Show simple item record

dc.contributor.authorWang, Y
dc.contributor.authorHu, Y
dc.contributor.authorLiew, Wee-Chung
dc.contributor.authorWang, J
dc.date.accessioned2019-06-10T01:34:31Z
dc.date.available2019-06-10T01:34:31Z
dc.date.issued2019
dc.identifier.isbn9781538654576
dc.identifier.issn2159-3442
dc.identifier.doi10.1109/TENCON.2018.8650146
dc.identifier.urihttp://hdl.handle.net/10072/385235
dc.description.abstractThis paper proposes a novel approach of weakly supervised video object segmentation, which only needs one pixel to guide the segmentation. We use two deep neural networks to get the instance-level semantic segmentation masks and optical flow maps of each frame. An object probability map to the first frame in video is generated by combining the semantic masks, the optical flow maps and the guiding pixel. The object probability map propagates forward and backward and becomes more accurate to each frame. Finally, an energy minimization problem on a function that consists of unary term of object probability and pairwise terms of label smoothness potentials is solved to get the pixel-wise object segmentation mask of each frame. We evaluate our method on a benchmark dataset, and the experimental results show that the proposed approach achieves impressive performance in comparison with state-of-the-art methods.
dc.description.peerreviewedYes
dc.publisherIEEE
dc.relation.ispartofconferencenameTENCON 2018 - 2018 IEEE Region 10 Conference
dc.relation.ispartofconferencetitleIEEE Region 10 Annual International Conference, Proceedings/TENCON
dc.relation.ispartofdatefrom2018-10-28
dc.relation.ispartofdateto2018-10-31
dc.relation.ispartoflocationJeju, Korea (South)
dc.relation.ispartofpagefrom315
dc.relation.ispartofpagefrom6 pages
dc.relation.ispartofpageto320
dc.relation.ispartofpageto6 pages
dc.relation.ispartofvolume2018-October
dc.subject.fieldofresearchArtificial Intelligence and Image Processing
dc.subject.fieldofresearchcode0801
dc.titleWeakly Supervised Video Object Segmentation
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
gro.hasfulltextNo Full Text
gro.griffith.authorLiew, Alan Wee-Chung
gro.griffith.authorWang, John


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record