6 datasets found

The Road Group dataset consists of 162 group pairs taken from a 2-camera crowded road scene.

The DukeMTMC Group dataset contains 177 group image pairs extracted from the 8-camera-view DukeMTMC dataset.

The i-LID MCTS dataset contains 274 group images for 64 groups.

This paper introduces STAR, a framework for spatio-temporal crowd trajectory prediction with only attention mechanisms.

The dataset used for crowd counting.

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.