GeoMMBench reveals deficiencies in current multimodal LLMs for geoscience tasks while GeoMMAgent demonstrates that tool-integrated agents achieve significantly higher performance.
Dota: A large-scale dataset for object detection in aerial images
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
A Twins-SVT vision transformer backbone with multiscale CNN decoder and Category Focus Module auxiliary task reduces MAE by 33-64% on VisDrone and iSAID multi-class counting benchmarks versus prior density estimators.
citing papers explorer
-
GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing
GeoMMBench reveals deficiencies in current multimodal LLMs for geoscience tasks while GeoMMAgent demonstrates that tool-integrated agents achieve significantly higher performance.
-
Getting the Numbers Right$\unicode{x2014}$Modelling Multi-Class Object Counting in Dense and Varied Scenes
A Twins-SVT vision transformer backbone with multiscale CNN decoder and Category Focus Module auxiliary task reduces MAE by 33-64% on VisDrone and iSAID multi-class counting benchmarks versus prior density estimators.