activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

TriCLE: Tri-Modal Vision-Language Reasoning for Edge-Deployed Fine-Grained Clustering

Kishor Datta Gupta, Md. Mahfuzur Rahman, Fahad Rahman +4

Edge platforms used for aerial observation must interpret aircraft imagery under limited memory, limited compute, and intermittent connectivity. This setting is difficult for stand…

cs.CV2026

LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception

Justin williams, Kishor Datta Gupta, Roy George +1

Vision-language-action (VLA) models have shown strong semantic grounding and task generalization in manipulation, but aerial deployment remains difficult because drones require low…

cs.CV2026

Physics-Based Benchmarking Metrics for Multimodal Synthetic Images

Kishor Datta Gupta, Marufa Kamal, Md. Mahfuzur Rahman +3

Current state of the art measures like BLEU, CIDEr, VQA score, SigLIP-2 and CLIPScore are often unable to capture semantic or structural accuracy, especially for domain-specific or…

cs.CV2026

VLCE: A Knowledge-Enhanced Framework for Image Description in Disaster Assessment

Md. Mahfuzur Rahman, Kishor Datta Gupta, Marufa Kamal +5

General-purpose vision-language models (VLMs) such as LLaVA and QwenVL produce descriptions of disaster imagery that lack domain-specific vocabulary and actionable detail. We propo…

cs.CV2024

UAV (Unmanned Aerial Vehicles): Diverse Applications of UAV Datasets in Segmentation, Classification, Detection, and Tracking

Md. Mahfuzur Rahman, Sunzida Siddique, Marufa Kamal +2

Unmanned Aerial Vehicles (UAVs), have greatly revolutionized the process of gathering and analyzing data in diverse research domains, providing unmatched adaptability and effective…

cs.CV2024

Physical Rule-Guided Convolutional Neural Network

Kishor Datta Gupta, Marufa Kamal, Rakib Hossain Rifat +2

The black-box nature of Convolutional Neural Networks (CNNs) and their reliance on large datasets limit their use in complex domains with limited labeled data. Physics-Guided Neura…