Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos

• Published in: arXiv.org
• Main Authors: Md Zahid Hasan, Chen, Jiajing, Wang, Jiyang, Rahman, Mohammed Shaiqur, Joshi, Ameya, Velipasalar, Senem, Hegde, Chinmay, Sharma, Anuj, Sarkar, Soumik
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 21.03.2024
• Subjects: Activity recognition; Classification; Computer vision; Distracted driving; Driver behavior; Learning; Natural language (computers); Pedestrians; Representations; Training; Video data

Recognizing the activities causing distraction in real-world driving scenarios is critical for ensuring the safety and reliability of both drivers and pedestrians on the roadways. Conventional computer vision techniques are typically data-intensive and require a large volume of annotated training da...