The following web courses are offered to AIDA Students (PhD students, Post-doc researchers, possibly qualified MSc students of AIDA Members) and other students worldwide.

AIDA Members are University partners of ICT48 Projects: AI4Media, HumanE AI Network, VISION.

Student eligibility: PhD students, Post-doc researchers, MSc students of AIDA Members can participate on preferential favorable terms, according to the rules of each short course. Qualified MSc students from AIDA Members can participate on availability basis.

Registration: Interested students should enter the course webpage to register.

CVML Web Lecture Series

Description: CVML Web courses are offered on the following 17 topics: Machine Learning, Neural Networks/Deep Learning, Computer Vision (CV), Image Processing, 2D Computer Vision/Image Analysis, 3D Imaging, Video Processing and Analysis, Signal and Systems, Digital Signal Processing and Analysis, Human Centered Computing, Network Theory/Social Media Analysis, Autonomous Systems and Robotics, Autonomous Cars, Autonomous Drones, Autonomous Marine Systems, CVML Mathematical Foundations, CVML Development and Programming Tools.

Each CVML Web Course has around 16 lectures and can cover more than one topic.

Institution: Aristotle University of Thessaloniki

Department: Department of Informatics

ECTS: 0.5 per CVML Web Course

Level: PhD/MSc/Senior undergraduate

Semester: Any time of the year.

Duration: Around 1 month per CVML Web Course.

Language: English

Participation: Asynchronous study mode through lecture PDFs, videos and understanding questionnaires to be accessed and studied at own pace.

Lecturer: Prof. Ioannis Pitas, pitas@csd.auth.gr

Link to course: https://icarus.csd.auth.gr/cvml-web-lecture-series/

Multiple Parametric Models Fitting

Description: Estimation of multiple parametric models that fit data corrupted by noise and outliers in Computer Vision applications. Multi-model fitting problem as a labeling energy minimization procedure assigning data points to model instances. Perspective based on preference analysis: the estimation of multiple structure is addressed in a procedural way leveraging on simple to implement clustering techniques. Perspective based on hypergraphs.

Institution: Politecnico Milano, University of Udine

Department: 

ECTS:

Level:

Semester: Any time of the year.

Duration:

Language: English

Participation: Asynchronous study mode through lecture PDFs, videos and understanding questionnaires to be accessed and studied at own pace.

Lecturer: Prof. Luca Magri luca.magri@polimi.it,  Andrea Fusiello andrea.fusiello@uniud.it, Eleonora Maset eleonora.maset@uniud.it

Link to course:

Synchronization: a general framework for mosaicking, 3D reconstruction, matching and segmentation problems

Description: The synchronization problem in Computer Vision to infer the unknown states of a network of nodes, where only the ratio between pairs of states can be measured. synchronization  in structure from motion, pose graph optimization,  point coordinates in 3D registration, image mosaicking and motion segmentation.

Institution: University of Udine, Technical University of Munich

Department: 

ECTS:

Level:

Semester: Any time of the year.

Duration:

Language: English

Participation: Asynchronous study mode through lecture PDFs, videos and understanding questionnaires to be accessed and studied at own pace.

Lecturer: Prof. F. Arrigoni, Prof. E. Maset, Prof. A. Fusiello, Prof. F. Bernard

Link to course:

Change and Anomaly Detection in Images, Signals and datastreams

Description: Change and anomaly-detection in signal/image analysis following the machine-learning perspective of supervised, semi-supervised and unsupervised monitoring tasks. Traditional models: autoencoders, learned projections and dictionaries yielding sparse representations. Deep learning models: CNNs, deep-one-class classifiers and deep generative models.

Institution: Politecnico di Milano

Department: 

ECTS:

Level:

Semester: Any time of the year.

Duration:

Language: English

Participation: Asynchronous study mode through lecture PDFs, videos and understanding questionnaires to be accessed and studied at own pace.

Lecturer: Prof. Giacomo Boracchi giacomo.boracchi@polimi.it, Diego Carrera diego.carrera@st.com

Link to course:

Graphbased Methods for Learning and Inference Problems in Pattern Analysis

Description: Graph-based methods in pattern recognition. The course aims at covering the fundamental principles of stochastic, spectral, probabilistic and manifold based methods related with graphs and their applications to segmentation and grouping, matching, classification and recognition. It also cover recent trends and developments related to deep networks and link inference in the structural pattern analysis space.

Institution: CSIRO AU, University of Alicante

Department: 

ECTS:

Level:

Semester: Any time of the year.

Duration:

Language: English

Participation: Asynchronous study mode through lecture PDFs, videos and understanding questionnaires to be accessed and studied at own pace.

Lecturer: Prof. Antonio Robles-Kelly antonio.robles-kelly@deakin.edu.au, Francisco Escolano Ruiz escolano.ua@gmail.com 

Link to course:

High-Dynamic-Range imaging: history, state of the art, improvements and limits

Description: Description of the dynamic range problem. Possible goals of the HDR pipeline: reproducing light field, reproducing appearance, improving image aesthetic and visibility. Limits of accurate camera acquisition (range and color) and the usable range of light for displays presented to human vision.

Institution: Politecnico di Milano

Department: 

ECTS:

Level:

Semester: Any time of the year.

Duration:

Language: English

Participation: Asynchronous study mode through lecture PDFs, videos and understanding questionnaires to be accessed and studied at own pace.

Lecturer: Prof. Alessandro Rizzi alessandro.rizzi@unimi.it 

Link to course: