialoguesSagar SoniAkshay Dudhaneet al.2025CVPR 2025
CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained AlignmentEdson AraujoAndrew Rouditchenkoet al.2025CVPR 2025
MarkushGrapher: Joint Visual and Textual Recognition of Markush StructuresLucas MorinValery Weberet al.2025CVPR 2025
Granite Vision: A Demo for Efficient Visual Document UnderstandingPengyuan LiGranite Vision Team2025CVPR 2025
VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic SegmentationNiccolo AvogaroThomas Fricket al.2025CVPR 2025
TerraMesh: A Planetary Mosaic of Multimodal Earth Observation DataBenedikt BlumenstielPaolo Fraccaroet al.2025CVPR 2025
The 2025 CVPR EARTHVISION Data Challenge by Embed2ScaleConrad AlbrechtJannik Schneideret al.2025CVPR 2025