其他
CVPR2020 | 旷视研究院提出SAT:优化解决半监督视频物体分割问题
IEEE国际计算机视觉与模式识别会议 CVPR 2020 (IEEE Conference on Computer Vision and Pattern Recognition) 将于 6 月 14-19 日在美国西雅图举行。近日,大会官方论文结果公布,旷视研究院 16 篇论文被收录,研究领域涵盖物体检测与行人再识别(尤其是遮挡场景),人脸识别,文字检测与识别,实时视频感知与推理,小样本学习,迁移学习,3D感知,GAN与图像生成,计算机图形学,语义分割,细粒度图像等众多领域,取得多项领先的技术研究成果,这与即将开源的旷视AI平台Brain++密不可分。
论文名称:State-Aware Tracker for Real-Time Video Object Segmentation 论文链接:https://arxiv.org/abs/2003.00482 论文代码:https://github.com/MegviiDetection/video_analyst
导语 简介 方法 架构 估计 反馈 剪裁策略回路 全局建模回路 实验 结论 参考文献 往期解读
架构
估计
反馈
剪裁策略回路
全局建模回路
或添加 farman7230 入群
参考文献
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceed- ings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016 Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural net- works. In Advances in neural information processing sys- tems, pages 1097–1105, 2012. Yinda Xu, Zeyu Wang, Zuoxin Li, Yuan Ye, and Gang Yu. SiamFC++: Towards Robust and Accurate Visual Track- ing with Target Estimation Guidelines. arXiv e-prints, page arXiv:1911.06188, 2019. Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Ar- bela ́ez, Alex Sorkine-Hornung, and Luc Van Gool. The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675, 2017. Federico Perazzi, Jordi Pont-Tuset, Brian McWilliams, Luc Van Gool, Markus Gross, and Alexander Sorkine-Hornung. A benchmark dataset and evaluation methodology for video object segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 724– 732, 2016. Ning Xu, Linjie Yang, Yuchen Fan, Jianchao Yang, Dingcheng Yue, Yuchen Liang, Brian Price, Scott Cohen, and Thomas Huang. Youtube-vos: Sequence-to-sequence video object segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), pages 585–601, 2018.