Video captioning with recurrent networks based on frame- and video-level features and visual content
来源:互联网 发布:java打印心形表白 编辑:程序博客网 时间:2024/06/06 04:53
Video captioning with recurrent networks based on frame- and video-level features and visual content classification
(Submitted on 9 Dec 2015)
In this paper, we describe the system for generating textual descriptions of short video clips using recurrent neural networks (RNN), which we used while participating in the Large Scale Movie Description Challenge 2015 in ICCV 2015. Our work builds on static image captioning systems with RNN based language models and extends this framework to videos utilizing both static image features and video-specific features. In addition, we study the usefulness of visual content classifiers as a source of additional information for caption generation. With experimental results we show that utilizing keyframe based features, dense trajectory video features and content classifier outputs together gives better performance than any one of them individually.
Submission history
From: Rakshith Shetty [view email][v1] Wed, 9 Dec 2015 17:17:29 GMT (86kb,D)
阅读全文
0 0
- Video captioning with recurrent networks based on frame- and video-level features and visual content
- Frame- and Segment-Level Features and Candidate Pool Evaluation for Video Caption Generation
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
- see the forest for the trees:spitial and temporal recurrent neural networks for video-based re-id
- Deep Learning for Video Classification and Captioning
- Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
- VideoIO Flash-based audio and video communication
- VideoIO Flash-based audio and video communication
- VideoIO Flash-based audio and video communication
- VideoIO Flash-based audio and video communication
- Video Captioning with Multi-Faceted Attention
- Video Captioning with Transferred Semantic Attributes
- Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation 论文笔记
- [深度学习论文笔记][Video Classification] Long-term Recurrent Convolutional Networks for Visual Recognition a
- Playing Video on the iPhone and iPad
- Streaming Video with RTSP and RTP
- long term recurrent convolutional networks for visual recognition and description
- Long-term Recurrent Convolutional Networks for Visual Recognition and Description
- 【转】计数系统架构实践一次搞定
- MyBatis简介
- java面试上集
- 24.从单向链表中删除指定值的节点
- MySQL修改字段的排列位置
- Video captioning with recurrent networks based on frame- and video-level features and visual content
- hdoj1077 Catching Fish(几何题,枚举遍历)
- C++学习(39)
- $.getScript("test.js", function(){ ··· });。其实应该指定test.js中哪个函数,这个是特殊情况,指定的是ready函数,即页面加载后就执行的函数
- Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
- 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(_)