Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation

2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)(2019)

引用 6|浏览0
暂无评分
摘要
While many individual tasks in the domain of human analysis have recently received an accuracy boost from deep learning approaches, multi-task learning has mostly been ignored due to a lack of data. New synthetic datasets are being released, filling this gap with synthetic generated data. In this work, we analyze four related human analysis tasks in still images in a multi-task scenario by leveraging such datasets. Specifically, we study the correlation of 2D/3D pose estimation, body part segmentation and full-body depth estimation. These tasks are learned via the well-known Stacked Hourglass module such that each of the task-specific streams shares information with the others. The main goal is to analyze how training together these four related tasks can benefit each individual task for a better generalization. Results on the newly released SURREAL dataset show that all four tasks benefit from the multi-task approach, but with different combinations of tasks: while combining all four tasks improves 2D pose estimation the most, 2D pose improves neither 3D pose nor full-body depth estimation. On the other hand 2D parts segmentation can benefit from 2D pose but not from 3D pose. In all cases, as expected, the maximum improvement is achieved on those human body parts that show more variability in terms of spatial distribution, appearance and shape, e.g. wrists and ankles.
更多
查看译文
关键词
multitask human analysis,depth map,multipart segmentation,deep learning approaches,multitask learning,new synthetic datasets,synthetic generated data,multitask scenario,body part segmentation,full-body depth estimation,multitask approach,hand 2D parts segmentation,human body parts,SURREAL dataset,task-specific streams,human analysis tasks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要