ITSC 2025 Paper Abstract

Paper FR-LM-T44.2

Thiyakesan Ponbagavathi, Thinesh (University of Stuttgart), Peng, Kunyu (Karlsruhe Institute of Technology), Roitberg, Alina (University of Stuttgart)

T-MASK: Temporal Masking for Probing Foundation Models across Camera Views in Driver Monitoring

Scheduled for presentation during the Regular Session "S44a-Human Factors and Human Machine Interaction in Automated Driving" (FR-LM-T44), Friday, November 21, 2025, 10:50−11:10, Currumbin

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Driver Behavior Monitoring and Feedback Systems for Semi-autonomous Vehicles, Human-Machine Interaction Systems for Enhanced Driver Assistance and Safety

Abstract

Changes of camera perspective are a common obstacle in driver monitoring. While deep learning and pretrained foundation models show strong potential for improved generalization via lightweight adaptation of the final layers (“probing”), their robustness to unseen viewpoints remains underexplored. We study this challenge by adapting image foundation models to driver monitoring using a single training view, and evaluating them directly on unseen perspectives without further adaptation. We benchmark simple linear probes, advanced probing strategies, and compare two foundation models (DINOv2 and CLIP) against parameter-efficient fine-tuning (PEFT) and full fine-tuning. Building on these insights, we introduce T-MASK – a new image-to-video probing method that leverages temporal token masking and emphasizes more dynamic video regions. Benchmarked on the public Drive&Act dataset, T-MASK improves cross-view top-1 accuracy by +1.23% over strong probing baselines and +8.0% over PEFT methods, without adding any parameters. It proves particularly effective for underrepresented secondary activities, boosting recognition by +5.42% under the trained view and +1.36% under cross-view settings. This work provides encouraging evidence that adapting foundation models with lightweight probing methods like T-MASK has strong potential in fine-grained driver observation, especially in cross- view and low-data settings. These results highlight the importance of temporal token selection when leveraging foundation models to build robust driver monitoring systems. Code and models will be made available to support ongoing research.