1. Robustni pristopi k vizualnemu učenju in razpoznavanju na osnovi podprostorovDanijel Skočaj, 2003, doktorska disertacija Ključne besede: visual learning, robust learning, robust recognition, weighted learning, missing pixels, incremental learning, subspace methods, principal component analysis, appearance-based modeling, view centred approach, computer vision, dissertations Celotno besedilo (datoteka, 2,64 MB) |
2. Real time panoramic depth imaging using standard camerasPeter Peer, 2003, doktorska disertacija Ključne besede: computer vision, stereo vision, reconstruction, depth image, multiperspective panoramic image, mosaicing, motion parallax effect, standard camera, real time, depth sensor, dissertations Celotno besedilo (datoteka, 2,83 MB) |
3. Recognizing visual object categories with subspace methods and a learned hierarchical shape vocabularySanja Fidler, 2010, doktorska disertacija Ključne besede: computer vision, subspace methods, robust classification, visual object class recognition and detection, visual learning, hierarchical representation, part-based representations, compositional hierarchies Celotno besedilo (datoteka, 9,71 MB) |
4. Computer-vision based polyp detection in underwater imagesKristijan Shirgoski, 2015, diplomsko delo Ključne besede: object detection, computer vision, machine learning, ACF, CNN, SVM, regression, non-maximum suppression Celotno besedilo (datoteka, 10,74 MB) |
5. A hierarchical adaptive model for robust short-term visual trackingLuka Čehovin Zajc, 2015, doktorska disertacija Ključne besede: computer vision, visual tracking, visual model, short-term tracking, articulated object, non-rigid objects, performance measures, performance evaluation, ranking Celotno besedilo (datoteka, 13,02 MB) |
|
|
|
9. Musculoskeletal images classification for detection of fractures using transfer learningIbrahem Kandel, Mauro Castelli, Aleš Popovič, 2020, izvirni znanstveni članek Ključne besede: transfer learning, computer vision, convolutional neural networks, image classification, musculoskeletal images, deep learning, medical images, neuroscience Celotno besedilo (datoteka, 550,23 KB) Gradivo ima več datotek! Več... |
10. Quantitative contact-less estimation of energy expenditure from video and 3D imageryGregor Koporec, Goran Vučković, Radoje Milić, Janez Perš, 2018, izvirni znanstveni članek Ključne besede: physical activity, energy expenditure, computer vision, optical flow, scene flow, heart rate, support vector machine, RBF kernel, KCF tracker, Microsoft Kinect, time-of-flight sensor, squash Celotno besedilo (datoteka, 7,87 MB) Gradivo ima več datotek! Več... |