Knowledge Integration Networks for Action Recognition AAAI 2020
AAAI 2020 码隆科技实验室+南京大学 1 摘要 在这项工作中，我们提出了用于视频动作识别的知识集成网络（KINet）。KINet能够聚合有意义的上下文特征，这些特征对于识别动作非常重要，例如人类信息和场景上下文。我们设计了一个由一个动作识别主分支和两个辅助分支组成的三分支体系结构，该结构允许模型对动作识别中的人和场景知识进行编码。我们探索了两种预先训练的教师网络模型来提取人类和场景的知识，
相关文章
- 1. PBRNet:Progressive Boundary Refinement Network for Temporal Action Detection （AAAI 2020）
- 2. Spatiotemporal Residual Networks for Video Action Recognition
- 3. Spatiotemporal Multiplier Networks for Video Action Recognition
- 4. 论文：3D Convolutional Neural Networks for Human Action Recognition
- 5. Action Recognition之SlowFast Networks
- 6. 译：Two-Stream Convolutional Networks for Action Recognition in Videos.md
- 7. 3D Convolutional Neural Networks for Human Action Recognition
- 8. 译：Two-stream convolutional networks for action recognition in videos
- 9. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
- 10. 译：3D Convolutional Neural Networks for Human Action Recognition
- 更多相关文章...
- • Swift for 循环 - Swift 教程
- • Scala for循环 - Scala教程
- • IntelliJ IDEA代码格式化设置
- • 使用阿里云OSS+CDN部署前端页面与加速静态资源
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. PBRNet:Progressive Boundary Refinement Network for Temporal Action Detection （AAAI 2020）
- 2. Spatiotemporal Residual Networks for Video Action Recognition
- 3. Spatiotemporal Multiplier Networks for Video Action Recognition
- 4. 论文：3D Convolutional Neural Networks for Human Action Recognition
- 5. Action Recognition之SlowFast Networks
- 6. 译：Two-Stream Convolutional Networks for Action Recognition in Videos.md
- 7. 3D Convolutional Neural Networks for Human Action Recognition
- 8. 译：Two-stream convolutional networks for action recognition in videos
- 9. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
- 10. 译：3D Convolutional Neural Networks for Human Action Recognition