Improved TokenPose with Sparsity
Over the past few years, the vision transformer and its various forms have gained significance in human pose estimation. By treating image patches as tokens, transformers can capture global relationships wisely, estimate the keypoint tokens by leveraging the visual tokens, and recognize the posture of the human body. Nevertheless, global attention is computationally demanding, which poses a challenge for scaling up transformer-based methods to high-resolution features. In this paper, we introduce sparsity in both keypoint token attention and visual token attention to improve human pose estimation. Experimental results on the MPII dataset demonstrate that our model has a higher level of accuracy and proved the feasibility of the method, achieving new state-of-the-art results. The idea can also provide references for other transformer-based models.
Code (0)
등록된 구현이 없습니다.
Tasks
Pose EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TokenPose: Learning Keypoint Tokens for Human Pose Estimation
Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to expli…
Pose EstimationRecognition of Freely Selected Keypoints on Human Limbs
Nearly all Human Pose Estimation (HPE) datasets consist of a fixed set of keypoints. Standard HPE models trained on such datasets can only detect these keypoints. If more points are desired, they have to be manually anno…
Pose EstimationDistilling Token-Pruned Pose Transformer for 2D Human Pose Estimation
Human pose estimation has seen widespread use of transformer models in recent years. Pose transformers benefit from the self-attention map, which captures the correlation between human joint tokens and the image. However…
2D Human Pose EstimationPose EstimationFirst-Order Sparse Convex Optimization: Better Rates with Sparse Updates
In was recently established that for convex optimization problems with a sparse optimal solution (may it be entry-wise sparsity or matrix rank-wise sparsity) it is possible to have linear convergence rates which depend o…
AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation
Movement and pose assessment of newborns lets experienced pediatricians predict neurodevelopmental disorders, allowing early intervention for related diseases. However, most of the newest AI approaches for human pose est…
Keypoint DetectionPose Estimation