Charades STA

AbstractTemporal language grounding in videos aims to localize the temporal span relevant to the given query sentence. Previous methods treat it either as a boundary regression task or a span …...

AbstractTemporal sentence grounding (TSG) is crucial and fundamental for video understanding. Previous works typically model the target activity referred to the sentence query in a video by extracting the appearance …...

AbstractVideo sentence localization aims to locate moments in an unstructured video according to a given natural language query. A main challenge is the expensive annotation costs and the annotation bias. …...