Knowledge Commons of Institute of Automation,CAS
Toward Accurate Pixelwise Object Tracking via Attention Retrieval | |
Zhang, Zhipeng1,2; Liu, Yufan1,2; Li, Bin1,2; Hu, Weiming1,2,3; Peng, Houwen4 | |
发表期刊 | IEEE Transactions on Image Processing |
2021 | |
卷号 | 30页码:8553-8566 |
摘要 | Pixelwise single object tracking is challening due to the competition of running speeds and segmentation accuracy. Current state-of-the-art real-time approaches seamlessly connect tracking and segmentation by sharing computation of the backbone network, e.g., SiamMask and D3S fork a light branch from the tracking model to predict segmentation mask. Although efficient, directly reusing features from tracking networks may harm the segmentation accuracy, since background clutter in the backbone feature tends to introduce false-positives in segmentation. To mitigate this problem, we propose a unified tracking-retrieval-segmentation framework consisting of an attention retrieval network (ARN) and an iterative feedback network (IFN). Instead of segmenting the target inside the bounding box, the proposed framework performs soft spatial constraints on backbone features to obtain an accurate global segmentation map. Concretely, in ARN, a look-up-table (LUT) is first built by sufficiently using the information of the first frame. By retrieving it, a target-aware attention map is generated to suppress the negative influence of background clutter. To ulteriorly refine the contour of the segmentation, IFN iteratively enhances the features at different resolutions by taking the predicted mask as feedback guidance. Our framework sets a new state of the art on the recent pixelwise tracking benchmark VOT2020 and runs at 40 fps. Notably, the proposed model surpasses SiamMask by 11.7/4.2/5.5 points on VOT2020, DAVIS2016, and DAVIS2017, respectively. Code is available at https://github.com/JudasDie/SOTS. |
收录类别 | SCI |
语种 | 英语 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48525 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
通讯作者 | Hu, Weiming |
作者单位 | 1.National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology 4.Microsoft Research Asia |
推荐引用方式 GB/T 7714 | Zhang, Zhipeng,Liu, Yufan,Li, Bin,et al. Toward Accurate Pixelwise Object Tracking via Attention Retrieval[J]. IEEE Transactions on Image Processing,2021,30:8553-8566. |
APA | Zhang, Zhipeng,Liu, Yufan,Li, Bin,Hu, Weiming,&Peng, Houwen.(2021).Toward Accurate Pixelwise Object Tracking via Attention Retrieval.IEEE Transactions on Image Processing,30,8553-8566. |
MLA | Zhang, Zhipeng,et al."Toward Accurate Pixelwise Object Tracking via Attention Retrieval".IEEE Transactions on Image Processing 30(2021):8553-8566. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Toward Accurate Pixe(3636KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论