PDF(8680 KB)
PDF(8680 KB)
FSS-VLM:基于细粒度跳跃连接和时空融合的驾驶视频问答模型
FSS-VLM: A Driving Video Question Answering Model Based on Fine-Grained Skip Connections and Spatio-Temporal Fusion
| {{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
| 〈 |
|
〉 |