Search Results for author: Mahmudul Hasan

Found 24 papers, 6 papers with code

Faster, Lighter, More Accurate: A Deep Learning Ensemble for Content Moderation

no code implementations10 Sep 2023 Mohammad Hosseini, Mahmudul Hasan

Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives.

Philosophy

Efficient Movie Scene Detection using State-Space Transformers

1 code implementation CVPR 2023 Md Mohaiminul Islam, Mahmudul Hasan, Kishan Shamsundar Athrey, Tony Braskich, Gedas Bertasius

Given a sequence of frames divided into movie shots (uninterrupted periods where the camera position does not change), the S4A block first applies self-attention to capture short-range intra-shot dependencies.

Video Recognition

BLPnet: A new DNN model and Bengali OCR engine for Automatic License Plate Recognition

no code implementations18 Feb 2022 Md. Saif Hassan Onim, Hussain Nyeem, Koushik Roy, Mahmudul Hasan, Abtahi Ishmam, Md. Akiful Hoque Akif, Tareque Bashar Ovi

This paper reports a computationally efficient and reasonably accurate Automatic License Plate Recognition (ALPR) system for Bengali characters with a new end-to-end DNN model that we call Bengali License Plate Network(BLPnet).

License Plate Recognition Management +1

The Case for High-Accuracy Classification: Think Small, Think Many!

no code implementations18 Mar 2021 Mohammad Hosseini, Mahmudul Hasan

Given the insight gained from our experiments, we hence propose a "think small, think many" philosophy in classification scenarios: that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, lightweight models with narrowed-down color spaces can possibly lead to predictions with higher accuracy.

Classification General Classification +2

Improving Multimodal Accuracy Through Modality Pre-training and Attention

no code implementations11 Nov 2020 Aya Abdelsalam Ismail, Mahmudul Hasan, Faisal Ishtiaq

Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance.

Emotion Recognition Sentiment Analysis

Virtual Screening of Plant Metabolites against Main protease, RNA-dependent RNA polymerase and Spike protein of SARS-CoV-2: Therapeutics option of COVID-19

no code implementations22 May 2020 Md Sorwer Alam Parvez, Kazi Faizul Azim, Abdus Shukur Imran, Topu Raihan, Aklima Begum, Tasfia Saiyara Shammi, Sabbir Howlader, Farhana Rumzum Bhuiyan, Mahmudul Hasan

The molecular interaction study revealed that Rifampin (-16. 3 kcal/mol) were topmost inhibitor of MPP where Azobechalcone were found most potent plant therapeutics for blocking the RdRp (-15. 9 kcal /mol) and S (-14. 4 kcal/mol) protein of SARS-CoV-2.

Blocking Molecular Docking

Comparisonal study of Deep Learning approaches on Retinal OCT Image

no code implementations16 Dec 2019 Nowshin Tasnim, Mahmudul Hasan, Ishrak Islam

In this research, we have taken such an attempt to detect retinal diseases from optical coherence tomography (OCT) X-ray images.

Prediction and Description of Near-Future Activities in Video

no code implementations2 Aug 2019 Tahmida Mahmud, Mohammad Billah, Mahmudul Hasan, Amit K. Roy-Chowdhury

Most of the existing works on human activity analysis focus on recognition or early recognition of the activity labels from complete or partial observations.

Video Captioning Video Description

Attack and Anomaly Detection in IoT Sensors in IoT Sites Using Machine Learning Approaches

no code implementations journal 2019 Mahmudul Hasan, Md. Milon Islam, Ishrak Islam, M. M. A. Hashem

The machine learning (ML) algorithms that have been used here are Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Artificial Neural Network (ANN).

Anomaly Detection BIG-bench Machine Learning

Context-Aware Query Selection for Active Learning in Event Recognition

no code implementations9 Apr 2019 Mahmudul Hasan, Sujoy Paul, Anastasios I. Mourikis, Amit K. Roy-Chowdhury

We formulate a conditional random field model that encodes the context and devise an information-theoretic approach that utilizes entropy and mutual information of the nodes to compute the set of most informative queries, which are labeled by a human.

Active Learning Activity Recognition +1

Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation

12 code implementations20 Feb 2018 Md Zahangir Alom, Mahmudul Hasan, Chris Yakopcic, Tarek M. Taha, Vijayan K. Asari

In this paper, we propose a Recurrent Convolutional Neural Network (RCNN) based on U-Net as well as a Recurrent Residual Convolutional Neural Network (RRCNN) based on U-Net models, which are named RU-Net and R2U-Net respectively.

Image Classification Image Segmentation +7

Handwritten Bangla Character Recognition Using The State-of-Art Deep Convolutional Neural Networks

1 code implementation28 Dec 2017 Md Zahangir Alom, Peheding Sidike, Mahmudul Hasan, Tark M. Taha, Vijayan K. Asari

In spite of advances in object recognition technology, Handwritten Bangla Character Recognition (HBCR) remains largely unsolved due to the presence of many ambiguous handwritten characters and excessively cursive Bangla handwritings.

Object Recognition Translation

Improved Inception-Residual Convolutional Neural Network for Object Recognition

no code implementations28 Dec 2017 Md Zahangir Alom, Mahmudul Hasan, Chris Yakopcic, Tarek M. Taha, Vijayan K. Asari

In this paper, we introduce a new DCNN model called the Inception Recurrent Residual Convolutional Neural Network (IRRCNN), which utilizes the power of the Recurrent Convolutional Neural Network (RCNN), the Inception network, and the Residual network.

Object Object Recognition

Joint Prediction of Activity Labels and Starting Times in Untrimmed Videos

no code implementations ICCV 2017 Tahmida Mahmud, Mahmudul Hasan, Amit K. Roy-Chowdhury

We propose a network similar to a hybrid Siamese network with three branches to jointly learn both the future label and the starting time.

Inception Recurrent Convolutional Neural Network for Object Recognition

1 code implementation CVPR 2015 Md Zahangir Alom, Mahmudul Hasan, Chris Yakopcic, Tarek M. Taha

Furthermore, we have investigated IRCNN performance against equivalent Inception Networks and Inception-Residual Networks using the CIFAR-100 dataset.

Object Object Recognition

Learning Temporal Regularity in Video Sequences

2 code implementations CVPR 2016 Mahmudul Hasan, Jonghyun Choi, Jan Neumann, Amit K. Roy-Chowdhury, Larry S. Davis

Perceiving meaningful activities in a long video sequence is a challenging problem due to ambiguous definition of 'meaningfulness' as well as clutters in the scene.

Semi-supervised Anomaly Detection Video Anomaly Detection

Context Aware Active Learning of Activity Recognition Models

no code implementations ICCV 2015 Mahmudul Hasan, Amit K. Roy-Chowdhury

We formulate a conditional random field (CRF) model that encodes the context and devise an information theoretic approach that utilizes entropy and mutual information of the nodes to compute the set of most informative query instances, which need to be labeled by a human.

Active Learning Activity Recognition +1

Incremental Activity Modeling and Recognition in Streaming Videos

no code implementations CVPR 2014 Mahmudul Hasan, Amit K. Roy-Chowdhury

Most of the state-of-the-art approaches to human activity recognition in video need an intensive training stage and assume that all of the training examples are labeled and available beforehand.

Active Learning Human Activity Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.