5 papers
Does Your Wildfire Prediction Model Actually Work, or Just Score Well?
Yangshuang Xu, Yuyang Dai, Liling Chang +2
Wildfire prediction is important for early warning and resource allocation, yet existing Earth foundation models (Earth FMs) are pretrained for general atmospheric and geophysical…
STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection
Yaoteng Zhang, Qing Zhou, Junyu Gao +1
Remote sensing imagery typically arrives in the form of continuous data streams. Traditional detectors often forget previously learned categories when learning new ones; therefore,…
Discriminative Perception via Anchored Description for Reasoning Segmentation
Tao Yang, Qing Zhou, Yanliang Li +1
Reasoning segmentation increasingly employs reinforcement learning to generate explanatory reasoning chains that guide Multimodal Large Language Models. While these geometric rewar…
Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection
Yaoteng Zhang, Zhou Qing, Junyu Gao +1
Incremental Object Detection (IOD) aims to continuously learn new object categories without forgetting previously learned ones. Recently, prompt-based methods have gained popularit…
STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery
Yansheng Li, Linlin Wang, Tingzhu Wang +11
Scene graph generation (SGG) in satellite imagery (SAI) benefits promoting understanding of geospatial scenarios from perception to cognition. In SAI, objects exhibit great variati…