5 papers
MGRL-RSCC: Multi-Granularity Reward Reinforcement Learning for Fine-Grained Remote Sensing Change Captioning
Futian Wang, Mengqi Wang, Xiao Wang +4
Remote Sensing Change Captioning (RSCC), which aims to generate accurate and detailed linguistic descriptions of ground object variations from bi-temporal remote sensing images, is…
DRGBT-1K: A Large-scale High-quality Benchmark for Dynamic RGBT Tracking
Zhaodong Ding, Chenglong Li, Zeyu Ding +2
Dynamic RGBT (DRGBT) tracking aims to continuously localize a target when the available sensing modalities and observation platforms vary over time. Compared with conventional RGBT…
DialBench: Towards Accurate Reading Recognition of Pointer Meter using Large Foundation Models
Futian Wang, Chaoliu Weng, Xiao Wang +3
The precise reading recognition of pointer meters plays a key role in smart power systems, but existing approaches remain fragile due to challenges like reflections, occlusions, dy…
EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation
Futian Wang, Fan Zhang, Xiao Wang +3
Event cameras produce asynchronous event streams that are spatially sparse yet temporally dense. Mainstream event representation learning algorithms typically use event frames, vox…
SAM Guided Semantic and Motion Changed Region Mining for Remote Sensing Change Captioning
Futian Wang, Mengqi Wang, Xiao Wang +2
Remote sensing change captioning is an emerging and popular research task that aims to describe, in natural language, the content of interest that has changed between two remote se…