Occluded Video Instance Segmentation: A Benchmark

Publikation: Working paper › Preprint › Forskning

Standard

Occluded Video Instance Segmentation : A Benchmark. / Qi, Jiyang; Gao, Yan; Hu, Yao; Wang, Xinggang; Liu, Xiaoyu; Bai, Xiang; Belongie, Serge; Yuille, Alan; Torr, Philip H. S.; Bai, Song.

2021.

Publikation: Working paper › Preprint › Forskning

Harvard

Qi, J, Gao, Y, Hu, Y, Wang, X, Liu, X, Bai, X, Belongie, S, Yuille, A, Torr, PHS & Bai, S 2021 'Occluded Video Instance Segmentation: A Benchmark'.

APA

Qi, J., Gao, Y., Hu, Y., Wang, X., Liu, X., Bai, X., Belongie, S., Yuille, A., Torr, P. H. S., & Bai, S. (2021). Occluded Video Instance Segmentation: A Benchmark.

Vancouver

Qi J, Gao Y, Hu Y, Wang X, Liu X, Bai X o.a. Occluded Video Instance Segmentation: A Benchmark. 2021 feb. 2.

Author

Qi, Jiyang ; Gao, Yan ; Hu, Yao ; Wang, Xinggang ; Liu, Xiaoyu ; Bai, Xiang ; Belongie, Serge ; Yuille, Alan ; Torr, Philip H. S. ; Bai, Song. / Occluded Video Instance Segmentation : A Benchmark. 2021.

Bibtex

@techreport{cddae69fcc2e4562b958f6ca741ff14d,
title = "Occluded Video Instance Segmentation: A Benchmark",
abstract = " Can our video understanding systems perceive objects when a heavy occlusion exists in a scene? To answer this question, we collect a large-scale dataset called OVIS for occluded video instance segmentation, that is, to simultaneously detect, segment, and track instances in occluded scenes. OVIS consists of 296k high-quality instance masks from 25 semantic categories, where object occlusions usually occur. While our human vision systems can understand those occluded instances by contextual reasoning and association, our experiments suggest that current video understanding systems cannot. On the OVIS dataset, the highest AP achieved by state-of-the-art algorithms is only 16.3, which reveals that we are still at a nascent stage for understanding objects, instances, and videos in a real-world scenario. We also present a simple plug-and-play module that performs temporal feature calibration to complement missing object cues caused by occlusion. Built upon MaskTrack R-CNN and SipMask, we obtain a remarkable AP improvement on the OVIS dataset. The OVIS dataset and project code are available at http://songbai.site/ovis . ",
keywords = "cs.CV, 68T07, 68T45",
author = "Jiyang Qi and Yan Gao and Yao Hu and Xinggang Wang and Xiaoyu Liu and Xiang Bai and Serge Belongie and Alan Yuille and Torr, {Philip H. S.} and Song Bai",
note = "project page at https://songbai.site/ovis",
year = "2021",
month = feb,
day = "2",
language = "Udefineret/Ukendt",
type = "WorkingPaper",

}

RIS

TY - UNPB

T1 - Occluded Video Instance Segmentation

T2 - A Benchmark

AU - Qi, Jiyang

AU - Gao, Yan

AU - Hu, Yao

AU - Wang, Xinggang

AU - Liu, Xiaoyu

AU - Bai, Xiang

AU - Belongie, Serge

AU - Yuille, Alan

AU - Torr, Philip H. S.

AU - Bai, Song

N1 - project page at https://songbai.site/ovis

PY - 2021/2/2

Y1 - 2021/2/2

N2 - Can our video understanding systems perceive objects when a heavy occlusion exists in a scene? To answer this question, we collect a large-scale dataset called OVIS for occluded video instance segmentation, that is, to simultaneously detect, segment, and track instances in occluded scenes. OVIS consists of 296k high-quality instance masks from 25 semantic categories, where object occlusions usually occur. While our human vision systems can understand those occluded instances by contextual reasoning and association, our experiments suggest that current video understanding systems cannot. On the OVIS dataset, the highest AP achieved by state-of-the-art algorithms is only 16.3, which reveals that we are still at a nascent stage for understanding objects, instances, and videos in a real-world scenario. We also present a simple plug-and-play module that performs temporal feature calibration to complement missing object cues caused by occlusion. Built upon MaskTrack R-CNN and SipMask, we obtain a remarkable AP improvement on the OVIS dataset. The OVIS dataset and project code are available at http://songbai.site/ovis .

AB - Can our video understanding systems perceive objects when a heavy occlusion exists in a scene? To answer this question, we collect a large-scale dataset called OVIS for occluded video instance segmentation, that is, to simultaneously detect, segment, and track instances in occluded scenes. OVIS consists of 296k high-quality instance masks from 25 semantic categories, where object occlusions usually occur. While our human vision systems can understand those occluded instances by contextual reasoning and association, our experiments suggest that current video understanding systems cannot. On the OVIS dataset, the highest AP achieved by state-of-the-art algorithms is only 16.3, which reveals that we are still at a nascent stage for understanding objects, instances, and videos in a real-world scenario. We also present a simple plug-and-play module that performs temporal feature calibration to complement missing object cues caused by occlusion. Built upon MaskTrack R-CNN and SipMask, we obtain a remarkable AP improvement on the OVIS dataset. The OVIS dataset and project code are available at http://songbai.site/ovis .

KW - cs.CV

KW - 68T07, 68T45

M3 - Preprint

BT - Occluded Video Instance Segmentation

ER -

ID: 303683496