Human Motion Segmentation via Velocity-Sensitive Dual-Side Auto-Encoder

Human Motion Segmentation via Velocity-Sensitive Dual-Side Auto-Encoder

Human motion segmentation (HMS) aims to segment a long human action video into a bunch of short and meaningful action clips. Existing supervised learning approaches need a large amount of training data which may be costly in real-world scenario, while most unsupervised clustering methods cannot full...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - PP(2022) vom: 22. Dez.
1. Verfasser: Bai, Yue (VerfasserIn)
Weitere Verfasser: Wang, Lichen, Liu, Yunyu, Yin, Yu, Di, Hang, Fu, Yun
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM355201372
003 DE-627
005 20231226063838.0
007 cr uuu---uuuuu
008 231226s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2022.3217720  |2 doi 
028 5 2 |a pubmed24n1183.xml 
035 |a (DE-627)NLM355201372 
035 |a (NLM)37015391 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Bai, Yue  |e verfasserin  |4 aut 
245 1 0 |a Human Motion Segmentation via Velocity-Sensitive Dual-Side Auto-Encoder 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 04.04.2023 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Human motion segmentation (HMS) aims to segment a long human action video into a bunch of short and meaningful action clips. Existing supervised learning approaches need a large amount of training data which may be costly in real-world scenario, while most unsupervised clustering methods cannot fully explore the temporal correlations among human motions and hard to achieve promising performances. In our paper, we design a novel unsupervised framework, called Velocity-Sensitive Dual-Side Auto-Encoder (VSDA), for HMS task. Specifically, a multi-neighbor auto-encoder (MNA) is proposed to extract informative temporal features, which fully explores the local temporal patterns of human motions. In addition, a long-short distance encoding (LSE) strategy is designed. It constrains the encoded representations of close (short-distance) frames becoming similar while the representations of far-away (long-distance) frames becoming distinctive. Similarly, this strategy is also deployed on the decoded outputs as the long-short distance decoding (LSD) module. The LSE/LSD guides the learning process explicitly and implicitly to achieve the dual-side structure. Moreover, we consider the energy variations during the human motion to propose the velocity-sensitive (VS) guidance mechanism for further model improvement. VSDA leverages the temporal characteristics of human motion and derives promising HMS performance. Comprehensive experiments on six real-world human motion datasets illustrate the effectiveness of our proposed model 
650 4 |a Journal Article 
700 1 |a Wang, Lichen  |e verfasserin  |4 aut 
700 1 |a Liu, Yunyu  |e verfasserin  |4 aut 
700 1 |a Yin, Yu  |e verfasserin  |4 aut 
700 1 |a Di, Hang  |e verfasserin  |4 aut 
700 1 |a Fu, Yun  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g PP(2022) vom: 22. Dez.  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:PP  |g year:2022  |g day:22  |g month:12 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2022.3217720  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2022  |b 22  |c 12