Show simple item record

dc.contributor.supervisor Wang, Yang (Computer Science) en_US
dc.contributor.author Chanda, Omit
dc.date.accessioned 2018-07-16T14:35:11Z
dc.date.available 2018-07-16T14:35:11Z
dc.date.issued 2018-06 en_US
dc.date.submitted 2018-07-15T18:56:32Z en
dc.identifier.citation O. Chanda, E. Teh, M. Rochan and Y. Wang. Adapting Object Detectors from Images to Weakly Labeled Videos. British Machine Vision Conference (BMVC), London, 2017. en_US
dc.identifier.uri http://hdl.handle.net/1993/33176
dc.description.abstract In this thesis, we consider the problem of localizing and segmenting objects in weakly labeled videos. Specifically, we consider two related problems which include adapting object detectors and object segmentation in weakly labeled videos. In the context of object detectors, a video is weakly labeled if we know the presence/absence of an object in a video (or each frame), but we do not know the exact spatial location. In the context of segmenting objects, our concern is to generalize segmentation network based on only a single annotated frame so that it works better for the entire video stream. In addition to weakly labeled videos, we assume access to a set of fully labeled images for the problem of localizing objects. For segmenting objects, we have some other labeled information but those labeled classes are not included in the test set of our data. We incorporate domain adaptation in our framework and adapt the information from the labeled images (source domain) to the weakly labeled videos (target domain). We demonstrate the effectiveness of our proposed approach based on the experimental results on standard benchmark datasets. Our work can also be used for collecting large-scale video datasets for object detection. en_US
dc.subject Computer vision en_US
dc.title Localizing and segmenting objects from weakly labeled videos en_US
dc.degree.discipline Computer Science en_US
dc.contributor.examiningcommittee Mohammed, Noman (Computer Science) Ferens, Ken (Electrical and Computer Engineering) en_US
dc.degree.level Master of Science (M.Sc.) en_US
dc.description.note October 2018 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

View Statistics