|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM348206186 |
| 003 |
DE-627 |
| 005 |
20231226035632.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3217852
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1160.xml
|
| 035 |
|
|
|a (DE-627)NLM348206186
|
| 035 |
|
|
|a (NLM)36306296
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Ding, Henghui
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a VLT
|b Vision-Language Transformer and Query Generation for Referring Segmentation
|
| 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 07.05.2023
|
| 500 |
|
|
|a Date Revised 07.05.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a We propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features. There are different ways to understand the dynamic emphasis of a language expression, especially when interacting with the image. However, the learned queries in existing transformer works are fixed after training, which cannot cope with the randomness and huge diversity of the language expressions. To address this issue, we propose a Query Generation Module, which dynamically produces multiple sets of input-specific queries to represent the diverse comprehensions of language expression. To find the best among these diverse comprehensions, so as to generate a better mask, we propose a Query Balance Module to selectively fuse the corresponding responses of the set of queries. Furthermore, to enhance the model's ability in dealing with diverse language expressions, we consider inter-sample learning to explicitly endow the model with knowledge of understanding different language expressions to the same object. We introduce masked contrastive learning to narrow down the features of different expressions for the same target object while distinguishing the features of different objects. The proposed approach is lightweight and achieves new state-of-the-art referring segmentation results consistently on five datasets
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Liu, Chang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Suchen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jiang, Xudong
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 6 vom: 28. Juni, Seite 7900-7916
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:6
|g day:28
|g month:06
|g pages:7900-7916
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3217852
|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 6
|b 28
|c 06
|h 7900-7916
|