Linhui Xiao

机构：Chinese Academy of Sciences · ORCID：0000-0003-2592-5264

发表论文 17 篇 · 总被引 658 次 · h-index 8

代表论文

• Dynamic-SLAM: Semantic monocular visual localization and mapping based on deep learning in dynamic environment (2019 · Robotics Auton. Syst. · 被引 344)
• SgVA-CLIP: Semantic-Guided Visual Adapting of Vision-Language Models for Few-Shot Image Classification (2022 · IEEE transactions on multimedia · 被引 91)
• CLIP-VG: Self-Paced Curriculum Adapting of CLIP for Visual Grounding (2023 · IEEE transactions on multimedia · 被引 90)
• Toward Visual Grounding: A Survey (2024 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 被引 63)
• HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding (2024 · ACM Multimedia · 被引 53)
• OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling (2024 · Neural Information Processing Systems · 被引 40)