Scholay

学术搜索 · AI 审稿 · LaTeX 协作

Ming-Hsuan Yang

发表论文 55 篇 · 总被引 787 次 · h-index 14

代表论文

  • Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos. (2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 被引 167)
  • Exploring plain ViT features for multi-class unsupervised visual anomaly detection (2025 · Computer Vision and Image Understanding · 被引 44)
  • Gemma 4 Technical Report (2026 · 被引 43)
  • One Flight Over the Gap: A Survey from Perspective to Panoramic Vision (2025 · arXiv.org · 被引 26)
  • Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation (2025 · arXiv.org · 被引 21)
  • DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency (2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 被引 19)