3 papers
cs.CV2026
SpatialV2A: Visual-Guided High-fidelity Spatial Audio Generation
Yanan Wang, Linjie Ren, Zihao Li +2
While video-to-audio generation has achieved remarkable progress in semantic and temporal alignment, most existing studies focus solely on these aspects, paying limited attention t…
cs.SD2025
Error-Resilient Semantic Communication for Speech Transmission over Packet-Loss Networks
Zhuohang Han, Jincheng Dai, Shengshi Yao +5
Real-time speech communication over wireless networks remains challenging, as conventional channel protection mechanisms cannot effectively counter packet loss under stringent band…
cs.CV2025
Prototype-Driven Structure Synergy Network for Remote Sensing Images Segmentation
Junyi Wang, Jinjiang Li, Guodong Fan +3
In the semantic segmentation of remote sensing images, acquiring complete ground objects is critical for achieving precise analysis. However, this task is severely hindered by two…