Computational Knowledge Vision

Computational Knowledge Vision: The First Footprints presents a novel advanced framework which combines structuralized knowledge and visual models—Computational Knowledge Vision. In advanced image and visual perception studies, a visual model's understanding and reasoning ability often determine whether it works well in complex scenarios. This book presents state-of-the-art mainstream vision models for visual perception. Computer vision is one of the key gateways to artificial intelligence and a significant component of modern intelligent systems. Currently, computer vision systems are highly specialized and very limited in their ability to do visual reasoning and causal inference. We need task-specific designs and large amounts of labeled training data for model training. However, the models trained in this way still lack a general understanding of common sense that is obvious to the average adult and cannot describe the workings of our physical and social worlds. Humans can thoroughly understand visual scenes because of priori knowledge from many domains and can learn and reason effectively based on their knowledge. Questions naturally arise (1) how can human knowledge be incorporated with visual models? (2) how does human knowledge promote the performance of visual models? To address these problems, Computational Knowledge Vision: The First Footprints proposes a new framework for computer vision– computational knowledge vision. a concept and basic framework of Computational Knowledge Vision that extends the knowledge engineering methodology to the computer vision fielda first retrospect work related to Computational Knowledge Vision in the light of the connectionist and symbolist streamsdiscusses neural networks, meta-learning, graph, and Transformer modelsillustrates a basic framework for Computational Knowledge Vision, whose essential techniques include structuralized knowledge, knowledge projection, and conditional feedback. The framework aims to enable visual models to gain the ability to represent, understand, and reason. We also describe in-depth works in Computational Knowledge Vision and its extensions in other fields