papers AI Learner
The Github is limit! Click to go to the new site.

Adaptive Feature Abstraction for Translating Video to Text

2017-11-17
Yunchen Pu, Martin Renqiang Min, Zhe Gan, Lawrence Carin

Abstract

Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features. However, the variable context-dependent semantics in the video may make it more appropriate to adaptively select features from the multiple CNN layers. We propose a new approach for generating adaptive spatiotemporal representations of videos for the captioning task. A novel attention mechanism is developed, that adaptively and sequentially focuses on different layers of CNN features (levels of feature “abstraction”), as well as local spatiotemporal regions of the feature maps at each layer. The proposed approach is evaluated on three benchmark datasets: YouTube2Text, M-VAD and MSR-VTT. Along with visualizing the results and how the model works, these experiments quantitatively demonstrate the effectiveness of the proposed adaptive spatiotemporal feature abstraction for translating videos to sentences with rich semantics.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1611.07837

PDF

https://arxiv.org/pdf/1611.07837


Similar Posts

Comments