Sign Up to like & get
recommendations!
1
Published in 2019 at "IEEE Access"
DOI: 10.1109/access.2019.2942000
Abstract: The attention mechanism and sequence-to-sequence framework have shown promising advancements in the temporal task of video captioning. However, imposing the attention mechanism on non-visual words, such as “of” and “the”, may mislead the decoder and…
read more here.
Keywords:
attention;
loss;
adaptive attention;
video captioning ... See more keywords
Sign Up to like & get
recommendations!
2
Published in 2022 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2021.3124336
Abstract: Restricted by the observation condition, synthetic aperture radar (SAR) automatic target classification based on deep learning usually suffers from insufficient training samples. To tackle this problem, a novel few-shot learning (FSL) framework for SAR target…
read more here.
Keywords:
network;
classification;
target classification;
mixed loss ... See more keywords