類似資料

• BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
  著者:: Islam, Md Mohaiminul, 等
  出版事項: (2025)
• Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
  著者:: Wang, Ziyang, 等
  出版事項: (2025)
• LoCoNet: Long-Short Context Network for Active Speaker Detection
  著者:: Wang, Xizi, 等
  出版事項: (2023)
• A Simple LLM Framework for Long-Range Video Question-Answering
  著者:: Zhang, Ce, 等
  出版事項: (2023)
• Video ReCap: Recursive Captioning of Hour-Long Videos
  著者:: Islam, Md Mohaiminul, 等
  出版事項: (2024)