Visual analysis especially detection and recognition is one of the most important branches of pattern recognition, which focuses on localizing and classifying visual patterns involved in various data. In the past years, great progress has been achieved in both the theories and applications of visual analysis. A typical visual analysis system is composed of pre-processing, feature extraction, classifier design and post-processing. Nowadays, we have entered a new era of big visual data, which offers both opportunities and challenges to the field of visual analysis. We should seek new visual detection and recognition theories to be adaptive to big visual data. We should also push forward new visual applications benefited from big visual data.

Deep Learning, which can be treated as the most significant breakthrough in the past 10 years in the field of pattern recognition and machine learning, has greatly affected the computer vision methodology and achieved terrific progress in both academy and industry. It can be seen as a solution to change the whole visual system. It achieved an end-to-end visual analysis, merging previous steps of pre-processing, feature extraction, classifier design and post-processing. It is expected that the development of deep learning theories and applications would further influence the field of computer vision.

Since 2016, the international workshop on deep learning for pattern recognition has been held three times (DLPR 2016, DLPR 2018, DLPR 2020). It successfully brought together worldwide researchers and practitioners from academia and industry to present their innovative research and to discuss recent advancements. In this year, we aim to continuously organize this workshop in conjunction with the International Conference on Pattern Recognition to further emphasize the deep learning for visual analysis especially detection and recognition. We hope to solicit original contributions, of leading researchers and practitioners from academia as well as industry, which address a wide range of theoretical and application issues in deep learning for visual detection and analysis.


  • ­Deep learning for object recognition
  • Deep learning for object detection
  • ­Deep learning for object tracking
  • ­Deep learning for 3D detection and recognition
  • ­Deep learning for text detection and recognition
  • ­Deep learning for visual search
  • ­Deep learning for facial detection and recognition
  • ­Deep learning for action and behavior recognition
  • ­Deep learning for semantic segmentation, grouping and shape
  • ­Deep learning for detection and segmentation in medical image
  • ­Deep learning for anomaly detection
  • ­Other topics related to visual detection and recognition