Occluded Video Instance Segmentation with Set Prediction Approach

被引：0

作者：

Bae, Heechul ^{[1
]}

Song, Soonyong ^{[1
]}

Park, Junhee ^{[1
]}

机构：

[1] Elect & Telecommun Res Inst ETRI, Ind & IoT Intelligence Res Dept, Daejeon, South Korea

来源：

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021) | 2021年

关键词：

D O I：

10.1109/ICCVW54120.2021.00429

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Occluded Video Instance Segmentation (OVIS) is a multi-task problem performing detection, segmentation, and tracking simultaneously under severe occlusions. We propose an extended model for the OVIS task based on the real-time one-stage instance segmentation method. The proposed model was applied to the OVIS dataset hold by the ICCV 2021 - Occluded Video Instance Segmentation Workshop 2021. We also show that the occlusions can be handled efficiently through one-stage approaches.

引用

页码：3843 / 3846

页数：4

共 50 条

[41] Video Instance Segmentation with a Propose-Reduce Paradigm
Lin, Huaijia
Wu, Ruizheng
Liu, Shu
Lu, Jiangbo
Jia, Jiaya
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 1719 - 1728
[42] LIP: Learning Instance Propagation for Video Object Segmentation
Lyu, Ye
Vosselman, George
Xia, Gui-Song
Yang, Michael Ying
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 2739 - 2748
[43] Crossover Learning for Fast Online Video Instance Segmentation
Yang, Shusheng
Fang, Yuxin
Wang, Xinggang
Li, Yu
Fang, Chen
Shan, Ying
Feng, Bin
Liu, Wenyu
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 8023 - 8032
[44] CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation
Fu, Yang
Yang, Linjie
Liu, Ding
Huang, Thomas S.
Shi, Humphrey
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 1361 - 1369
[45] Joint Future Semantic and Instance Segmentation Prediction
Couprie, Camille
Luc, Pauline
Verbeek, Jakob
COMPUTER VISION - ECCV 2018 WORKSHOPS, PT III, 2019, 11131 : 154 - 168
[46] Towards Open-Vocabulary Video Instance Segmentation
Wang, Haochen
Yan, Cilin
Wang, Shuai
Jiang, Xiaolong
Tang, Xu
Hu, Yao
Xie, Weidi
Gavves, Efstratios
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 4034 - 4043
[47] Instance Motion Tendency Learning for Video Panoptic Segmentation
Wang, Le
Liu, Hongzhen
Zhou, Sanping
Tang, Wei
Hua, Gang
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 764 - 778
[48] End-to-End Video Instance Segmentation with Transformers
Wang, Yuqing
Xu, Zhaoliang
Wang, Xinlong
Shen, Chunhua
Cheng, Baoshan
Shen, Hao
Xia, Huaxia
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 8737 - 8746
[49] Tag-Based Attention Guided Bottom-Up Approach for Video Instance Segmentation
Kini, Jyoti
Shah, Mubarak
2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 3536 - 3542
[50] Semantic Instance Meets Salient Object: Study on Video Semantic Salient Instance Segmentation
Trung-Nghia Le
Sugimoto, Akihiro
2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, : 1779 - 1788

← 1 2 3 4 5 →