У нас вы можете посмотреть бесплатно Data Matters Seminar: Using Vision Foundation Models to Map Sites en masse in GeoPACHA-AI или скачать в максимальном доступном качестве, видео которое было загружено на ютуб. Для загрузки выберите вариант из формы ниже:
Если кнопки скачивания не
загрузились
НАЖМИТЕ ЗДЕСЬ или обновите страницу
Если возникают проблемы со скачиванием видео, пожалуйста напишите в поддержку по адресу внизу
страницы.
Спасибо за использование сервиса ClipSaver.ru
South American Archaeology, at Scale?: Using Vision Foundation Models to Map Sites en masse in GeoPACHA-AI Abstract: Archaeologists excel at documenting the material dimensions of social life at local and regional scales but we often struggle to generate national and continental-sale datasets with continuous, systematic coverage. Collecting such data is important for at least three reasons: 1) macro-regional datasets provide context for understanding the variation that we observe at local and regional scales; 2) synthetic databases stitched together out of regional projects often amplify sampling biases; and 3) past peoples themselves frequently understood and acted in their worlds through large scale networks, including empires, circuits of interregional trade, and long-distance seasonal migration. In this presentation, I discuss the development and deployment of one solution to this problem: GeoPACHA-AI (Geospatial Platform for Andean Culture, History, and Archaeology), an international collaborative project that develops and harnesses Vision Transformer-based AI models to conduct continental-scale archaeological imagery survey. GeoPACHA’s project area covers nearly the entirety of the central Andes, from northern Ecuador through southern Chile, and we seek to enable new perspectives on interregional social networks, the broad impacts of imperial expansions, and long-term responses to climate change. Speaker Bio: Parker VanValkenburgh’s research and publications employ archaeological methods to address anthropological research questions, with a particular focus on the long-term impacts of colonialism and imperialism on Indigenous people and environments in the Peruvian Andes. Through the study of diverse materials and media––including architecture, ceramics, environmental datasets, and archival documents––he seeks to understand how relationships between people, institutions, and environments are transformed in the course of imperial histories, as well as how the strategies of survival and resilience that communities develop to deal with empires are passed down and reworked across generations. In the course of doing so, he strives to generate approaches that are widely applicable to the study of empire(s) beyond the Andean region and which contribute to interdisciplinary understanding of imperial legacies in the modern world. In this work, he draws amply on digital methodologies, including the tools of geographic information systems (GIS), to map and analyze social, political, and environmental change in space and time. He also applies a critical lens to the study of digital media and methodologies, asking not just how these techniques facilitate archaeological scholarship, but how digital mediation transforms the ways we work with collaborators, research subjects, students, and public audiences. __ The Data Matters Seminar Series is hosted by the Data Science Institute, covering why data matters across the physical, biological, computational, and social sciences. Data Matters is intended to stimulate conversations and collaboration by bringing multiple perspectives to challenging data-driven problems.