Search papers, labs, and topics across Lattice.
Karlsruhe Institute of Technology (KIT)
3
0
4
HOWTransfer achieves an 86% success rate in translating human hand motions into robot actions, surpassing teleoperation in user preference.
Fine-tuning vision-language models on a richly described dataset boosts their accuracy in interpreting subtle driver actions by 10 points, revealing a critical gap in existing training methods.
Faulty negatives and unreliable positives can be effectively managed in multi-modal learning, leading to significant improvements in driver distraction detection accuracy.
