2 datasets found

Formats: JSON Tags: video datasets

Filter Results

  • MOT Challenge

    Object detectors are vital to many modern computer vision applications. However, even state-of-the-art object detectors exhibit inconsistent behavior when the input undergoes...

  • Video In-Context Learning

    Video In-Context Learning (Vid-ICL) is a novel framework that extends in-context learning to video data.
You can also access this registry using the API (see API Docs).