ACM Multimedia 2019 2019

W2VV++: Fully Deep Learning for Ad-hoc Video Search

ACM Multimedia 2019 2019 li-xirong/w2vvpp

The backbone of our method is the proposed W2VV++ model, a super version of Word2VisualVec (W2VV) previously developed for visual-to-text matching.

AD-HOC VIDEO SEARCH REPRESENTATION LEARNING TEXT MATCHING