UnivIS
Informationssystem der Friedrich-Alexander-Universität Erlangen-Nürnberg © Config eG 
FAU Logo
  Sammlung/Stundenplan    Modulbelegung Home  |  Rechtliches  |  Kontakt  |  Hilfe    
Suche:      Semester:   
 
 Darstellung
 
Druckansicht

 
 
 Außerdem im UnivIS
 
Vorlesungs- und Modulverzeichnis nach Studiengängen

 
 
Veranstaltungskalender

Stellenangebote

Möbel-/Rechnerbörse

 
 
Vorlesungsverzeichnis >> Technische Fakultät (TF) >>

  Seminar Computer Vision (SemCV)

Dozentinnen/Dozenten
Anguelos Nicolaou, Ronak Kosti, Ph.D.

Angaben
Seminar
4 SWS, ECTS-Studium, ECTS-Credits: 5, Sprache Englisch, This course will be held online until the coronavirus pandemic is contained to such an extent that the Bavarian state government can allow face-to-face teaching again
Zeit und Ort: Di 14:00 - 16:00, 02.134-113

Studienfächer / Studienrichtungen
WPF INF-MA ab 1
WPF CE-MA-SEM ab 1
WPF ICT-MA ab 1

Inhalt
Seminar Computer Vision (CV) will consist mostly of students presenting Computer Vision scientific literature. This seminar will be designed as a micro-conference where lecturers will be the reviewers/chairs. The seminar follows ‘View Points’ and ‘CV topics’ in parallel. Each CV topic has to be explored at the least on each of the listed view points. So, every presentation on any particular cv topic will assess or evaluate how it fares on each of the view points.

Seminar Requirements:

Familiarity with Scientific reading/writing (in English)

Familiarity with Image or Signal processing

View points:

1. Energy

2. Reproducibility

3. Interpretability

4. Performance Evaluation

5. Model Capacity

CV Topics:

Image Classification

Pixel Classification

BBox Regression: Faster RCNN, RetinaNet, etc

Keypoint detection, registration

Saliency, Attention

Captioning

Show and tell

Image Captioning with Semantic Attention

Adversarial Losses (GAN)

Variational Auto Encoders (VAE)

Adversarial Samples

Empfohlene Literatur
Hartley R. and Zisserman A.: "Multiple View Geometry in Computer Vision", Cambridge University Press, 2004

ECTS-Informationen:
Credits: 5

Zusätzliche Informationen
Schlagwörter: computer vision, pinhole camera model, stereo vision
Erwartete Teilnehmerzahl: 10
www: http://www5.cs.fau.de/lectures/ss-20/seminar-computer-vision-semcv/

Verwendung in folgenden UnivIS-Modulen
Startsemester SS 2020:
Seminar Computer Vision (SemCV)

Institution: Lehrstuhl für Informatik 5 (Mustererkennung)
UnivIS ist ein Produkt der Config eG, Buckenhof