Learning text-to-video retrieval from image captioning

[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning‏

J Li, Z Wang, J Zheng, X Zhou, G Wang, G Song… - arxiv preprint arxiv …, 2024‏ - arxiv.org‏
Multimodal task specification is essential for enhanced robotic performance, where\textit
{Cross-modality Alignment} enables the robot to holistically understand complex task …‏
حفظ اقتباس تم اقتباسها في عدد: 1 مقالات ذات صلة الإصدارات الـ 3كلها إصدار HTML‏