MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video

By Jinlu Zhang, Zhigang Tu, Jianyu Yang, Yujin Chen, Junsong Yuan. Computer Vision and Pattern Recognition, 2022

410 citations recorded by the source corpus.

Recent transformer-based solutions have been introduced to estimate 3D human pose from 2D keypoint sequence by considering body joints among all frames globally to learn spatio-temporal correlation. We observe that the motions of different joints differ significantly. However, the previous methods cannot efficiently model the solid inter-frame correspondence of each joint, leading to insufficient learning of spatial-temporal correlation. We propose MixSTE (Mixed Spatio-Temporal Encoder), which has a temporal transformer block to separately model the temporal motion of each joint and a spatial transformer block to learn inter-joint spatial correlation. These two blocks are utilized alternately to obtain better spatio-temporal feature encoding. In addition, the network output is extended from the central frame to entire frames of the input video, thereby improving the coherence between the input and output sequences. Extensive experiments are conducted on three benchmarks (i.e. Human3.6M, MPI-INF-3DHP, and HumanEva). The results show that our model outperforms the state-of-the-art approach by 10.9% P-MPJPE and 7.6% MPJPE. The code is available at https://github.com/JinluZhang1126/MixSTE.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9beb07bd254f85b63529ace5ecae90397f5e171f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Libin Liu
  2. Wenjie Zhu
  3. Wayne Wu
  4. Xiaoxuan Ma
  5. Zhaoyang Liu

In Computer Vision and Pattern Recognition

  1. Libin Liu
  2. Wenjie Zhu
  3. Wayne Wu
  4. Xiaoxuan Ma
  5. Zhaoyang Liu

Citations in the corpus