CASIA OpenIR  > 模式识别国家重点实验室  > 先进时空数据分析与学习
Video Object Detection with Locally-Weighted Deformable Neighbors
Jiang ZK(蒋正锴)1,2; Gao P(高鹏)3; Guo CX(郭超旭)1,2; Zhang Q(张骞)4; Xiang SM(向世明)1,2; Pan CH(潘春洪)1,2
2019-07
Conference NameProceedings of the AAAI Conference on Artificial Intelligence
Conference Date2019-1
Conference Place美国夏威夷
Abstract

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.

KeywordVideo Object Detection Feature Propagation and Aggregation
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/39265
Collection模式识别国家重点实验室_先进时空数据分析与学习
Corresponding AuthorJiang ZK(蒋正锴)
Affiliation1.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
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Jiang ZK,Gao P,Guo CX,et al. Video Object Detection with Locally-Weighted Deformable Neighbors[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
4871-Article Text-79(1134KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jiang ZK(蒋正锴)]'s Articles
[Gao P(高鹏)]'s Articles
[Guo CX(郭超旭)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jiang ZK(蒋正锴)]'s Articles
[Gao P(高鹏)]'s Articles
[Guo CX(郭超旭)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jiang ZK(蒋正锴)]'s Articles
[Gao P(高鹏)]'s Articles
[Guo CX(郭超旭)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 4871-Article Text-7937-1-10-20190709.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.