About this Research Topic
Technology has evolved and advanced to harness human intelligence for the benefit of humanity, just like the visionary goal of artificial intelligence - to simulate, extend and expand human intelligence. With the opening of Industry 4.0, the establishment of smart factories with adaptability, resource efficiency, and genetic engineering is in full swing, with the aim of improving the intelligence of manufacturing. With the remarkable progress of deep learning theories and methods in the field of visual information processing, we would like to solicit some practical application cases of deep learning-based visual information processing methods in the field of industrial anomaly detection, not just database-based runtime results.
The development of science and technology is for the benefit of human beings. Through the publication of these proceedings, there are papers not only from industry but also from academia, and we aim to create a platform for mutual cooperation and build a bridge of collaboration between them. Our aim is to jointly promote the academic results and, more importantly, to have valuable academic research drive the Industrial Revolution 4.0. For example, high-precision segmentation-guided metal surface corrosion detection and corrosion degree assessment, multi-dimensional high-precision security inspection image recognition, industrial parts surface defect detection, and anomaly detection on industrial scenes or assembly lines are generically driving the industry's big development.
Topics include, but are not limited to:
• 2D and 3D anomaly detection
• Adversarial learning, adversarial attack, and defense methods
• Computational photography
• Datasets and evaluation
• Explainable AI, fairness, accountability, privacy, transparency
and ethics in vision anomaly detection
• Anomaly classification
• Low-level and physics-based vision
• Scene anomaly analysis and understanding
• Transfer, low-shot, semi-, and unsupervised learning
• Video analysis and understanding
• Vision + language, vision + other modalities
• Vision applications and systems, vision for robotics and autonomous vehicles
Short papers and reviews are both welcomed.
The development of science and technology is for the benefit of human beings. Through the publication of these proceedings, there are papers not only from industry but also from academia, and we aim to create a platform for mutual cooperation and build a bridge of collaboration between them. Our aim is to jointly promote the academic results and, more importantly, to have valuable academic research drive the Industrial Revolution 4.0. For example, high-precision segmentation-guided metal surface corrosion detection and corrosion degree assessment, multi-dimensional high-precision security inspection image recognition, industrial parts surface defect detection, and anomaly detection on industrial scenes or assembly lines are generically driving the industry's big development.
Topics include, but are not limited to:
• 2D and 3D anomaly detection
• Adversarial learning, adversarial attack, and defense methods
• Computational photography
• Datasets and evaluation
• Explainable AI, fairness, accountability, privacy, transparency
and ethics in vision anomaly detection
• Anomaly classification
• Low-level and physics-based vision
• Scene anomaly analysis and understanding
• Transfer, low-shot, semi-, and unsupervised learning
• Video analysis and understanding
• Vision + language, vision + other modalities
• Vision applications and systems, vision for robotics and autonomous vehicles
Short papers and reviews are both welcomed.
Keywords: vision information processing, pattern analysis, machine intelligence, image processing, deep learning, practical applications in industry
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
