Tahir Hasan

Publications

Research interests: hierarchical and conditional computation for medical imaging, sign language understanding, data-efficient vision, and explainable AI. The common thread is making models spend capacity where the decision is genuinely hard — and being able to show their evidence.

Diagram of a two-stage pipeline: a YOLO detector localises the leaf, an ECA-NFNet classifier names the disease, and an explainability map highlights the evidence

An Explainable AI based Plant Disease Identification using a Two-Stage Detection-Classification Pipeline with YOLO and ECA-NFNet Framework

T. Hasan, et al.

IEEE ICCIT 2025 International Conference on Computer and Information Technology

Two-stage pipeline: YOLO localises the leaf, ECA-NFNet classifies the disease, and saliency overlays show which regions drove each prediction.

DOI Code Write-up

BibTeX 
@inproceedings{hasan2025plant,
  author    = {Hasan, Tahir and others},
  title     = {An Explainable {AI} based Plant Disease Identification using a Two-Stage Detection-Classification Pipeline with {YOLO} and {ECA-NFNet} Framework},
  booktitle = {2025 28th International Conference on Computer and Information Technology (ICCIT)},
  publisher = {IEEE},
  year      = {2025},
  doi       = {10.1109/ICCIT68739.2025.11490422}
}
Hand-landmark skeleton over a video frame, feeding a temporal model that outputs a running word sequence

Implementation of Bangla Sign Language (BdSL) Recognition in Continuous Real Time

T. Hasan, M. Ahmed, S. I. Moyeen

Under review Under review

Continuous, real-time BdSL recognition built on a new 9,010-video dataset spanning 530 word classes.

Dataset Write-up

Taxonomy diagram organising sign-language recognition systems by sensing, modelling, and output stage

A Comprehensive Review on Advancements in Real Time Detection and Conversion of Sign Gestures

M. Ahmed, T. Hasan

In preparation In preparation

Survey of real-time sign-gesture detection and translation systems: sensing, modelling approaches, datasets, and evaluation gaps.

Block diagram of a gas-leak sensing node triggering shutoff, ventilation, and alert subsystems

IoT Based Multi-Purpose Smart Automated Gas Hazard Prevention System

S. M. Taron, T. Hasan, et al.

ICMIME 2022 5th International Conference on Mechanical, Industrial and Materials Engineering

Embedded sensing node that detects gas leaks and automatically triggers shutoff, ventilation, and remote alerts.

BibTeX 
@inproceedings{taron2022gas,
  author    = {Taron, S. M. and Hasan, Tahir and others},
  title     = {IoT Based Multi-Purpose Smart Automated Gas Hazard Prevention System},
  booktitle = {5th International Conference on Mechanical, Industrial and Materials Engineering (ICMIME)},
  year      = {2022}
}