BriefGPT.xyz
Nov, 2016
视频翻译的自适应特征抽象
Adaptive Feature Abstraction for Translating Video to Language
HTML
PDF
Yunchen Pu, Martin Renqiang Min, Zhe Gan, Lawrence Carin
TL;DR
本研究提出了一种新的方法，使用自适应的注意力机制和多层卷积神经网络特征（即特征抽象）来生成视频的时空表示，通过实验验证了该方法的有效性。
Abstract
A new model for
video captioning
is developed, using a deep three-dimensional
convolutional neural network
(C3D) as an encoder for videos and a Recurrent Neural Network (RNN) as a decoder for captions. We conside
→