MythPose: Enhanced Detection of Complex Poses in Thangka Figures [PDF]
SensorsThangka is a unique form of painting in Tibet, which holds rich cultural significance and artistic value. In Thangkas, in addition to the standard human form, there are also figures with multiple limbs. Existing human pose estimation methods are not well
Qijun Zhao, Ping Lan, Te Shen
exaly +6 more sources
Thangka Image Captioning Based on Semantic Concept Prompt and Multimodal Feature Optimization [PDF]
Journal of Imaging, 2023 Thangka images exhibit a high level of diversity and richness, and the existing deep learning-based image captioning methods generate poor accuracy and richness of Chinese captions for Thangka images. To address this issue, this paper proposes a Semantic
Wenjin Hu
exaly +4 more sources
RPTK1: A New Thangka Data Set for Object Detection of Thangka Images [PDF]
IEEE Access, 2021 Data set is the basis of machine learning, a good data set can promote the development of various applications. Machine learning has been deeply involved in the protection and inheritance of cultural resources.
Chen Yuhong, Xiaojing Liu
exaly +4 more sources
Art and Environmental Struggle Curating an Exhibition About Place-Rooted Ecological Knowledge. [PDF]
Geohealth, 2022 Abstract Inspired by ecological calendars, the Herbert F. Johnson Museum of Art organized the exhibition Art and Environmental Struggle to coincide with the international conference Rhythms of the Land: Indigenous Knowledge, Science, and Thriving Together in a Changing Climate, held at Cornell University in October 2021.
Avril E +4 more
europepmc +2 more sources
Thangka super-resolution diffusion model based on discrete cosine transform domain padding upsampling and high-frequency focused attention. [PDF]
PLoS ONEThangka is a traditional Tibetan painting art form, possessing profound cultural significance and a unique artistic style. Image super-resolution technology, as an effective means of digital preservation and restoration, plays an important role in ...
Xin Chen +5 more
doaj +3 more sources
Artificial Intelligence for Pigment Classification Task in the Short-Wave Infrared Range [PDF]
Sensors, 2021 Hyperspectral reflectance imaging in the short-wave infrared range (SWIR, “extended NIR”, ca. 1000 to 2500 nm) has proven to provide enhanced characterization of paint materials.
Emeline Pouyet +3 more
doaj +2 more sources
Connection Science, 2022 Aiming at the problems of few detecting samples, deformable target sizes and overlapping among targets in the detection of headdresses and seats of Thangka Yidam, we propose an optimised few shot Thangka detection method based on the ResNet and ...
Hu Wenjin +5 more
exaly +2 more sources
Heritage Science, 2023 Presently, face recognition technology is rapidly advancing and has emerged as a crucial field of research. Thangka, being a significant repository of Buddhist imagery, encompass a vast amount of Buddha image data depicting diverse Buddhist themes from ...
Fenglei Fan
exaly +2 more sources
Research on the semantic segmentation of Thangka images via an improved PIDNet. [PDF]
PLoS ONEIn the digital preservation, restoration, and research of Thangka paintings, real-time semantic segmentation plays a crucial role in rapid image analysis.
Jiao Wu +5 more
doaj +2 more sources
Visual symptoms associated with refractive errors among Thangka artists of Kathmandu valley [PDF]
BMC Ophthalmology, 2017 Background Prolong near work, especially among people with uncorrected refractive error is considered a potential source of visual symptoms. The present study aims to determine the visual symptoms and the association of those with refractive errors among
Deepa Dhungel, Gauri Shankar Shrestha
doaj +2 more sources