Loading...
Loading...
Available on 1 platform
Sign in to view source links and access this dataset
VCBench contains 4,574 clipped video segments totaling approximately 80 GB, developed by buaaplay and last updated in March 2026. The collection is organized into 8 subcategories specifically designed to evaluate spatial-temporal state maintenance in video understanding models. It focuses on two primary task types: object counting and event counting.
Users should ensure they have approximately 80 GB of storage and tools capable of processing H.264 MP4 files before downloading.