arrow
返回

Global Memory and Local Continuity for Video Object Detection

delete2023-01-01
delete11
PRE
AI
L
Liang Han
Z
Zhaozheng Yin *
DOI:10.1109/TMM.2022.3164253delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
To deal with the challenges in video object detection (VOD), such as occlusion and motion blur, many state-of-the-art video object detectors adopt a feature aggregation module to encode the long-range contextual information to support the current frame. The main drawbacks of these detectors are three-folds: first, the frame-wise detection slows down the detection speed; second, the frame-wise detection usually ignores the local continuity of the objects in a video, resulting in temporal inconsistent detection; third, the feature aggregation module usually encodes temporal features either from a local video clip or a single video, without exploiting the features in other videos. In this work, we develop an online VOD algorithm, aiming at a balanced high-speed and high-accuracy, by exploiting the global memory and local continuity. In the algorithm, an effective and efficient global memory bank (GMB) is designed to deposit and update object class features, which enables us to exploit the support features in other videos to enhance object features in the current video frames. Besides, to further speed up the detection, we design an object tracker to perform object detection for non-key frames based on the detection results of the key frame by leveraging the local continuity property of the video. Considering the trade-off between detection accuracy and speed, the proposed framework achieves superior performance on the ImageNet VID dataset. Source codes will be released to the public via our GitHub website.
Keyword:
Feature extraction
Object detection
Detectors
Proposals
Target tracking
Signal processing algorithms
Costs
Video object detection
global memory bank
feature aggregation
local continuity
object tracker

期刊

IEEE Transactions on Multimedia 封面图
IEEE Transactions on Multimedia
IF:
9.7
论文数:
4.5K
被引数:
2.4W

机构

S
state university of new york (suny) system
学者数:
6.5W
论文数: 5.8W
被引数: 65
引用论文

引用论文

err分享
err收藏
E‐business e‐commerce evolution: perspective and strategy
err2001-07-01
err0
PREAI
errFaramarz Damanpour; Jamshid Ali Damanpour
err分享
err收藏
err分享
err收藏
Discovery of compounds that protect tyrosine hydroxylase activity through different mechanisms
err2015-09-01
err0
PREAI
errMagnus Hole; Jarl Underhaug; Hector Diez; Ming Ying; Åsmund Kjendseth Røhr; Ana Jorge-Finnigan; Noèlia Fernàndez-Castillo; Angels García-Cazorla; K. Kristoffer Andersson; Knut Teigen; Aurora Martinez
err分享
err收藏
Global networking with ISDN
err1994-06-01
err0
PREAI
errN. Dagdeviren; J.A. Newell; L.A. Spindel; M.I. Stefanick
err分享
err收藏
学者 查看更多内容