With the rapid advancements in autonomous driving, accurately predicting pedestrian behavior has become essential for ensuring safety in complex and unpredictable traffic conditions. The growing inter
We introduce RoadSocial, a large-scale, diverse VideoQA dataset tailored for generic road event understanding from social media narratives. Unlike existing datasets limited by regional bias, viewpoint
This dataset aims at facilitating research in the domain of driving behavior, particularly for 2 wheelers in an Indian Urban traffic setting. The dataset provides visual data (2-4 streams) alongside I
Real-world multimodal rider safety dataset containing radar, IMU, GPS, velocity, braking, and mobility sensing data collected from an instrumented e-cycle platform for intelligent transportation and s
The problem statement is to develop an algorithm for detecting autorickshaws in images and drawing bounding boxes around them. The challenge is to accurately detect the autorickshaws despite variation
