Baoqi Pei

机构：Zhejiang University

发表论文 21 篇 · 总被引 264 次 · h-index 5

代表论文

• InternVideo2: Scaling Foundation Models for Multimodal Video Understanding (2024 · Lecture notes in computer science · 被引 145)
• EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World (2024 · 被引 39)
• Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding (2025 · International Journal of Computer Vision · 被引 33)
• Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding (2024 · arXiv (Cornell University) · 被引 19)
• InternVideo2: Scaling Foundation Models for Multimodal Video Understanding (2024 · arXiv (Cornell University) · 被引 16)
• Guiding Audio-Visual Question Answering with Collective Question Reasoning (2025 · International Journal of Computer Vision · 被引 5)