Multi‐scale feature learning and temporal probing strategy for one‐stage temporal action localization

计算机科学 人工智能 模式识别(心理学) 水准点(测量) 联营 特征(语言学) 卷积神经网络 运动(物理) 弹道 计算机视觉 深度学习 分割 特征学习 物理 哲学 天文 语言学 地理 大地测量学
作者
Leiyue Yao,Wei Yang,Wei Huang,Nan Jiang,Bingbing Zhou
出处
期刊:International Journal of Intelligent Systems [Wiley]
卷期号:37 (7): 4092-4112 被引量:4
标识
DOI:10.1002/int.22713
摘要

The aim of temporal action localization (TAL) is to determine the start and end frames of an action in a video. In recent years, TAL has attracted considerable attention because of its increasing applications in video understanding and retrieval. However, precisely estimating the duration of an action in the temporal dimension is still a challenging problem. In this paper, we propose an effective one-stage TAL method based on a self-defined motion data structure, called a dense joint motion matrix (DJMM), and a novel temporal detection strategy. Our method provides three main contributions. First, compared with mainstream motion images, DJMMs can preserve more pre-processed motion features and provides more precise detail representations. Furthermore, DJMMs perfectly solve the temporal information loss problem caused by motion trajectory overlaps within a certain time period. Second, a spatial pyramid pooling (SPP) layer, which is widely used in the object detection and tracking fields, is innovatively incorporated into the proposed method for multi-scale feature learning. Moreover, the SPP layer enables the backbone convolutional neural network (CNN) to receive DJMMs of any size in the temporal dimension. Third, a large-scale-first temporal detection strategy inspired by a well-developed Chinese text segmentation algorithm is proposed to address long-duration videos. Our method is evaluated on two benchmark data sets and one self-collected data set: Florence-3D, UTKinect-Action3D and HanYue-3D. The experimental results show that our method achieves competitive action recognition accuracy and high TAL precision, and its time efficiency and few-shot learning capabilities enable it to be utilized for real-time surveillance.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
万能图书馆应助小兰采纳,获得10
1秒前
科研通AI2S应助DARKNESS采纳,获得10
2秒前
3秒前
3秒前
YoYo发布了新的文献求助10
3秒前
小蘑菇应助热情芝麻采纳,获得10
5秒前
wuxunxun2015完成签到,获得积分10
6秒前
lzx发布了新的文献求助10
6秒前
sam给英俊雅琴的求助进行了留言
8秒前
Pony完成签到,获得积分10
8秒前
娜娜发布了新的文献求助10
9秒前
10秒前
FashionBoy应助cbf采纳,获得10
10秒前
10秒前
mengli完成签到 ,获得积分10
11秒前
健壮的百褶裙完成签到,获得积分10
11秒前
12秒前
lzx完成签到,获得积分10
13秒前
jason完成签到,获得积分10
14秒前
寸木完成签到 ,获得积分10
15秒前
jioujg发布了新的文献求助10
16秒前
ming发布了新的文献求助10
16秒前
qing完成签到,获得积分10
18秒前
光亮的世界完成签到,获得积分20
18秒前
wyy发布了新的文献求助10
19秒前
隐形曼青应助YoYo采纳,获得10
22秒前
jioujg完成签到,获得积分10
23秒前
2810527600完成签到,获得积分10
24秒前
31秒前
777y完成签到,获得积分10
33秒前
36秒前
Owen应助BlingBling的我呀采纳,获得10
37秒前
wyy完成签到,获得积分10
42秒前
含蓄的惜梦完成签到 ,获得积分10
43秒前
谭显芝完成签到,获得积分10
43秒前
46秒前
快乐小土豆完成签到,获得积分10
47秒前
Lucas应助若楼兰不死采纳,获得10
49秒前
sllytn关注了科研通微信公众号
50秒前
51秒前
高分求助中
The Oxford Handbook of Social Cognition (Second Edition, 2024) 1050
Kinetics of the Esterification Between 2-[(4-hydroxybutoxy)carbonyl] Benzoic Acid with 1,4-Butanediol: Tetrabutyl Orthotitanate as Catalyst 1000
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
Chen Hansheng: China’s Last Romantic Revolutionary 500
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3140405
求助须知:如何正确求助?哪些是违规求助? 2791283
关于积分的说明 7798359
捐赠科研通 2447650
什么是DOI,文献DOI怎么找? 1301996
科研通“疑难数据库(出版商)”最低求助积分说明 626359
版权声明 601194