7 datasets found

Tags: crowded scenes

Filter Results

  • UCSD dataset

    The UCSD dataset is a benchmark for the analysis of abnormal detection and localization in crowded scenes.

  • MOT20

    The dataset used for the MOT20 challenge, which consists of 8 different sequences depicting very crowded challenging scenes.

  • UCY

    Pedestrian trajectory prediction is an important component in a range of applications such as social robots and self-driving vehicles, and plays a key role in understanding...

  • ETH

    Pedestrian trajectory forecasting is a fundamental task in multiple utility areas, such as self-driving, autonomous robots, and surveillance systems. The future trajectory...

  • MOSE 2023

    MOSE 2023 dataset is a novel VOS benchmark featuring extreme scenarios of the video sequence which are not handled good enough by existing VOS methods.

  • APOLLO MOTS

    More challenging MOTS dataset with higher instance density and crowded scenes.

  • UCSD Ped2

    A benchmark for anomaly detection in crowded scenes. It contains 19600 frames captured using two different cameras.
You can also access this registry using the API (see API Docs).