activity
20242026
most citedPerformance Analysis of Few-Shot Learning Approaches for Bangla Handwritten Character and Digit Recognition

9 citations · 9 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

Virtual Try-On for Cultural Clothing: A Benchmarking Study

Muhammad Tausif Ul Islam, Shahir Awlad, Sameen Yeaser Adib +3

Although existing virtual try-on systems have made significant progress with the advent of diffusion models, the current benchmarks of these models are based on datasets that are d…

cs.CV2026

From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet

Radib Bin Kabir, Tawsif Tashwar Dipto, Mehedi Ahamed +2

Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior…

cs.CV2025

VisionTrap: Unanswerable Questions On Visual Data

Asir Saadat, Syem Aziz, Shahriar Mahmud +2

Visual Question Answering (VQA) has been a widely studied topic, with extensive research focusing on how VLMs respond to answerable questions based on real-world images. However, t…

cs.CV2025

Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Model

Nokimul Hasan Arif, Shadman Rabby, Md Hefzul Hossain Papon +1

Visual hallucinations in Large Language Models (LLMs), where the model generates responses that are inconsistent with the visual input, pose a significant challenge to their reliab…

cs.CV2025

DExNet: Combining Observations of Domain Adapted Critics for Leaf Disease Classification with Limited Data

Sabbir Ahmed, Md. Bakhtiar Hasan, Tasnim Ahmed +1

While deep learning-based architectures have been widely used for correctly detecting and classifying plant diseases, they require large-scale datasets to learn generalized feature…

cs.CV20259 cited

Performance Analysis of Few-Shot Learning Approaches for Bangla Handwritten Character and Digit Recognition

Mehedi Ahamed, Radib Bin Kabir, Tawsif Tashwar Dipto +3

This study investigates the performance of few-shot learning (FSL) approaches in recognizing Bangla handwritten characters and numerals using limited labeled data. It demonstrates…