To tackle the issues of numerous parameters, high computational complexity, and extended detection time prevalent in current human pose estimation network models, we have incorporated an hourglass structure to create a lightweight single-path network model, which has fewer parameters and a shorter computation time. To ensure model accuracy, we have implemented a window self-attention mechanism with a reduced parameter count. Additionally, we have redesigned this self-attention module to effectively extract local and global information, thereby enriching the feature information learned by the model. This module merges with the inverted residual network architecture, creating a separate module of WGNet. Finally, WGNet can be flexibly embedded into different stages of the model. Training and validation on COCO and MPII datasets demonstrate that this model reduces the number of parameters by 25%, computational complexity by 41%, and inference time by nearly two times, compared to Hrformer, which also utilizes the windowed self-attention mechanism, at the cost of only 3.5% accuracy.

No abstract

Multi-patent pools based on different technical standards are appearing in many technique industries with competitions becoming intensive among technical standards. Theoretical model of cumulative innovation effect of competitive patent pools based on different technical standards is developed by dynamic game theory in this paper to study the cumulative innovation effect of competitive patent pool under the different patent types of relationship between patents, which are blocking patent, substitutability patent and additional innovation patent. This research indicates: the R&D investments of an enterprise inside a patent pool increase (or decrease) as the R&D investments of other enterprises inside the same patent pool decrease (or increase) or as the R&D investments of the enterprises inside another patent pool or the R&D investments of the enterprises outside patent pools increase (or decrease) during the patent race of blocking patent. The bigger differentiation degree between patents is, the R&D investments of all enterprises are more during the patent race of substitutability patent. The R&D investments of an enterprise inside a patent pool are bigger than outside the patent pools during the patent race of additional innovation patent.