|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM343594315 |
| 003 |
DE-627 |
| 005 |
20250303141633.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2022.3189811
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1145.xml
|
| 035 |
|
|
|a (DE-627)NLM343594315
|
| 035 |
|
|
|a (NLM)35839182
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhuang, Peiqin
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Action Recognition With Motion Diversification and Dynamic Selection
|
| 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 Completed 26.07.2022
|
| 500 |
|
|
|a Date Revised 06.01.2025
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a Motion modeling is crucial in modern action recognition methods. As motion dynamics like moving tempos and action amplitude may vary a lot in different video clips, it poses great challenge on adaptively covering proper motion information. To address this issue, we introduce a Motion Diversification and Selection (MoDS) module to generate diversified spatio-temporal motion features and then select the suitable motion representation dynamically for categorizing the input video. To be specific, we first propose a spatio-temporal motion generation (StMG) module to construct a bank of diversified motion features with varying spatial neighborhood and time range. Then, a dynamic motion selection (DMS) module is leveraged to choose the most discriminative motion feature both spatially and temporally from the feature bank. As a result, our proposed method can make full use of the diversified spatio-temporal motion information, while maintaining computational efficiency at the inference stage. Extensive experiments on five widely-used benchmarks, demonstrate the effectiveness of the method and we achieve state-of-the-art performance on Something-Something V1 & V2 that are of large motion variation
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Guo, Yu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yu, Zhipeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhou, Luping
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Bai, Lei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liang, Ding
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Zhiyong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Yali
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ouyang, Wanli
|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 31(2022) vom: 01., Seite 4884-4896
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnas
|
| 773 |
1 |
8 |
|g volume:31
|g year:2022
|g day:01
|g pages:4884-4896
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2022.3189811
|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 31
|j 2022
|b 01
|h 4884-4896
|