Fig 1.
Overall Architecture of DATP Model.
The DATP model consists of three core components: an OATE Input Module (Occlusion-Aware and Trend-Enhanced Input Module), a UFTA Module (Unified Feature Encoding and Temporal Alignment Module).
Fig 2.
Structure of the Multi-Scale Perception and Adaptive Scale Weighting Module.
This figure illustrates the architecture of the multi-scale perception and adaptive scale weighting module used in the proposed DATP model.
Fig 3.
Architecture of the Adaptive Graph Topology Modeling Network (AGTM-Net).
Fig 4.
Comparison of existing SOTA methods.
Including T3D-CNN, MHFormer, STCFormer, and DTF with the proposed fusion model under different levels of missing joints on the MPI-INF-3DHP dataset. As the number of missing joints increases, the proposed method maintains better robustness, exhibiting the lowest MPJPE increase overall.
Table 1.
Comparison of SOTA Methods with 16 Missing Joints per Frame on MPI-INF-3DHP Datasets Using PCK and AUC Metrics (Input Length = 81).
Table 2.
AComparison of the Proposed DATP Model with Existing SOTA Methods in Terms of MPJPE for 16 Missing Joints Per Frame on the Human3.6M Datasets Using 2D CPN (Protocol 1).
Table 3.
Comparison of the Proposed DATP Model with Existing SOTA Methods in Terms of MPJPE for 16 Missing Joints Per Frame on the Human3.6M Datasets Using 2D CPN (Protocol 2).
Table 4.
Ablation Study of Proposed DATP Architecture under Protocols 1 and 2 with 4 Random Missing 2D Joints per Frame.
Table 5.
Comparative tests between AGTM-Net and other models.
Fig 5.
The gradient-based interpretability analysis performed on the datasets with a score of 0.
Fig 6.
The perturbation-based interpretability analysis performed on the datasets with a score of 0.