Curated VidSTG and VIPOSeg datasets with caption grounding, action labels, temporal intervals, and object masks.
-
Viviannnyang/VidSTG-caption-action-temporal-train-combined
Viewer • Updated • 5.09k • 57 -
Viviannnyang/VIPOSeg-caption-action-temporal-val-final
Viewer • Updated • 345 • 58 -
Viviannnyang/VIPOSeg-caption-action-temporal-train-final
Viewer • Updated • 2.8k • 100 -
Viviannnyang/RDCap-caption-action-temporal-train-combined
Viewer • Updated • 35.5k • 198