Knowledge Commons of Institute of Automation,CAS
Video Object Detection with Locally-Weighted Deformable Neighbors | |
Jiang, Zhengkai1,2; Gao, Peng3; Guo, Chaoxu1,2; Zhang, Qian4; Xiang, Shiming1,2; Pan, Chunhong1,2 | |
2019-07 | |
会议名称 | Proceedings of the AAAI Conference on Artificial Intelligence |
会议日期 | 2019-1 |
会议地点 | 美国夏威夷 |
摘要 | Deep convolutional neural networks have achieved great success on various image recognition tasks. However, it is nontrivial to transfer the existing networks to video due to the fact that most of them are developed for static image. Frame-byframe processing is suboptimal because temporal information that is vital for video understanding is totally abandoned. Furthermore, frame-by-frame processing is slow and inefficient, which can hinder the practical usage. In this paper, we propose LWDN (Locally-Weighted Deformable Neighbors) for video object detection without utilizing time-consuming optical flow extraction networks. LWDN can latently align the high-level features between keyframes and keyframes or nonkeyframes. Inspired by (Zhu et al. 2017a) and (Hetang et al. 2017) who propose to aggregate features between keyframes and keyframes, we adopt brain-inspired memory mechanism to propagate and update the memory feature from keyframes to keyframes. We call this process Memory-Guided Propagation. With such a memory mechanism, the discriminative ability of features in keyframes and non-keyframes are both enhanced, which helps to improve the detection accuracy. Extensive experiments on VID dataset demonstrate that our method achieves superior performance in a speed and accuracy trade-off, ie, 76.3% on the challenging VID dataset while maintaining 20fps in speed on Titan X GPU. |
关键词 | Video Object Detection Feature Propagation and Aggregation |
收录类别 | EI |
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/173211/39265 |
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 | Jiang, Zhengkai |
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.The Chinese University of Hong Kong 4.Horizon Robotics |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Jiang, Zhengkai,Gao, Peng,Guo, Chaoxu,et al. Video Object Detection with Locally-Weighted Deformable Neighbors[C],2019. |
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 | ||
4871-Article Text-79(1134KB) | 会议论文 | 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