An Attention Module for Convolutional Neural Networks

Attention mechanism has been regarded as an advanced technique to capture long-range feature interactions and to boost the representation capability for convolutional neural networks. However, we found two ignored problems in current attentional activations-based models: the approximation problem and the insufficient capacity problem of the...

Indexing and Retrieval of Visual Design Representations

Recognizing architectural representations

Simulation and representation. Learning from airflow analyses in buildings

Route analysis in complex buildings

Fuzzy Modeling of Floor Plan Layout