期刊
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
卷 -, 期 -, 页码 3057-3065出版社
IEEE
DOI: 10.1109/ICCV.2017.330
关键词
-
资金
- Austrian Science Fund [FWF P27076]
- EPSRC Programme Grant Seebibyte [EP/M013774/1]
- EPSRC [EP/M013774/1] Funding Source: UKRI
Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cumbersome each year. In this paper we propose a ConvNet architecture that jointly performs detection and tracking, solving the task in a simple and effective way. Our contributions are threefold: (i) we set up a ConvNet architecture for simultaneous detection and tracking, using a multi-task objective for frame-based object detection and across-frame track regression; (ii) we introduce correlation features that represent object co-occurrences across time to aid the ConvNet during tracking; and (iii) we link the frame level detections based on our across-frame tracklets to produce high accuracy detections at the video level. Our ConvNet architecture for spatiotemporal object detection is evaluated on the large-scale ImageNet VID dataset where it achieves state-of-the-art results. Our approach provides better single model performance than the winning method of the last ImageNet challenge while being conceptually much simpler. Finally, we show that by increasing the temporal stride we can dramatically increase the tracker speed.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据