WE4.M2.2
REDUNDANCY-AWARE PRETRAINING OF VISION-LANGUAGE FOUNDATION MODELS IN REMOTE SENSING
Mathis Jürgen Adler, Leonard Hackel, Technische Universität Berlin, Germany; Gencer Sumbul, École Polytechnique Fédérale de Lausanne, Switzerland; Begüm Demir, Technische Universität Berlin, Germany
Session:
WE4.M2: Foundation Models for Geospatial Artificial Intelligence III Oral
Track:
Community-Contributed Sessions
Location:
Room M2
Presentation Time:
Wednesday, 6 August, 16:00 - 16:15
Session Co-Chairs:
Shailesh Deshpande, Tata Consultancy Services Research and Jagobondhu Hazra, IBM India Research Lab
Presentation
Discussion
Resources
No resources available.
Session WE4.M2
WE4.M2.1: ESAD-GPT: Earth's Surface Anomaly Detection Using Large Vision-language Models
Xing-ao Wang, Zhi Gao, Zhaohong Liao, Shuying Xia, Wuhan University, China; Min Cao, Wuhan Guanggu Zoyon Science and Technology Company Ltd, China; Qiao Wang, Beijing Normal University, China
WE4.M2.2: REDUNDANCY-AWARE PRETRAINING OF VISION-LANGUAGE FOUNDATION MODELS IN REMOTE SENSING
Mathis Jürgen Adler, Leonard Hackel, Technische Universität Berlin, Germany; Gencer Sumbul, École Polytechnique Fédérale de Lausanne, Switzerland; Begüm Demir, Technische Universität Berlin, Germany
WE4.M2.3: EarthCaption: A Task-driven remote-sensing Image Caption Dataset for Earth Understanding
Zihang Chen, Ailong Ma, Wuhan University, China; Junjue Wang, The University of Tokyo, Japan; Yanfei Zhong, Wuhan University, China
WE4.M2.4: LARGE LANGUAGE MODELS WITH RETRIEVAL AUGMENTED GENERATION TO STREAMLINE SENTINEL-2 DATA DESCRIPTION
Teodor Costachioiu, Corina VADUVA, Daniela FAUR, National University of Science and Technology Politehnica Bucharest, Romania
WE4.M2.5: ONTOVIT-GRU: A CONCEPTUAL APPROACH FOR ONTOLOGY-ENHANCED FLOOD PREDICTION USING A FOUNDATIONAL VISION TRANSFORMER (PRITHVI-EO-2.0) GATE RECURRENT UNIT (GRU) ARCHITECTURE
Ion Grujdin, Mihai Datcu, Universitatea Națională de Știință și Tehnologie POLITEHNICA București, Romania
Resources
No resources available.