Title
A Better Way to Attend: Attention With Trees for Video Question Answering.
Abstract
We propose a new attention model for video question answering. The main idea of the attention models is to locate on the most informative parts of the visual data. The attention mechanisms are quite popular these days. However, most existing visual attention mechanisms regard the question as a whole. They ignore the word-level semantics where each word can have different attentions and some words ...
Year
DOI
Venue
2018
10.1109/TIP.2018.2859820
IEEE Transactions on Image Processing
Keywords
Field
DocType
Knowledge discovery,Visualization,Task analysis,Computational modeling,Syntactics,Natural languages,Semantics
Question answering,Pattern recognition,Natural language,Natural language processing,Artificial intelligence,Knowledge extraction,Parsing,Syntax,Semantics,Mathematics,Recursion,Visual Word
Journal
Volume
Issue
ISSN
27
11
1057-7149
Citations 
PageRank 
References 
6
0.44
17
Authors
4
Name
Order
Citations
PageRank
Hongyang Xue1813.54
Wenqing Chu2466.74
Zhou Zhao377390.87
Deng Cai47938320.26