Datasets Activity Stream About Order by Relevance Name Ascending Name Descending Last Modified Go 1 dataset found Organizations: No Organization Filter Results Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Vide... Human-centric spatio-temporal video grounding (HC-STVG) task aims to localize a spatio-temporal tube of the target person indicated by a language description. Dataset JSON