Pose Recognition with Cascade Transformers
Citations Over TimeTop 1% of 2021 papers
Abstract
In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject to various heuristic designs (not end-to-end mostly), whereas regression-based approaches attain relatively lower accuracy but they have less intermediate non-differentiable steps. Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches. We demonstrate the keypoint hypothesis (query) refinement process across different self-attention layers to reveal the recursive self-attention mechanism in Transformers. In the experiments, we report competitive results for pose recognition when compared with the competing regression-based methods.
Related Papers
- → Further optimization of Q-cascades(2015)10 cited
- → The neurobiology of categorization(2010)4 cited
- → Design of a 160% pitch passage for cascade experiments using optimization methods(2010)2 cited
- → One-pitch passage designed inversely with a single blade for cascade experiments(2010)1 cited
- → Two categorization patterns in idiom semantics(2016)1 cited