FR4.R11.4

LIT-4-RSVQA: LIGHTWEIGHT TRANSFORMER-BASED VISUAL QUESTION ANSWERING IN REMOTE SENSING

Leonard Hackel, Kai Norman Clasen, Technische Universität Berlin, Germany; Mahdyar Ravanbakhsh, Zalando SE Berlin, Germany; Begüm Demir, Technische Universität Berlin, Germany
Session:
FR4.R11: Large AI Models for EO Oral
Track:
Community-Contributed Sessions
Location:
Room 106
Presentation Time:
Fri, 21 Jul, 16:21 - 16:33 Pacific Time (UTC -8)
Session Co-Chairs:
Nicolas Longepe, ESA and Begum Demir, TU-Berlin
Session Manager:
HUMAIRA SANAM
Presentation
Not logged in.
Discussion
Not logged in.
Resources
No resources available.
Session FR4.R11
FR4.R11.1: TEXT AS A RICHER SOURCE OF SUPERVISION IN SEMANTIC SEGMENTATION TASKS
Valerie Zermatten, Javiera Castillo Navarro, Lloyd Hughes, Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland; Tobias Kellenberger, Federal Office of Topography swisstopo, Switzerland; Devis Tuia, Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland
FR4.R11.2: MULTIMODAL SELF-SUPERVISED LEARNING FOR BOOSTING CROP CLASSIFICATION USING SENTINEL2 AND PLANETSCOPE
Ankit Patnala, Scarlet Stadtler, Martin Schultz, Forschungszentrum Juelich, Germany; Juergen Gall, University of Bonn, Germany
FR4.R11.3: SELF-LEARNING ONTOLOGY FOR NATURAL HAZARDS
Ion Grujdin, CEOSpaceTech, University Politehnica of Bucharest, Romania, Romania; Mihai Datcu, CEOSpaceTech, University Politehnica of Bucharest, Romania; Remote Sensing Technology Institute, German Aerospace Center (DLR), Germany, Romania
FR4.R11.4: LIT-4-RSVQA: LIGHTWEIGHT TRANSFORMER-BASED VISUAL QUESTION ANSWERING IN REMOTE SENSING
Leonard Hackel, Kai Norman Clasen, Technische Universität Berlin, Germany; Mahdyar Ravanbakhsh, Zalando SE Berlin, Germany; Begüm Demir, Technische Universität Berlin, Germany
FR4.R11.5: OVERCOMING LANGUAGE BIAS IN REMOTE SENSING VISUAL QUESTION ANSWERING VIA ADVERSARIAL TRAINING
Zhenghang Yuan, Lichao Mou, Xiaoxiang Zhu, Technical University of Munich, Germany
FR4.R11.6: A SELF-SUPERVISED CROSS-MODAL REMOTE SENSING FOUNDATION MODEL WITH MULTI-DOMAIN REPRESENTATION AND CROSS-DOMAIN FUSION
Yingchao Feng, Peijin Wang, Wenhui Diao, Qibin He, Huiyang Hu, Hanbo Bi, Xian Sun, Kun Fu, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China, China
Resources
No resources available.