Zero-shot Learning for Visual Recognition Problems
| dc.contributor.author | Naha, Shujon | |
| dc.contributor.examiningcommittee | Bruce, Neil (Computer Science) Hossain, Ekram (Electrical and Computer Engineering) | en_US |
| dc.contributor.supervisor | Wang, Yang (Computer Science) | en_US |
| dc.date.accessioned | 2016-09-19T16:00:15Z | |
| dc.date.available | 2016-09-19T16:00:15Z | |
| dc.date.issued | 2015 | en_US |
| dc.date.issued | 2016 | en_US |
| dc.degree.discipline | Computer Science | en_US |
| dc.degree.level | Master of Science (M.Sc.) | en_US |
| dc.description.abstract | In this thesis we discuss different aspects of zero-shot learning and propose solutions for three challenging visual recognition problems: 1) unknown object recognition from images 2) novel action recognition from videos and 3) unseen object segmentation. In all of these three problems, we have two different sets of classes, the “known classes”, which are used in the training phase and the “unknown classes” for which there is no training instance. Our proposed approach exploits the available semantic relationships between known and unknown object classes and use them to transfer the appearance models from known object classes to unknown object classes to recognize unknown objects. We also propose an approach to recognize novel actions from videos by learning a joint model that links videos and text. Finally, we present a ranking based approach for zero-shot object segmentation. We represent each unknown object class as a semantic ranking of all the known classes and use this semantic relationship to extend the segmentation model of known classes to segment unknown class objects. | en_US |
| dc.description.note | October 2016 | en_US |
| dc.identifier.citation | Shujon Naha and Yang Wang. Zero-Shot Object Recognition Using Semantic Label Vectors. The 12th Conference on Computer and Robot Vision (CRV), 2015. | en_US |
| dc.identifier.citation | Shujon Naha and Yang Wang. Beyond Verbs: Understanding Actions in Videos with Text. International Conference on Pattern Recognition (ICPR), 2016. | en_US |
| dc.identifier.citation | Shujon Naha and Yang Wang. Object Figure-Ground Segmentation Using Zero-Shot Learning. International Conference on Pattern Recognition (ICPR), 2016. | en_US |
| dc.identifier.uri | http://hdl.handle.net/1993/31806 | |
| dc.language.iso | eng | en_US |
| dc.publisher | IEEE | en_US |
| dc.publisher | Elsevier | en_US |
| dc.rights | open access | en_US |
| dc.subject | Zero-shot Learning | en_US |
| dc.subject | Computer Vision | en_US |
| dc.subject | Object Recognition | en_US |
| dc.subject | Action Recognition | en_US |
| dc.subject | Object Segmentation | en_US |
| dc.title | Zero-shot Learning for Visual Recognition Problems | en_US |
| dc.type | master thesis | en_US |