Knowledge Commons of Institute of Automation,CAS
Progressive Sparse Local Attention for Video Object Detection | |
Guo, Chaoxu1,2![]() ![]() ![]() ![]() ![]() | |
2019-10 | |
会议名称 | IEEE Proceedings of International Conference on Computer Vision |
期号 | 2019 |
页码 | 3909-3918 |
会议日期 | 2019-10-27 |
会议地点 | Seoul, Korea |
摘要 | Transferring image-based object detectors to the domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between accuracy and efficiency. However, introducing an extra model to estimate optical flow can significantly increase the overall model size. The gap between optical flow and high-level features can also hinder it from establishing spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense Feature Transforming (DenseFT) are proposed to model temporal appearance and enrich feature representation respectively in a novel video object detection framework. Experiments on ImageNet VID show that our method achieves the best accuracy compared to existing methods with smaller model size and acceptable runtime speed. |
学科门类 | 工学 |
收录类别 | EI |
资助项目 | National Science Foundation of China[61573352,61876180] ; Young Elite Scientists Sponsorship Program by CAST[2018QNRC001] ; Beijing Natural Science Foundation[L172053] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[91646207] ; Beijing Natural Science Foundation[L172053] ; Young Elite Scientists Sponsorship Program by CAST[2018QNRC001] ; National Science Foundation of China[61573352,61876180] |
语种 | 英语 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39103 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Fan, Bin |
作者单位 | 1.Institute of Automation, Chinese Academy of Science 2.School of Artifical Intelligence, University of Chinese Academy of Science 3.Horizon Robotics |
推荐引用方式 GB/T 7714 | Guo, Chaoxu,Fan, Bin,Gu, Jie,et al. Progressive Sparse Local Attention for Video Object Detection[C],2019:3909-3918. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Guo_Progressive_Spar(1461KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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