1 code implementation • 19 Oct 2024 • Md Mubtasim Ahasan, Md Fahim, Tasnim Mohiuddin, A K M Mahbubur Rahman, Aman Chadha, Tariq Iqbal, M Ashraful Amin, Md Mofijul Islam, Amin Ahsan Ali
Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis.
no code implementations • 9 Jun 2024 • Ovi Paul, Abu Bakar Siddik Nayem, Anis Sarker, Amin Ahsan Ali, M Ashraful Amin, AKM Mahbubur Rahman
The results show that the annotated BD-SAT is sufficient to train large deep learning models with adequate accuracy for five major LULC classes: forest, farmland, built-up areas, water bodies, and meadows.
no code implementations • 31 May 2023 • Mir Sazzat Hossain, Sugandha Roy, K. M. B. Asad, Arshad Momen, Amin Ahsan Ali, M Ashraful Amin, A. K. M. Mahbubur Rahman
Out of the estimated few trillion galaxies, only around a million have been detected through radio frequencies, and only a tiny fraction, approximately a thousand, have been manually classified.
no code implementations • 4 Jan 2022 • Tonmoay Deb, Akib Sadmanee, Kishor Kumar Bhaumik, Amin Ahsan Ali, M Ashraful Amin, A K M Mahbubur Rahman
However, growing model complexity for visual data encourages more explicit feature interaction for fine-grained information, which is currently absent in the video captioning domain.
1 code implementation • 27 Apr 2021 • Kashob Kumar Roy, Amit Roy, A K M Mahbubur Rahman, M Ashraful Amin, Amin Ahsan Ali
Graph Neural Networks (GNNs) learn low dimensional representations of nodes by aggregating information from their neighborhood in graphs.
1 code implementation • 27 Apr 2021 • Kashob Kumar Roy, Amit Roy, A K M Mahbubur Rahman, M Ashraful Amin, Amin Ahsan Ali
Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks.
1 code implementation • 26 Apr 2021 • Amit Roy, Kashob Kumar Roy, Amin Ahsan Ali, M Ashraful Amin, A K M Mahbubur Rahman
However, most state-of-the-art approaches have designed spatial-only (e. g. Graph Neural Networks) and temporal-only (e. g. Recurrent Neural Networks) modules to separately extract spatial and temporal features.
1 code implementation • 31 Mar 2021 • Amit Roy, Kashob Kumar Roy, Amin Ahsan Ali, M Ashraful Amin, A K M Mahbubur Rahman
Most of the recent works employed graph neural networks(GNN) with multiple layers to capture the spatial dependency.
1 code implementation • 7 Mar 2021 • M Tanjid Hasan Tonmoy, Saif Mahmud, A K M Mahbubur Rahman, M Ashraful Amin, Amin Ahsan Ali
Wearable sensor based human activity recognition is a challenging problem due to difficulty in modeling spatial and temporal dependencies of sensor signals.
no code implementations • 25 Nov 2020 • Qianwei Cheng, AKM Mahbubur Rahman, Anis Sarker, Abu Bakar Siddik Nayem, Ovi Paul, Amin Ahsan Ali, M Ashraful Amin, Ryosuke Shibasaki, Moinul Zaber
Image encompassing 70% of the urban space was used for training and the remaining 30% was used for testing and validation.
2 code implementations • 17 Mar 2020 • Saif Mahmud, M Tanjid Hasan Tonmoy, Kishor Kumar Bhaumik, A K M Mahbubur Rahman, M Ashraful Amin, Mohammad Shoyaib, Muhammad Asif Hossain Khan, Amin Ahsan Ali
In this regard, the existing recurrent or convolutional or their hybrid models for activity recognition struggle to capture spatio-temporal context from the feature space of sensor reading sequence.