7 papers
GeoDose-CP: Graph-Local Conformal Inference for Continuous-Treatment Earth Observation
Md Khalid Hasan Sakib, Dristi Datta, Manoranjan Paul +1
Reliable intervention-oriented uncertainty quantification from Earth observation (EO) remains challenging when continuous treatment shifts, spatial dependence, limited support, and…
Calibrated Tree-Neural Fusion for Fine-Grained Vegetation Community Classification
Dristi Datta, Md Khalid Hasan Sakib, Manoranjan Paul
Accurate vegetation-community classification is essential for ecological monitoring, habitat assessment, and evidence-based environmental management in heterogeneous landscapes. Ex…
FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection
Md Redwanul Haque, Manzur Murshed, Manoranjan Paul +1
Generalization remains a critical bottleneck in AI-generated image detection. Because many modern generators are proprietary or adversarially modified, existing detectors overfit t…
A Novel Image Similarity Metric for Scene Composition Structure
Md Redwanul Haque, Manzur Murshed, Manoranjan Paul +1
The rapid advancement of generative AI models necessitates novel methods for evaluating image quality that extend beyond human perception. A critical concern for these models is th…
ReflectGAN: Modeling Vegetation Effects for Soil Carbon Estimation from Satellite Imagery
Dristi Datta, Manoranjan Paul, Manzur Murshed +2
Soil organic carbon (SOC) is a critical indicator of soil health, but its accurate estimation from satellite imagery is hindered in vegetated regions due to spectral contamination…
FSDR: A Novel Deep Learning-based Feature Selection Algorithm for Pseudo Time-Series Data using Discrete Relaxation
Mohammad Rahman, Manzur Murshed, Shyh Wei Teng +1
Conventional feature selection algorithms applied to Pseudo Time-Series (PTS) data, which consists of observations arranged in sequential order without adhering to a conventional t…
A new way of video compression via forward-referencing using deep learning
S. M. A. K. Rajin, M. Murshed, M. Paul +2
To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimatio…