2016/07/22 by Filip Piekniewski, Filip Piȩkniewski, Patryk A. Laurent +11 · 1 voice · 1 citation
Computer Science · #Advanced Vision and Imaging #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.1607.06854
38 pages, 20 figures, v3. Added several citations to relevant papers, expanded the discussion of existing approach in deep learning
openalex publication_date 2016/07/22 · arxiv published 2016/07/22 · arxiv created 2016/09/30 · arxiv updated 2016/10/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Understanding visual reality involves acquiring common-sense knowledge about countless regularities in the visual world, e.g., how illumination alters the appearance of objects in a scene, and how motion changes their apparent spatial relationship. These regularities are hard to label for training supervised machine learning algorithms; consequently, algorithms need to learn these regularities from the real world in an unsupervised way. We present a novel network meta-architecture that can learn world dynamics from raw, continuous video. The components of this network can be implemented using any algorithm that possesses three key capabilities: prediction of a signal over time, reduction of signal dimensionality (compression), and the ability to use supplementary contextual information to inform the prediction. The presented architecture is highly-parallelized and scalable, and is implemented using localized connectivity, processing, and learning. We demonstrate an implementation of this architecture where the components are built from multi-layer perceptrons. We apply the implementation to create a system capable of stable and robust visual tracking of objects as seen by a moving camera. Results show performance on par with or exceeding state-of-the-art tracking algorithms. The tracker can be trained in either fully supervised or unsupervised-then-briefly-supervised regimes. Success of the briefly-supervised regime suggests that the unsupervised portion of the model extracts useful information about visual reality. The results suggest a new class of AI algorithms that uniquely combine prediction and scalability in a way that makes them suitable for learning from and --- and eventually acting within --- the real world.