Cross-Modal Graph with Meta Concepts for Video Captioning. (arXiv:2108.06458v3 [cs.CV] UPDATED)

Video captioning targets interpreting the complex visual contents as text
descriptions, which requires the model to fully understand video scenes
including objects and their interactions. Prevailing methods adopt
off-the-shelf object detection networks to give object proposals and use the
attention mechanism to model the relations between objects. They often miss
some undefined semantic concepts of the pretrained model and fail to identify
exact predicate relationships between objects. In this paper, we investigate an
open research task of generating text descriptions …

arxiv captioning cv graph meta video