TH3.M3: Leveraging Vision Transformers and Generative Models for Remote Sensing and Earth Observation I
Thursday, 7 August, 13:15 - 14:30
Location: Room M3
Session Type: Oral
Track: AI and Big Data
Thu, 7 Aug, 13:15 - 13:30

TH3.M3.1: Efficient Vision Transformer Framework: Near-Surface O3 Prediction with Missing Satellite Data
Prasanjit Dey, Technological University Dublin, Ireland; Soumyabrata Dev, University College Dublin, Ireland; Bianca Schoen-Phelan, Technological University Dublin, Ireland
Thu, 7 Aug, 13:30 - 13:45

TH3.M3.2: A Vision-Language Framework for Multispectral Scene Representation Using Language-Grounded Features
Enes Karanfil, Hacettepe University, Turkey; Nevrez Imamoglu, National Institute of Advanced Industrial Science and Technology, Japan; Erkut Erdem, Hacettepe University, Turkey; Aykut Erdem, Koç University, Turkey
Thu, 7 Aug, 13:45 - 14:00

TH3.M3.3: Learnable Channel Converter for Multi-Spectral Image to RGB Visualization using a Vision-Text Model
Haoxiang Qiu, Tomoya Sakai, Takayuki Katsuki, Daiki Kimura, IBM Research, Japan
Thu, 7 Aug, 14:00 - 14:15

TH3.M3.4: Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing
Vlad-Mihai Vasilescu, Ana-Antonia Neacșu, Daniela Faur, CAMPUS Research Institute, Romania
Thu, 7 Aug, 14:15 - 14:30

TH3.M3.5: SPATIO-TEMPORAL TRANSFORMERS FOR LONG TERM NDVI PREDICTION
Ido Faran, Nathan Netanyahu, Bar-Ilan University, Israel; Elena Roitberg, Maxim Shoshany, Technion Israel Institute of Technology,, Israel