ACCELERATED LOCAL FEATURE EXTRACTION IN A REUSE SCHEME FOR EFFICIENT ACTION RECOGNITION

被引：0

作者：

Chen, Jia-Lin ^{[1
]}

Lin, Zhi-Yi ^{[1
]}

Wan, Yi-Chen ^{[1
]}

Chen, Liang-Gee ^{[1
]}

机构：

[1] Natl Taiwan Univ, Grad Inst Elect Engn, DSP IC Design Lab, Taipei, Taiwan

来源：

2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2016年

关键词：

Feature reuse; local feature extraction; partial feature extraction; action recognition; region of interest;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, we propose an accelerated local feature extraction in a reuse scheme for action recognition. Most local features of the previous frame could be reused due to the high correlation between successive frames. Feature extraction is only needed to be applied partially in the current frame. The full-frame features of the current frame are combined by features extracted at different times. Experimental results show that the proposed reuse scheme can achieve comparable performance to full-frame feature extraction while computational effort is reduced significantly.

引用

页码：296 / 299

页数：4

共 50 条

[1] Local motion feature extraction and spatiotemporal attention mechanism for action recognition
Song, Xiaogang
Zhang, Dongdong
Liang, Li
He, Min
Hei, Xinhong
VISUAL COMPUTER, 2024, 40 (11) : 7747 - 7759
[2] Efficient Local Feature Encoding for Human Action Recognition with Approximate Sparse Coding
Wang, Yu
Kato, Jien
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2016, E99D (04): : 1212 - 1220
[3] MA-VLAD: a fine-grained local feature aggregation scheme for action recognition
Feng, Na
Tang, Ying
Song, Zikai
Yu, Junqing
Chen, Yi-Ping Phoebe
Yang, Wei
MULTIMEDIA SYSTEMS, 2024, 30 (03)
[4] EFFICIENT OBJECT FEATURE SELECTION FOR ACTION RECOGNITION
Zhang, Tianyi
Zhang, Yu
Cai, Jianfei
Kot, Alex C.
2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 2707 - 2711
[5] Automatic target recognition based on local feature extraction
Jia, Ping
Xu, Ning
Zhang, Ye
Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2013, 21 (07): : 1898 - 1905
[6] Palmprint Recognition Based on Local DCT Feature Extraction
Choge, H. Kipsang
Oyama, Tadahiro
Karungaru, Stephen
Tsuge, Satoru
Fukumi, Minoru
NEURAL INFORMATION PROCESSING, PT 1, PROCEEDINGS, 2009, 5863 : 639 - 648
[7] Robust Feature Extraction for Shift and Direction Invariant Action Recognition
Jeon, Younghan
Sandhan, Tushar
Choi, Jin Young
ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2015, PT II, 2015, 9315 : 321 - 329
[8] An Improved Action Recognition Network With Temporal Extraction and Feature Enhancement
Jiang, Jie
Zhang, Yi
IEEE ACCESS, 2022, 10 : 13926 - 13935
[9] Action Recognition Based on Feature Extraction From Time Series
Keceli, Ali Seydi
Can, Ahmet Burak
2014 22ND SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2014, : 485 - 488
[10] Lightweight skeleton-based action recognition model based on global-local feature extraction and fusion
Deng, Zhe
Wang, Yulin
Wei, Xing
Yang, Fan
Zhao, Chong
Lu, Yang
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2025, 16 (03) : 1477 - 1488

← 1 2 3 4 5 →