The teaching is organized as follows:

Learning objectives

The course introduces students to the fundamental theories and concepts of human-computer interaction (HCI), which is an interdisciplinary field that draws from cognitive psychology, computer science, and design. HCI aims to provide both theoretical understanding and hands-on experience in key aspects of human perception, cognition, and learning as they relate to interface design, implementation, and evaluation. Covered topics include the foundations of HCI, focusing on human factors, interaction design, usability, and gaming and gamification. The course also explores visual interaction techniques, 3D model reconstruction, and rendering in Unity. The curriculum further extends to multimodal interfaces (touch, vision, natural language, audio). Special emphasis will be placed on equipping students with foundational knowledge, methodologies, and tools necessary for designing, implementing, and evaluating computer systems capable of capturing, representing, and automatically analyzing user behavior. This encompasses various forms of non-verbal communication, including gestures, movements, facial expressions, and speech. Moreover, students will learn strategies for effectively interacting with users by providing multisensory feedback, utilizing elements such as images, sounds, and control of actuators.

At the end of the course, students will:
- Understand the rationale behind utilizing multimodal interactive systems for specific applications, comprehend the logical architectures defining the main components of such systems, grasp the design and development guidelines for multimodal interactive systems, and recognize the potential application areas for their successful deployment.
- Familiarize themselves with the key devices for capturing user behaviour data, comprehend their functionality, and discern appropriate usage scenarios.
- Acquire knowledge of essential techniques for representing and automatically analysing user behaviour, including those that process data from multiple sensor devices across various sensory channels.
-Demonstrate proficiency in designing and implementing major components of a multimodal interactive system using the development tools introduced in lectures and practical sessions throughout the course.

Prerequisites and basic notions

Basic knowledge of statistics and computer graphics

Program

## Theory
* **Introduction:** Motivation, course objectives, professional opportunities, open research challenges, overview of the course syllabus, and examination methods.
* **Foundations of Human–Computer Interaction (HCI):** Human factors, interaction design, usability, games and gamification.
* **Visual Interaction:** Camera calibration, Structure from Motion (SfM), and 3D scene reconstruction.
* **Nonverbal Behavior in Communication:** Types of nonverbal behavior (facial expressions, gestures, posture, and eye gaze), data collection methodologies, software tools for nonverbal behavior analysis, and annotation tools (e.g., ELAN).
* **Automated Analysis of Human Behavior:** Analysis of body movements, gestures, facial expressions, and speech; data acquisition techniques, feature extraction, and automated behavior analysis.
* **Social Artificial Intelligence:** Applications of social AI, foundations of social psychology and organizational psychology, and social robotics.
* **Affective Computing:** Theories of emotion, emotion recognition systems, and applications of emotion recognition in Human–Computer Interaction.
* **Multimodal Integration of Nonverbal Cues:** Techniques for combining multimodal information, including early and late fusion approaches.
## Laboratory
* **Deep Image Matching:** Python implementation of feature detection and feature matching algorithms.
* **3D Model Reconstruction:** Structure from Motion using Zephyr.
* **Camera Pose Estimation:** C# implementation of Fiore's camera pose estimation method.
* **3D Graphics:** 3D modeling and rendering using Unity.
* **Model-Based Augmented Reality:** Implementation of a complete augmented reality pipeline integrating Python-based computer vision algorithms with Unity.
* **Advanced Topics:** Deep learning-based camera pose estimation and 3D model recognition.

Bibliography

Didactic methods

Lectures and laboratory sessions

Learning assessment procedures

The exam consists of the development of a project, the delivery of a written report and an oral interview dedicated to the presentation and discussion of the project and the report.

Evaluation criteria

To pass the exam, students must demonstrate: - understanding the concepts of multimodal human-computer interaction and the design of interactive and intelligent systems; - being able to present their arguments precisely and coherently; - being able to apply the knowledge acquired to implement practical HCI systems;

Criteria for the composition of the final grade

50% oral 50% laboratory activity evaluation

Exam language

Inglese o Italiano (English or Italian)