TY - CONF
T1 - Semi-supervised Learning
T2 - Fusion of Self-supervised, Supervised Learning, and Multimodal Cues for Tactical Driver Behavior Detection
AU - Narayanan, Athma
AU - Chen, Yi-Ting
AU - Malla, Srikanth
PY - 2018/7
Y1 - 2018/7
N2 - In this paper, we presented a preliminary study for tactical driver behavior detection from untrimmed naturalistic driving recordings. While supervised learning based detection is a common approach, it suffers when labeled data is scarce. Manual annotation is both time-consuming and expensive. To emphasize this problem, we experimented on a 104-hour real-world naturalistic driving dataset with a set of predefined driving behaviors annotated. There are three challenges in the dataset. First, predefined driving behaviors are sparse in a naturalistic driving setting. Second, the distribution of driving behaviors is long-tail. Third, a huge intra-class variation is observed. To address these issues, recent self-supervised and supervised learning and fusion of multimodal cues are leveraged into our architecture design. Preliminary experiments and discussions are reported.
AB - In this paper, we presented a preliminary study for tactical driver behavior detection from untrimmed naturalistic driving recordings. While supervised learning based detection is a common approach, it suffers when labeled data is scarce. Manual annotation is both time-consuming and expensive. To emphasize this problem, we experimented on a 104-hour real-world naturalistic driving dataset with a set of predefined driving behaviors annotated. There are three challenges in the dataset. First, predefined driving behaviors are sparse in a naturalistic driving setting. Second, the distribution of driving behaviors is long-tail. Third, a huge intra-class variation is observed. To address these issues, recent self-supervised and supervised learning and fusion of multimodal cues are leveraged into our architecture design. Preliminary experiments and discussions are reported.
U2 - 10.48550/arXiv.1807.00864
DO - 10.48550/arXiv.1807.00864
M3 - Paper
SP - 1
EP - 3
ER -