27th International Conference on Pattern Recognition (ICPR 2024)

The 27th International Conference on Pattern Recognition (ICPR 2024) covers topics such as:

• Computer Vision and Robotic Perception
  • Stereo and 3D vision
  • Early and low-level vision
  • Object detection and recognition
  • Multiple view geometry
  • Deformable models and registration
  • Motion, tracking and video analysis
  • Scene analysis and understanding
  • Learning for vision
  • Vision and language
  • Action and behavior recognition
  • Vision for robotics, robot navigation and SLAM
  • Perception for autonomous navigation and/or driving
  • Perceptually driven reinforcement learning
• Artificial Intelligence, Machine Learning for Pattern Analysis
  • Statistical learning theory
  • Classification and clustering
  • Neural network architectures and models
  • Syntactic and structural pattern recognition
  • Deep learning
  • Graph models
  • Online learning and continual learning
  • Representation learning
  • Transfer learning and meta learning
  • Supervised, unsupervised, self-supervised and semi-supervised learning
  • Active and ensemble learning
  • Multi-modal and multi-view learning
  • Compressed sensing and sparse representation
  • Reinforcement learning
  • Recurrent networks, temporal models and non-feed-forward methods
  • Large scale learning and big data
  • Generative models
  • Low-shot and long-tailed learning
• Biometrics and Human-Machine Interaction
  • Soft biometrics: skin, hair, ear, vein, facial expression
  • Hard biometrics: face, iris, fingerprint, palmprint
  • Multi-biometrics
  • Gait and behavior
  • Human-robot interaction
  • Person identification and re-identification
  • Social robotics
  • Brain-computer interfaces
  • Speech and natural language-based interaction
  • Human body motion and gesture-based interaction
  • Surveillance and security
  • Affective computing
  • Ethics and fairness issues in the use of biometrics
• Image, Video, Speech, and Signal Analysis
  • Image and video processing
  • Sensor array and multichannel signal processing
  • Segmentation, features and descriptors
  • Enhancement, restoration and filtering
  • Speech and speaker recognition
  • Coding, compression and super-resolution
  • Computational photography
  • Audio and acoustic processing
  • Image analysis with ill-structured and spatial information
  • Models, representations, and techniques for image mining
• Biomedical Image Analysis and Informatics
  • Clinical predictive modeling
  • Data-driven modeling of clinical care
  • Biomedical imaging techniques
  • Biostatistics
  • Medical image analysis
  • Quantitative microscopy
  • Visualization and 3D printing
  • Interactive segmentation
  • Medical applications
• Document and Media Analysis
  • Handwritten text recognition
  • Text and symbol recognition
  • Document understanding
  • Document image analysis
  • Scene text detection and recognition
  • Natural language processing
  • Content based image retrieval and data mining
  • Graphics recognition
  • Multimedia document analysis
  • Visual question and answering
  • Multimodal fusion
  • Media analysis for augmented and virtual reality
  • Video text detection and recognition
  • Table detection, recognition, and structure extraction
  • Human-document interaction