|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM34710150X |
| 003 |
DE-627 |
| 005 |
20231226033029.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3211612
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1156.xml
|
| 035 |
|
|
|a (DE-627)NLM34710150X
|
| 035 |
|
|
|a (NLM)36194713
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Li, Xiangtai
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Improving Video Instance Segmentation via Temporal Pyramid Routing
|
| 264 |
|
1 |
|c 2023
|
| 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 10.04.2023
|
| 500 |
|
|
|a Date Revised 11.04.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Video Instance Segmentation (VIS) is a new and inherently multi-task problem, which aims to detect, segment, and track each instance in a video sequence. Existing approaches are mainly based on single-frame features or single-scale features of multiple frames, where either temporal information or multi-scale information is ignored. To incorporate both temporal and scale information, we propose a Temporal Pyramid Routing (TPR) strategy to conditionally align and conduct pixel-level aggregation from a feature pyramid pair of two adjacent frames. Specifically, TPR contains two novel components, including Dynamic Aligned Cell Routing (DACR) and Cross Pyramid Routing (CPR), where DACR is designed for aligning and gating pyramid features across temporal dimension, while CPR transfers temporally aggregated features across scale dimension. Moreover, our approach is a light-weight and plug-and-play module and can be easily applied to existing instance segmentation methods. Extensive experiments on three datasets including YouTube-VIS (2019, 2021) and Cityscapes-VPS demonstrate the effectiveness and efficiency of the proposed approach on several state-of-the-art instance and panoptic segmentation methods. Codes will be publicly available at https://github.com/lxtGH/TemporalPyramidRouting
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a He, Hao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Yibo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ding, Henghui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Kuiyuan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Cheng, Guangliang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Tong, Yunhai
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Tao, Dacheng
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 5 vom: 04. Mai, Seite 6594-6601
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:5
|g day:04
|g month:05
|g pages:6594-6601
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3211612
|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 45
|j 2023
|e 5
|b 04
|c 05
|h 6594-6601
|