Fused GRU with semantic-temporal attention for video captioning
Sign Up to like & getrecommendations! Published in 2020 at "Neurocomputing"
DOI: 10.1016/j.neucom.2018.06.096
Abstract: Abstract The encoder-decoder framework has been widely used for video captioning to achieve promising results, and various attention mechanisms are proposed to further improve the performance. While temporal attention determines where to look, semantic decides… read more here.
Keywords: temporal attention; attention; semantic temporal; video captioning ... See more keywords