Si Liu

机构：National Research Tomsk State University, Artificial Intelligence Research Institute, Beihang University · ORCID：0000-0002-9180-2935

发表论文 345 篇 · 总被引 14602 次 · h-index 57

代表论文

• DiffUIE: Learning Latent Global Priors in Diffusion Models for Underwater Image Enhancement (2024 · IEEE Transactions on Multimedia · 被引 31)
• LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding (2025 · 被引 16)
• MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection (2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 被引 14)
• AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation (2025 · 被引 6)
• Generative Map Priors for Collaborative BEV Semantic Segmentation (2025 · 被引 4)
• Revisiting Audio-Visual Segmentation with Vision-Centric Transformer (2025 · 被引 3)