video narration captioning

1 papers with code • 1 benchmarks • 1 datasets

Human narration is another critical factor to understand a multi-shot video. It often provides information of the background knowledge and commentator’s view on visual events. We conduct experiments to predict the narration caption of a video-shot and name this task single-shot narration captioning. We adopt the same model structure as single-shot video captioning with the ASR text as additional input, except that the prediction target is the narration caption.