摘要：
In remote sensing, change detection has always been a fundamental yet challenging research topic, with profound theoretical significance and extensive application value. Over the past decades, the emergence and development of deep learning has provided new technical supports for supervised change detection and advanced its accuracy to unprecedented levels. Nevertheless, owing to the strong reliance and weak transferability of pre-labeled references, supervised learning modes still require some degrees of human assistance, which is not applicable to all the change detection tasks. In addition, agnostic to any specific inherent property, changes may display inconstant and irregular characteristics when occurring between different land cover categories, making them incompatible with traditional end-to-end learning formats. In this research, we investigate the utilization of unsupervised deep learning mode, and develop a novel approach, namely content-invariant translation (CIT), for unsupervised change detection in bi-temporal remotely sensed images. In this method, a new framework integrating the adversarial learning algorithm and hybrid attention mechanism is designed to learn a one-sided cross-domain translation from the pre-event domain to the post-event one. During this process, a self-attention module focuses on small-scale image patches and ensures the content consistency of each pair of pre-event and translated patches, and meanwhile, a cross-domain module focuses on large-scale images and guarantees the style similarity of two groups of translated and post-event patches. After translation, the style discrepancies in bi-temporal images are suppressed while the real content changes are highlighted. Extensive experiments conducted on three typical datasets that with diverse types of changes verify the effectiveness and competitiveness of our newly proposed CIT by a large margin.
作者机构：
[Wang, Jinwei] Beijing Int Studies Univ, Sch Tourism Sci, Beijing, Peoples R China.;[Wang, Jinwei] Res Ctr Beijing Tourism Dev, Beijing, Peoples R China.;[Wang, Jinwei] Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China.;[He, Qimin] Cent China Normal Univ, Natl Res Ctr Cultural Ind, Wuhan, Peoples R China.;[Qian, Lili] Hangzhou City Univ, Int Sch Cultural Tourism, Hangzhou, Peoples R China.
关键词：
Dark tourism;Tourist perception;Cognitive evaluation;Behavioral intention;S-O-R framework;Social exchange theory;Turismo oscuro;Percepcion de los turistas;Evaluacion cognitiva;Intencion de comportamiento;Marco E-O-R;Teoria del intercambio social
摘要：
PurposeThis study aims to reveal the empirical linkage between tourists' perspectives and attitudes towards disaster ruins and dark tourism by attesting influence relationships between disaster memorials perception, dark tourism evaluation, as well as heritage protection and tourism development intention. Design/methodology/approachPartial least squares structural equation modeling analysis was used on a sample of 413 valid visitor questionnaires collected at the 5 center dot 12 Wenchuan Earthquake Memorial Museum, Sichuan Province, China. FindingsDisaster memorials perception positively influences positive evaluation of dark tourism, heritage protection intention and tourism development intention, while negatively influencing negative evaluation of dark tourism. Furthermore, positive evaluation of dark tourism and heritage protection intention positively affect tourism development intention. In addition, prior knowledge is a significant moderator in the research model. Originality/valueThis study applied the stimulus-organism-response framework and social exchange theory to predict tourists' behavioral intention toward disaster memorials, providing valuable insights to dark tourism research. It illuminates tourists' psychological and behavioral characteristics at natural disaster sites and deepens research on the human-nature relationship from the disaster perspective.
