Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation

no code implementations • 20 Oct 2021 • Haiyang Liu, Dingli Luo, Songlin Du, Takeshi Ikenaga

To solve these problems, this paper proposes (i) a new loss organization method which uses self-supervised heatmaps to reduce prediction contradictions and spatial-sequential attention to enhance networks' features extraction; (ii) a new combination of predictions composed by heatmaps, Part Affinity Fields (PAFs) and our block-inside offsets to fix pixel-level joints positions and further demonstrates the effectiveness of proposed loss function.

Multi-Person Pose Estimation