Spatio-temporal Self-Attention for Egocentric 3D Pose Estimation

Jinman Park, Kimathi Kaai, Saad Hossain, Norikatsu Sumi, Sirisha Rambhatla, Paul W. Fieguth

Keywords: pose estimation, egocentric vision, computer vision, self-attention, spatio-temporal data analysis

TL;DR: spatio-temporal egocentric pose estimation using transformers.

Abstract:

Vision-based ego-centric 3D human pose estimation (ego-HPE) is essential to support critical applications of xR-technologies. However, severe self-occlusions and strong distortion introduced by the fish-eye view from the head mounted camera, make ego-HPE extremely challenging. While current state-of-the-art (SOTA) methods try to address the distortion, they still suffer from large errors in the most critical joints (such as hands) due to self-occlusions. To this end, we propose a spatio-temporal transformer model that can attend to semantically rich feature maps obtained from popular convolutional backbones. Leveraging the complex spatio-temporal information encoded in ego-centric videos, we design a spatial concept called feature map tokens (FMT) which can attend to all the other spatial units in our spatio-temporal feature maps. Powered by this FMT-based transformer, we build Egocentric Spatio-Temporal Self-Attention Network (Ego-STAN), which uses heatmap-based representations and spatio-temporal attention specialized to address distortions and self-occlusions in ego-HPE.
Our quantitative evaluation on the contemporary sequential xR-EgoPose dataset, achieves a 38.2% improvement on the highest error joints against the SOTA ego-HPE model, while accomplishing a 22% decrease in the number of parameters. Finally, we also demonstrate the generalization capabilities of our model to real-world HPE tasks beyond ego-views.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)