The article builds a bridge between the Gestalt principles in human perception (describing how visual elements are interpreted) and convolutional neural networks modeling. It suggests that a single principle – adoption to the statistical structure of the environment might suffice to explain perceptual mechanisms.
Continue ReadingLayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
A multi-modal framework that integrates a spatial-aware self-attention mechanism into the Transformer architecture
Continue ReadingAs We Could Have Thought: Deploying Historical Narratives of the Memex in Support of Innovation
An important warning about the use of simplistic historical arguments to undergird innovation where the notion of ideal users conflicted with existing paradigms.
Continue Reading