ECTS credits ECTS credits: 3
ECTS Hours Rules/Memories Hours of tutorials: 1 Expository Class: 15 Interactive Classroom: 10 Total: 26
Use languages Spanish, Galician
Type: Ordinary Degree Subject RD 1393/2007 - 822/2021
Departments: Electronics and Computing
Areas: Computer Science and Artificial Intelligence
Center Higher Technical Engineering School
Call: Second Semester
Teaching: With teaching
Enrolment: Enrollable
To understand advanced concepts in computer vision, the various techniques currently in use, and their areas of application.
Upon successful completion of the course, students will:
- Understand advanced concepts in image processing.
- Be able to implement and apply the fundamental algorithms and techniques for advanced image processing, analysis, and interpretation.
- Develop the ability to apply the most appropriate computer vision technique to real-world problems.
- Visual Transformers
- Multimodal Models
- Open-vocabulary Detection and Segmentation
- Generative Models
BASIC
- Richard Szeliski (2022), Computer Vision: Algorithms and Applications, 2nd ed., Springer.
- Uday Kamath, Kenneth Graham, Wael Emara (2022), Transformers for Machine Learning: A Deep Dive, Chapman & Hall.
SUPPLEMENTARY
- Omar Sanseviero, Pedro Cuenca, Apolinário Passos, Jonathan Whitaker (2024), Hands-On Generative AI with Transformers and Diffusion Models, O'Reilly.
BASIC AND GENERAL
- CB2: Students should be able to apply their knowledge to their work or vocation in a professional manner and possess the competencies usually demonstrated through the development and defense of arguments and problem-solving within their field of study.
- CB4: Students should be able to convey information, ideas, problems, and solutions to both specialist and non-specialist audiences.
- CG4: Ability to select and justify appropriate methods and techniques to solve a specific problem or to develop and propose new methods based on artificial intelligence.
- CG5: Ability to design new computational systems and/or evaluate the performance of existing systems that integrate artificial intelligence models and techniques.
TRANSVERSAL
- TR1: Ability to communicate and convey their knowledge, skills, and abilities.
- TR3: Ability to create new models and solutions independently and creatively, adapting to new situations. Initiative and entrepreneurial spirit.
- TR5: Ability to develop ethical, non-discriminatory, and trustworthy models, techniques, and solutions based on artificial intelligence.
SPECIFIC
- CE12: Understand the fundamentals of artificial intelligence algorithms and models for solving complex problems, understand their computational complexity, and be capable of designing new models.
The course's teaching dynamics will encourage active student participation in both lectures and tutorials. The theoretical and practical sessions will focus on the progressive development of the intended competencies using student-centered methodologies.
Each thematic block will be introduced by the instructor with a presentation of its objectives, key contents, and recommended resources. From there, additional documentation, readings, examples, and supporting materials will be provided to guide independent study. These sessions will target competencies such as CG4, CG5, and CE12.
Throughout the course, various tasks will be proposed, including practical exercises, problem-solving, oral presentations, or small projects, which may be carried out individually or in groups. These activities will have previously established deadlines for submission or presentation, which will be communicated through the course's official communication channels.
In the practical sessions, students will apply the knowledge acquired using specific software tools for each block. These sessions will help develop competencies such as CB2, CB4, CG5, TR1, TR3, and CE12.
Student work will be carried out autonomously, always supported and guided by the teaching staff. The course will also include lab scripts, seminars, and other complementary activities to reinforce learning.
Assessment will consider both the theoretical part (40%) and the practical part (60%). To pass the course, students must achieve an overall score of 5 out of 10 or higher, according to the following:
- Theoretical part: Assessed through a single exam held on the official date. A minimum grade of 4 out of 10 is required to pass the course. Otherwise, the exam must be repeated in the resit opportunity.
- Practical part: The practical exercises proposed during interactive sessions will be assessed in the next session, and will correspond to the topics indicated in the Contents Section. Two assignments will be proposed, to be submitted at the end of the second and fourth thematic blocks. A minimum grade of 4 out of 10 is required in this part to pass the course.
Students who do not attend the exam and do not submit any practical work will be marked as "not presented." Attendance at both interactive and lecture sessions will not be mandatory and will have no impact on the final grade.
To pass the course in the resit period, students must be assessed on all pending mandatory parts, as specified above. Grades obtained for the remaining parts during the course will be retained.
In accordance with the ETSE's anti-plagiarism policy (approved by the ETSE Board on 19/12/2019), total or partial copying of any practical or theoretical assignment will result in failing both assessment opportunities of the course, with a grade of 0 in both cases.
- On-site work time: 25 total hours, divided into 15 lecture hours and 10 interactive hours.
- Personal work time: 50 total hours, divided into 20 hours of independent study (theory and practice) and 30 hours for assignments, projects, and other activities.
It is recommended that students have previously passed the course "Computer Vision."
Students are encouraged to solve, implement, verify, and validate all proposed exercises and practicals. It is also considered important to make use of tutorials to resolve any doubts.
Teaching will be supported by the use of the Virtual Campus, which will serve as the central space for accessing course materials (presentations, texts, exercises, readings...), and for communication with the teaching staff, whether through email, forums, or online tutorials.
The course will be taught in Galician.
Nicolas Vila Blanco
Coordinador/a- Department
- Electronics and Computing
- Area
- Computer Science and Artificial Intelligence
- Phone
- 881815509
- nicolas.vila [at] usc.es
- Category
- Professor: LOU (Organic Law for Universities) PhD Assistant Professor
Cesar Díaz Parga
- Department
- Electronics and Computing
- Area
- Computer Science and Artificial Intelligence
- cesardiaz.parga [at] usc.es
- Category
- Xunta Pre-doctoral Contract
| Tuesday | |||
|---|---|---|---|
| 18:30-20:00 | Grupo /CLE_01 | Galician | IA.01 |
| Wednesday | |||
| 15:30-16:30 | Grupo /CLIL_01 | Galician | IA.01 |
| 05.25.2026 16:00-20:00 | Grupo /CLIL_01 | IA.01 |
| 05.25.2026 16:00-20:00 | Grupo /CLE_01 | IA.01 |
| 07.01.2026 09:30-14:00 | Grupo /CLIL_01 | IA.11 |
| 07.01.2026 09:30-14:00 | Grupo /CLE_01 | IA.11 |