SPRA provides an international technical forum for experts from industry and academia to exchange ideas and present results of on-going research in most state-of-the-art areas of computers and communications.We solicit both academic, research, and industrial contributions. We welcome technical papers presenting research and practical results, position papers addressing the pros and cons of specific proposals. Topics of interests include but not limited to:
Track 1: Computer Vision
- Vision sensors
- Early vision
- Low-level vision
- Biologically motivated vision
- Illumination and reflectance modeling
- Image based modeling
- Physics-based vision
- Perceptual organization
- Shape modeling and encoding
- Computational photography
- 3D shape recovery
- Motion, tracking and video analysis
- 2D/3D object detection and recognition
- Scene understanding
- Occlusion and shadow detection
- Stereo and multiple view geometry
- Reconstruction and camera motion estimation
- Vision for graphics
- Vision for robotics
- Cognitive and embodied vision
Track 2: Biomedical Image Analysis
- Vision sensors
- Medical image and signal analysis
- Biological image and signal analysis
- Modeling, simulation and visualization
- Computer-aided detection and diagnosis
- Image guidance and robot guidance of interventions
- Content based image retrieval and data mining
- Medical and biological imaging
- Segmentation of medical images
- Molecular and cellular image analysis
- Volumetric image analysis
- Deformable object tracking and registration
- Computational anatomy and digital human
- VR/AR in medical education, diagnosis and surgery
- Medical robotics
- Brain-computer interfaces
- Data mining for biological databases
- Algorithms for molecular biology
Track 3: Pattern Recognition and Machine Learning
- Statistical, syntactic and structural pattern recognition
- Machine learning and data mining
- Artificial neural networks
- Dimensionality reduction and manifold learning
- Classification and clustering
- Representation and analysis in pixel/voxel images
- Support vector machines and kernel methods
- Symbolic learning
- Active and ensemble learning
- Deep learning
- Transfer learning
- Semi-supervised learning and spectral methods
- Model selection
- Reinforcement learning and temporal models
Track 4: Image, Speech, Signal and Video Processing
- Signal, image and video processing
- Image and video analysis and understanding
- Audio and acoustic processing and analysis
- Spoken language processing
- Sensor array & multichannel signal processing
- Segmentation, features and descriptors
- Texture and color analysis
- Enhancement, restoration and filtering
- Coding, compression and super-resolution
- Automatic speech and speaker recognition
- Multimedia analysis, indexing and retrieval