Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
来源:互联网 发布:linux怎么退出tail 编辑:程序博客网 时间:2024/06/16 06:15
Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
(Submitted on 26 Oct 2015 (v1), last revised 6 Apr 2016 (this version, v2))
We present an approach that exploits hierarchical Recurrent Neural Networks (RNNs) to tackle the video captioning problem, i.e., generating one or multiple sentences to describe a realistic video. Our hierarchical framework contains a sentence generator and a paragraph generator. The sentence generator produces one simple short sentence that describes a specific short video interval. It exploits both temporal- and spatial-attention mechanisms to selectively focus on visual elements during generation. The paragraph generator captures the inter-sentence dependency by taking as input the sentential embedding produced by the sentence generator, combining it with the paragraph history, and outputting the new initial state for the sentence generator. We evaluate our approach on two large-scale benchmark datasets: YouTubeClips and TACoS-MultiLevel. The experiments demonstrate that our approach significantly outperforms the current state-of-the-art methods with BLEU@4 scores 0.499 and 0.305 respectively.
Submission history
From: Haonan Yu [view email][v1] Mon, 26 Oct 2015 22:47:00 GMT (4584kb,D)
[v2] Wed, 6 Apr 2016 02:24:35 GMT (2630kb,D)
阅读全文
0 0
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
- Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
- Hierarchical Boundary-Aware Neural Encoder for Video Captioning
- Video captioning with recurrent networks based on frame- and video-level features and visual content
- Gated Recurrent Neural Networks
- Recurrent Neural Networks Tutorial
- Recurrent Neural Networks - collections
- Recurrent Neural Networks regularization
- Recurrent Neural Networks
- Recurrent Neural Networks
- Batch Normalized Recurrent Neural Networks
- Recurrent Neural Networks 循环神经网络
- TensorFlow3: RNN, Recurrent Neural Networks
- Recurrent Neural Networks Tutorial 中文翻译
- RNN(recurrent neural networks)简介
- tensorflow 的 Recurrent Neural Networks
- QRNN(Quasi-Recurrent Neural Networks)
- Recurrent Neural Networks VS LSTM
- 微信移动端数据库组件WCDB系列(二) — 数据库修复三板斧
- 树莓派配置静态IP
- MySQL修改字段名、字段类型
- Kotlin-神奇的下划线字符(_)
- 前端面试题
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
- win下scala环境配置
- 思想决定行为,行为决定习惯,习惯决定性格,性格决定命运
- static,final ,==,equals
- [经验] 一种基于FreeRTOS的CPU使用率测算方法及原理介绍
- java面试下集
- Dense-Captioning Events in Videos
- JavaBean属性命名特殊规范
- js:利用for循环,循环输出HelloWord