Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning
Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning.CVPR,2019. 摘要 自动生成视频字幕是一项基本的计算机视觉的任务，最近使用CNN和RNN技术解决该任务。这些方法主要关注于使用RNN序列学习方法生成更好的字幕，但却忽略了使用CNN提取特征的重要性。我们精
相关文章
- 1. Semantic Compositional Networks for Visual Captioning论文分享
- 2. Spatiotemporal Residual Networks for Video Action Recognition
- 3. Watch,Listen,and Describe:Globally and Locally Aligned Cross-Modal Attentions for Video Captioning
- 4. Context Encoding for Semantic Segmentation[CVPR2018]
- 5. CVPR 2018 Oral：Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
- 6. Context Encoding for Semantic Segmentation
- 7. Spatiotemporal CNN for Video Object Segmentation
- 8. Spatiotemporal Multiplier Networks for Video Action Recognition
- 9. Video Captioning 综述
- 10. Direct Access to Video Encoding and Decoding
- 更多相关文章...
- • C# 特性（Attribute） - C#教程
- • Swift for 循环 - Swift 教程
- • RxJava操作符（七）Conditional and Boolean
- • Composer 安装与使用
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Semantic Compositional Networks for Visual Captioning论文分享
- 2. Spatiotemporal Residual Networks for Video Action Recognition
- 3. Watch,Listen,and Describe:Globally and Locally Aligned Cross-Modal Attentions for Video Captioning
- 4. Context Encoding for Semantic Segmentation[CVPR2018]
- 5. CVPR 2018 Oral：Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
- 6. Context Encoding for Semantic Segmentation
- 7. Spatiotemporal CNN for Video Object Segmentation
- 8. Spatiotemporal Multiplier Networks for Video Action Recognition
- 9. Video Captioning 综述
- 10. Direct Access to Video Encoding and Decoding