3 datasets found

Formats: JSON Tags: CrowdHuman

Filter Results

  • MOT17 half-half

    The proposed architecture is described in Fig. 3 which is based on TransTrack [21] with several improvements to reduce the computational complexity and model size.

  • CrowdHuman

    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.

  • MOT17

    Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based...
You can also access this registry using the API (see API Docs).