Trajectory-Set Feature for Action Recognition

被引：1

作者：

Matsui, Kenji ^{[1
]}

Tamaki, Toru ^{[1
]}

Raytchev, Bisser ^{[1
]}

Kaneda, Kazufumi ^{[1
]}

机构：

[1] Hiroshima Univ, Higashihiroshima 7398527, Japan

来源：

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2017年 / E100D卷 / 08期

关键词：

action recognition; trajectory; improved Dense Trajectory; HISTOGRAMS;

D O I：

10.1587/transinf.2017EDL8049

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We propose a feature for action recognition called Trajectory-Set (TS), on top of the improved Dense Trajectory (iDT). The TS feature encodes only trajectories around densely sampled interest points, without any appearance features. Experimental results on the UCF50 action dataset demonstrates that TS is comparable to state-of-the-arts, and outperforms iDT; the accuracy of 95.0%, compared to 91.7% by iDT.

引用

页码：1922 / 1924

页数：3

共 50 条

[1] TRAJECTORY FEATURE FUSION FOR HUMAN ACTION RECOGNITION
Megrhi, Sameh
Beghdadi, Azeddine
Souidene, Wided
2014 5TH EUROPEAN WORKSHOP ON VISUAL INFORMATION PROCESSING (EUVIP 2014), 2014,
[2] Learning Discriminative Feature Representation for Open Set Action Recognition
Zhang, Hongjie
Liu, Yi
Wang, Yali
Wang, Limin
Qiao, Yu
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 7696 - 7705
[3] Action Recognition by Jointly Using Video Proposal and Trajectory
Qi, Lei
Lu, Xiaoqiang
Li, Xuelong
PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON VISION, IMAGE AND SIGNAL PROCESSING (ICVISP 2018), 2018,
[4] A novel feature for action recognition
Wen, Hao
Lu, Zhe-Ming
Cui, Jia-Lin
Li, Hao-Lai
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (14) : 41441 - 41456
[5] A novel feature for action recognition
Hao Wen
Zhe-Ming Lu
Jia-Lin Cui
Hao-Lai Li
Multimedia Tools and Applications, 2024, 83 : 41441 - 41456
[6] Human Action Recognition: a feature point trajectory and space-time interest point based approach
Chen, Xinyi
Yi, Yang
2018 IEEE SMARTWORLD, UBIQUITOUS INTELLIGENCE & COMPUTING, ADVANCED & TRUSTED COMPUTING, SCALABLE COMPUTING & COMMUNICATIONS, CLOUD & BIG DATA COMPUTING, INTERNET OF PEOPLE AND SMART CITY INNOVATION (SMARTWORLD/SCALCOM/UIC/ATC/CBDCOM/IOP/SCI), 2018, : 1160 - 1164
[7] FEATURE SAMPLING STRATEGIES FOR ACTION RECOGNITION
Zhou, Youjie
Yu, Hongkai
Wang, Song
2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3968 - 3972
[8] Motion Boundary Trajectory for Human Action Recognition
Lo, Sio-Long
Tsoi, Ah-Chung
COMPUTER VISION - ACCV 2014 WORKSHOPS, PT I, 2015, 9008 : 85 - 98
[9] Action Recognition Based on the Feature Trajectories
Du, Ji-Xiang
Yang, Kai
Zhai, Chuan-Min
INTELLIGENT COMPUTING THEORIES AND APPLICATIONS, ICIC 2012, 2012, 7390 : 250 - 257
[10] A COMPACT PAIRWISE TRAJECTORY REPRESENTATION FOR ACTION RECOGNITION
Huang, Qingya
Sun, Shan
Wang, Feng
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 1767 - 1771

← 1 2 3 4 5 →