4 datasets found

A large-scale dataset for video scene parsing in the wild.

Video scene parsing in the wild with diverse scenarios is a challenging and great significance task, especially with the rapid development of automatic driving technique. The...

The VIPSeg dataset, which is a benchmark for video scene parsing.

The VSPW dataset is a large-scale dataset for video scene parsing in the wild, containing 2,806 videos with 480x853 pixel frames and 124 semantic categories.