Jianfeng Dong, Xirong Li, Cees G. M. Snoek. Predicting Visual Features From Text for Image and Video Caption Retrieval. IEEE Transactions on Multimedia, 20(12):3377-3388, 2018. [doi]
@article{DongLS18-0,
title = {Predicting Visual Features From Text for Image and Video Caption Retrieval},
author = {Jianfeng Dong and Xirong Li and Cees G. M. Snoek},
year = {2018},
doi = {10.1109/TMM.2018.2832602},
url = {https://doi.org/10.1109/TMM.2018.2832602},
researchr = {https://researchr.org/publication/DongLS18-0},
cites = {0},
citedby = {0},
journal = {IEEE Transactions on Multimedia},
volume = {20},
number = {12},
pages = {3377-3388},
}