3 papers
cs.CV2026
SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion
Timing Li, Yiming Sun, Boan Tao +3
Spatial misregistration and cross-modal discrepancies often cause ghosting, structural blurring, and content imbalance in RGB-T fusion. Existing methods typically decouple appearan…
cs.CV2026
Socialized Detector Learning: Trajectory-Guided and Reciprocal Distillation for Heterogeneous Object Detectors
Weihao Li, Yunqi Zhu, Zhihe Fan +5
Object detection knowledge is fragmented across independently trained, heterogeneous detectors with complementary category supports. In socialized learning, this knowledge resides…
cs.CV2026
Rethinking Air-Ground Collaboration: A Progressive Cross-Task Benchmark and Socialized Learning Framework
Zhoupeng Guo, Yunqi Zhu, Zhihe Fan +6
Air-ground collaborative perception is crucial for robust visual understanding in real-world dynamic environments. However, existing studies typically formulate collaboration as si…