|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM26416623X |
| 003 |
DE-627 |
| 005 |
20250220152638.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231224s2016 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2016.2605305
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n0880.xml
|
| 035 |
|
|
|a (DE-627)NLM26416623X
|
| 035 |
|
|
|a (NLM)27608461
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Yu Zhang
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Action Recognition in Still Images With Minimum Annotation Efforts
|
| 264 |
|
1 |
|c 2016
|
| 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 20.11.2019
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a We focus on the problem of still image-based human action recognition, which essentially involves making prediction by analyzing human poses and their interaction with objects in the scene. Besides image-level action labels (e.g., riding, phoning), during both training and testing stages, existing works usually require additional input of human bounding boxes to facilitate the characterization of the underlying human-object interactions. We argue that this additional input requirement might severely discourage potential applications and is not very necessary. To this end, a systematic approach was developed in this paper to address this challenging problem of minimum annotation efforts, i.e., to perform recognition in the presence of only image-level action labels in the training stage. Experimental results on three benchmark data sets demonstrate that compared with the state-of-the-art methods that have privileged access to additional human bounding-box annotations, our approach achieves comparable or even superior recognition accuracy using only action annotations in training. Interestingly, as a by-product in many cases, our approach is able to segment out the precise regions of underlying human-object interactions
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Li Cheng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jianxin Wu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jianfei Cai
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Do, Minh N
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jiangbo Lu
|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 25(2016), 11 vom: 01. Nov., Seite 5479-5490
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:25
|g year:2016
|g number:11
|g day:01
|g month:11
|g pages:5479-5490
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2016.2605305
|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 25
|j 2016
|e 11
|b 01
|c 11
|h 5479-5490
|