12 datasets found

The VisDrone-SOT2019 dataset is a large-scale drone benchmark for single object tracking.

Object detection on Unmanned Aerial Vehicles (UAVs) is still a challenging task. The recordings are mostly sparse and contain only small objects.

The DTB70 dataset is a large-scale benchmark for drone object detection and tracking.

The image object detection track on VisDrone2018 provides a dataset of 10,209 images, with 10 categories of pedestrians, vehicles, and other traffic objects annotated.

Object permanence is the concept that objects in a physical world continue to exist despite the observers inability to sense them. This can result in temporally unstable...

BEHAVE: Dataset and method for tracking human object interactions.

The BEHAVE dataset is annotated with text descriptions for 3D human-object interactions.

The unmanned aerial vehicle benchmark: Object detection and tracking.

The CARLA dataset is a complex urban-like environment with multi-agent dynamics, pedestrians, intersections, cross-traffic, roundabout, and changing weather conditions.

CrowdHuman is a challenging benchmark to evaluate the ability of crowded scene detection of detectors, which contains about 15k training images and 4k images for evaluation.

LSP dataset: A dataset for human pose estimation and tracking in videos.

MPII Video Pose dataset: A dataset for human pose estimation and tracking in videos.