no code implementations • 22 Jan 2024 • Shoaib Meraj Sami, Md Mahedi Hasan, Nasser M. Nasrabadi, Raghuveer Rao
The transductive transfer learning (TTL) method that incorporates a CycleGAN-based unpaired domain translation network has been previously proposed in the literature for effective ATR annotation.
no code implementations • 14 Dec 2023 • Md Mahedi Hasan, Shoaib Meraj Sami, Nasser Nasrabadi
However, learning a discriminative joint embedding within the multimodal space poses a considerable challenge due to the semantic gap in the unaligned image-text representations, along with the complexities arising from ambiguous and incoherent textual descriptions of the face.
no code implementations • 13 Aug 2023 • Md Mahedi Hasan, Nasser Nasrabadi
Additionally, we design a textual feature refinement module (TFRM) that refines the textual features of the pre-trained BERT encoder by updating the contextual embeddings.
no code implementations • 22 Feb 2023 • Md Shamimul Islam, A. J. M. Akhtarujjaman Joha, Md Nur Hossain, Sohaib Abdullah, Ibrahim Elwarfalli, Md Mahedi Hasan
The proposed model utilizes human pose information, which has shown to be successful in analyzing sign language patterns.
1 code implementation • 27 Dec 2018 • Sheikh Muhammad Saiful Islam, Md Mahedi Hasan, Sohaib Abdullah
Diabetic Retinopathy (DR) is a constantly deteriorating disease, being one of the leading causes of vision impairment and blindness.
no code implementations • 31 Oct 2018 • Sheikh Muhammad Saiful Islam, Md Mahedi Hasan
The present gap between the amount of available protein sequence due to the development of next generation sequencing technology (NGS) and slow and expensive experimental extraction of useful information like annotation of protein sequence in different functional aspects, is ever widening, which can be reduced by employing automatic function prediction (AFP) approaches.