Tour guides' self-efficacy and resilience capability building through sharing economy platforms

Purpose: This study aims to explore how the local tour guides (LTGs) operate through the sharing economy platform. This study explores how LTGs have responded to the COVID-19 pandemic restrictions using self-efficacy and other resources to improve resilience and performance. This study also delineates the working mechanisms of peer-to-peer (P2P) platform-enabled, dynamic capability building processes, in the tourism sharing economy. Design/methodology/approach: This research adopted an interpretive approach to understand the focal phenomenon using two types of data. A total of 40 semi-structured interviews with LTGs and 26,478 online tourist reviews from tour guide service participants' before and during the COVID-19 pandemic were used. Findings: The findings of this study revealed that LTGs used sharing economy platforms to arrange flexible tour guide services. Resilience emerged through dynamic capability that addressed contextual factors in real time. LTGs coordinated different resources and customers during a time of uncertainty. Different sources of self-efficacy and types of dynamic capability were identified. The interplay between LTGs' self-efficacy and dynamic capability was also delineated. Practical implications: The findings provide guidance for LTGs on P2P platforms and other sharing economy sectors on how diverse resources enabled by the sharing economy can enhance resilience during times of uncertainty. LTGs that engage with contextual information and are dynamic can adopt itineraries and services that will benefit tourists and their business. Originality/value: This study contributes to the sharing economy literature by theorizing the working flow that enables LTGs to exert self-efficacy and leverage dynamic capability on P2P platforms. This study also contributes by linking resilience to contextual factors in real time. The outcomes provide guidance for LTGs to remain competitive and establish resilience in uncertain environments. © 2023, Emerald Publishing Limited.

DuDoTrans: Dual-Domain Transformer for Sparse-View CT Reconstruction

While Computed Tomography (CT) is necessary for clinical diagnosis, ionizing radiation in the imaging process induces irreversible injury, thereby driving researchers to study sparse-view CT reconstruction. Iterative models are proposed to alleviate the appeared artifacts in sparse-view CT images, but their computational cost is expensive. Deep-learning-based methods have gained prevalence due to the excellent reconstruction performances and computation efficiency. However, these methods ignore the mismatch between the CNN's local feature extraction capability and the sinogram's global characteristics. To overcome the problem, we propose Dual-Domain Transformer (DuDoTrans) to simultaneously restore informative sinograms via the long-range dependency modeling capability of Transformer and reconstruct CT image with both the enhanced and raw sinograms. With such a novel design, DuDoTrans even with fewer involved parameters is more effective and generalizes better than competing methods, which is confirmed by reconstruction performances on the NIH-AAPM and COVID-19 datasets. Finally, experiments also demonstrate its robustness to noise.

Improving Generalizability in Limited-Angle CT Reconstruction with Sinogram Extrapolation

Computed tomography (CT) reconstruction from X-ray projections acquired within a limited angle range is challenging, especially when the angle range is extremely small. Both analytical and iterative models need more projections for effective modeling. Deep learning methods have gained prevalence due to their excellent reconstruction performances, but such success is mainly limited within the same dataset and does not generalize across datasets with different distributions. Hereby we propose ExtraPolationNetwork for limited-angle CT reconstruction via the introduction of a sinogram extrapolation module, which is theoretically justified. The module complements extra sinogram information and boots model generalizability. Extensive experimental results show that our reconstruction model achieves state-of-the-art performance on NIH-AAPM dataset, similar to existing approaches. More importantly, we show that using such a sinogram extrapolation module significantly improves the generalization capability of the model on unseen datasets (e.g., COVID-19 and LIDC datasets) when compared to existing approaches. © 2021, Springer Nature Switzerland AG.