Video Captioning With Adaptive Attention and Mixed Loss Optimization

Video Captioning With Adaptive Attention and Mixed Loss Optimization

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 decrea...

Full description

Bibliographic Details
Main Authors: Huanhou Xiao, Jinglun Shi
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Video captioning
sequence-to-sequence
adaptive attention
reinforcement learning
long short-term memory
Online Access:https://ieeexplore.ieee.org/document/8840863/

Internet

https://ieeexplore.ieee.org/document/8840863/

Similar Items