6 papers
SynCLIP: Synonym-Coherent Language-Image Pretraining for Robust Open-Vocabulary Dense Perception
Mingjie Xie, Guangjun He, Dongli Xu +5
The paper introduces SynCLIP, a language‑image pretraining framework that aligns spatial attention across synonymous textual expressions to improve the robustness of open‑vocabular…
Bridging Perception and Action: A Lightweight Multimodal Meta-Planner Framework for Robust Earth Observation Agents
Jinghui Xu, Boyi Shangguan, Mengke Zhu +10
Autonomous Earth Observation (EO) agents are transitioning from passive perception to complex, multi-step task execution. However, current architectures that integrate planning and…
Physics-Aware Novel-View Acoustic Synthesis with Vision-Language Priors and 3D Acoustic Environment Modeling
Congyi Fan, Jian Guan, Youtian Lin +5
Spatial audio is essential for immersive experiences, yet novel-view acoustic synthesis (NVAS) remains challenging due to complex physical phenomena such as reflection, diffraction…
Dual-level Progressive Hardness-Aware Reweighting for Cross-View Geo-Localization
Guozheng Zheng, Jian Guan, Mingjie Xie +4
Cross-view geo-localization (CVGL) between drone and satellite imagery remains challenging due to severe viewpoint gaps and the presence of hard negatives, which are visually simil…
Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation
Congyi Fan, Jian Guan, Xuanjia Zhao +5
Automatically generating natural, diverse and rhythmic human dance movements driven by music is vital for virtual reality and film industries. However, generating dance that natura…
Band Prompting Aided SAR and Multi-Spectral Data Fusion Framework for Local Climate Zone Classification
Haiyan Lan, Shujun Li, Mingjie Xie +6
Local climate zone (LCZ) classification is of great value for understanding the complex interactions between urban development and local climate. Recent studies have increasingly f…