4 papers
Layout Anything: One Transformer for Universal Room Layout Estimation
Md Sohag Mia, Muhammad Abdullah Adnan
We present Layout Anything, a transformer-based framework for indoor layout estimation that adapts the OneFormer's universal segmentation architecture to geometric structure predic…
GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection
Md Sohag Mia, Md Nahid Hasan, Muhammad Abdullah Adnan
Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic information. Capturing contextu…
DANet: Enhancing Small Object Detection through an Efficient Deformable Attention Network
Md Sohag Mia, Abdullah Al Bary Voban, Abu Bakor Hayat Arnob +3
Efficient and accurate detection of small objects in manufacturing settings, such as defects and cracks, is crucial for ensuring product quality and safety. To address this issue,…
ViTs are Everywhere: A Comprehensive Study Showcasing Vision Transformers in Different Domain
Md Sohag Mia, Abu Bakor Hayat Arnob, Abdu Naim +2
Transformer design is the de facto standard for natural language processing tasks. The success of the transformer design in natural language processing has lately piqued the intere…