CASIA OpenIR  > 模式识别国家重点实验室  > 先进时空数据分析与学习
Progressive Sparse Local Attention for Video Object Detection
Chaoxu Guo1,2; Bin Fan1; Jie Gu1,2; Qian Zhang3; Shiming Xiang1,2; Veronique Prinet1; Chunhong Pan1
2019-10
Conference NameIEEE Proceedings of International Conference on Computer Vision
Issue2019
Pages3909-3918
Conference Date2019-10-27
Conference PlaceSeoul, Korea
Abstract

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.

MOST Discipline Catalogue工学
Indexed ByEI
Funding ProjectNational 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]
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/39103
Collection模式识别国家重点实验室_先进时空数据分析与学习
Corresponding AuthorBin Fan
Affiliation1.Institute of Automation, Chinese Academy of Science
2.School of Artifical Intelligence, University of Chinese Academy of Science
3.Horizon Robotics
Recommended Citation
GB/T 7714
Chaoxu Guo,Bin Fan,Jie Gu,et al. Progressive Sparse Local Attention for Video Object Detection[C],2019:3909-3918.
Files in This Item: Download All
File Name/Size DocType Version Access License
Guo_Progressive_Spar(1461KB)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
[Chaoxu Guo]'s Articles
[Bin Fan]'s Articles
[Jie Gu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chaoxu Guo]'s Articles
[Bin Fan]'s Articles
[Jie Gu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chaoxu Guo]'s Articles
[Bin Fan]'s Articles
[Jie Gu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Guo_Progressive_Sparse_Local_Attention_for_Video_Object_Detection_ICCV_2019_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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