no code implementations • 29 Dec 2022 • 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.
no code implementations • 23 Apr 2022 • Mahmudul Hasan, Jakub R. Kaczmarzyk, David Paredes, Lyanne Oblein, Jaymie Oentoro, Shahira Abousamra, Michael Horowitz, Dimitris Samaras, Chao Chen, Tahsin Kurc, Kenneth R. Shroyer, Joel Saltz
Understanding the impact of tumor biology on the composition of nearby cells often requires characterizing the impact of biologically distinct tumor regions.
no code implementations • 26 Mar 2022 • Fozlur Rahman, Marium Sana Mim, Feekra Baset Baishakhi, Mahmudul Hasan, Md. Kishor Morol
Virtual Reality has become a significant element of education throughout the years.
no code implementations • 18 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).
no code implementations • 9 Dec 2021 • Abtahi Ishmam, Mahmudul Hasan, Md. Saif Hassan Onim, Koushik Roy, Md. Akiful Haque Akif, Hossain Nyeem
In contrast, the model with MediaPipe offers faster landmark detection capability with an average FPS of 20 and detection accuracy of 94. 4%.
no code implementations • 18 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.
no code implementations • 11 Nov 2020 • Aya Abdelsalam Ismail, Mahmudul Hasan, Faisal Ishtiaq
Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance.
1 code implementation • International Conference on Cyber Security and Computer Science 2020 • Pritom Mojumder, Mahmudul Hasan, Md. Faruque Hossain, K. M. Azharul Hasan
Such types of task in the Bangla language is also important.
no code implementations • 22 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.
no code implementations • 15 Apr 2020 • Md. Sorwer Alam Parvez, Md. Adnan Karim, Mahmudul Hasan, Jomana Jaman, Ziaul Karim, Tohura Tahsin, Md. Nazmul Hasan, Mohammad Jakir Hosen
The pandemic prevalence of COVID-19 has become a very serious global health issue.
no code implementations • 16 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.
no code implementations • 2 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.
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).
no code implementations • 9 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.
11 code implementations • 20 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.
1 code implementation • 28 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.
no code implementations • 28 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.
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.
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.
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.
Ranked #2 on Traffic Accident Detection on A3D
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.
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.