Manuel Martin — accepted AI-conference papers

2026

FlowNar: Scalable Streaming Narration for Long-Form Videos

Zeyun Zhong, Manuel Martin, Chengzhi Wu, David Schneider, Frederik DIEDERICHS, Juergen Gall +1

ICML 2026poster

Recent Large Multimodal Models (LMMs), primarily designed for offline settings, are ill-suited for the dynamic requirements of streaming video. While recent online adaptations improve real-time processing, they still face critical scalability challenges, with resource demands typically growing at le…

Cited by 0 Source ↗Scholar ↗

2019

Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles

Manuel Martin, Alina Roitberg, Monica Haurilet, Matthias Horne, Simon Reiss, Michael Voit +1

ICCV 2019poster

We introduce the novel domain-specific Drive&Act benchmark for fine-grained categorization of driver behavior. Our dataset features twelve hours and over 9.6 million frames of people engaged in distractive activities during both, manual and automated driving. We capture color, infrared, depth and 3D…

Cited by 243 PDF ↗Scholar ↗