Search Results for author:
Found 1 papers, 1 papers with code
W2VV++: Fully Deep Learning for Ad-hoc Video Search
The backbone of our method is the proposed W2VV++ model, a super version of Word2VisualVec (W2VV) previously developed for visual-to-text matching.
Ranked #3 on
Ad-hoc video search
on TRECVID-AVS18 (IACC.3)
(using extra training data)
Cannot find the paper you are looking for? You can
Submit a new open access paper.
