图 书 馆
基于多任务递归神经网络的即时性预测Multi-Task Recurrent Neural Network for Immediacy Prediction |
|
| 课程网址: | http://videolectures.net/iccv2015_chu_neural_network/ |
| 主讲教师: | Xiao Chu |
| 开课单位: | 视频讲座网 |
| 开课时间: | 2016-02-10 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | In this paper, we propose to predict immediacy for interacting persons from still images. A complete immediacy set includes interactions, relative distance, body leaning direction and standing orientation. These measures are found to be related to the attitude, social relationship, social interaction, action, nationality, and religion of the communicators. A large-scale dataset with 10,000 images is constructed, in which all the immediacy cues and the human poses are annotated. We propose a rich set of immediacy representations that help to predict immediacy from imperfect 1-person and 2-person pose estimation results. A multi-task deep recurrent neural network is constructed to take the proposed rich immediacy representations as the input and learn the complex relationship among immediacy predictions through multiple steps of refinement. The effectiveness of the proposed approach is proved through extensive experiments on the large-scale dataset. |
| 关 键 词: | 即时互动; 相对距离; 静态图像 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-12-02：chenxin01 |
| 最后编审: | 2022-12-02：chenxin01 |
| 阅读次数: | 23 |