|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM299082458 |
| 003 |
DE-627 |
| 005 |
20250225145428.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2020 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2019.2926728
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n0996.xml
|
| 035 |
|
|
|a (DE-627)NLM299082458
|
| 035 |
|
|
|a (NLM)31295103
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhang, Zhenyu
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Joint Task-Recursive Learning for RGB-D Scene Understanding
|
| 264 |
|
1 |
|c 2020
|
| 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 04.09.2020
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a RGB-D scene understanding under monocular camera is an emerging and challenging topic with many potential applications. In this paper, we propose a novel Task-Recursive Learning (TRL) framework to jointly and recurrently conduct three representative tasks therein containing depth estimation, surface normal prediction and semantic segmentation. TRL recursively refines the prediction results through a series of task-level interactions, where one-time cross-task interaction is abstracted as one network block of one time stage. In each stage, we serialize multiple tasks into a sequence and then recursively perform their interactions. To adaptively enhance counterpart patterns, we encapsulate interactions into a specific Task-Attentional Module (TAM) to mutually-boost the tasks from each other. Across stages, the historical experiences of previous states of tasks are selectively propagated into the next stages by using Feature-Selection unit (FS-Unit), which takes advantage of complementary information across tasks. The sequence of task-level interactions is also evolved along a coarse-to-fine scale space such that the required details may be refined progressively. Finally the task-abstracted sequence problem of multi-task prediction is framed into a recursive network. Extensive experiments on NYU-Depth v2 and SUN RGB-D datasets demonstrate that our method can recursively refines the results of the triple tasks and achieves state-of-the-art performance
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Cui, Zhen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xu, Chunyan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jie, Zequn
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Xiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Jian
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 42(2020), 10 vom: 02. Okt., Seite 2608-2623
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:42
|g year:2020
|g number:10
|g day:02
|g month:10
|g pages:2608-2623
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2019.2926728
|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 42
|j 2020
|e 10
|b 02
|c 10
|h 2608-2623
|