Multi-modality Fusion Network for Action Recognition

被引：0

作者：

Huang, Kai ^{[1
]}

Qin, Zheng ^{[1
]}

Xu, Kaiping ^{[1
]}

Ye, Shuxiong ^{[1
]}

Wang, Guolong ^{[1
]}

机构：

[1] Tsinghua Univ, Sch Software, Beijing, Peoples R China

来源：

ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2017, PT II | 2018年 / 10736卷

关键词：

Action recognition; 2D ConvNets; 3D ConvNets; Fusion; HISTOGRAMS;

D O I：

10.1007/978-3-319-77383-4_14

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Deep neural networks have outperformed many traditional methods for action recognition on video datasets, such as UCF101 and HMDB51. This paper aims to explore the performance of fusion of different convolutional networks with different dimensions. The main contribution of this work is multi-modality fusion network (MMFN), a novel framework for action recognition, which combines 2D ConvNets and 3D ConvNets. The accuracy of MMFN outperforms the state-of-the-art deep-learning-based methods on the datasets of UCF101 (94.6%) and HMDB51 (69.7%).

引用

页码：139 / 149

页数：11

共 50 条

[1] Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition
Zhu, Xiaoguang
Zhu, Ye
Wang, Haoyu
Wen, Honglin
Yan, Yan
Liu, Peilin
[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2022, 18 (03)
[2] Multi-Modality Adaptive Feature Fusion Graph Convolutional Network for Skeleton-Based Action Recognition
Zhang, Haiping
Zhang, Xinhao
Yu, Dongjin
Guan, Liming
Wang, Dongjing
Zhou, Fuxing
Zhang, Wanjun
[J]. SENSORS, 2023, 23 (12)
[3] Multi-modality learning for human action recognition
Ziliang Ren
Qieshi Zhang
Xiangyang Gao
Pengyi Hao
Jun Cheng
[J]. Multimedia Tools and Applications, 2021, 80 : 16185 - 16203
[4] Multi-modality learning for human action recognition
Ren, Ziliang
Zhang, Qieshi
Gao, Xiangyang
Hao, Pengyi
Cheng, Jun
[J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (11) : 16185 - 16203
[5] Human Action Recognition Via Multi-modality Information
Gao, Zan
Song, Jian-ming
Zhang, Hua
Liu, An-An
Xue, Yan-Bing
Xu, Guang-ping
[J]. JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY, 2014, 9 (02) : 739 - 748
[6] Focal Channel Knowledge Distillation for Multi-Modality Action Recognition
Gan, Lipeng
Cao, Runze
Li, Ning
Yang, Man
Li, Xiaochao
[J]. IEEE ACCESS, 2023, 11 : 78285 - 78298
[7] Multi-modality Empowered Network for Facial Action Unit Detection
Liu, Peng
Zhang, Zheng
Yang, Huiyuan
Yin, Lijun
[J]. 2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, : 2175 - 2184
[8] An Encoder Generative Adversarial Network for Multi-modality Image Recognition
Chen, Yu
Yang, Chunling
Zhu, Min
Yang, ShiYan
[J]. IECON 2018 - 44TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, 2018, : 2689 - 2694
[9] Space-Time Block Code Recognition Algorithm Based on Multi-Modality Features Fusion Network
Zhang, Yu-Yuan
Yan, Wen-Jun
Zhang, Li-Min
[J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2023, 51 (02): : 489 - 498
[10] AFDFusion: An adaptive frequency decoupling fusion network for multi-modality image
[J]. Pu, Yuanyuan (yuanyuanpu@ynu.edu.cn), 2025, 263

← 1 2 3 4 5 →