$$\mathrm R^2$$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

作者：Ye Liu, Jixuan He, Wanhua Li, Junsik Kim, Donglai Wei, Hanspeter Pfister, Chang Wen Chen · 发表于：Lecture notes in computer science · 年份：2024 · DOI：10.1007/978-3-031-72940-9_24 · 被引用次数：8 · 研究领域：Video Analysis and Summarization、Human Pose and Action Recognition、Multimodal Machine Learning Applications