|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM377795917 |
| 003 |
DE-627 |
| 005 |
20250306162303.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240919s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2024.3459800
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1258.xml
|
| 035 |
|
|
|a (DE-627)NLM377795917
|
| 035 |
|
|
|a (NLM)39292596
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Su, Ke
|e verfasserin
|4 aut
|
| 245 |
1 |
3 |
|a To Boost Zero-Shot Generalization for Embodied Reasoning With Vision-Language Pre-Training
|
| 264 |
|
1 |
|c 2024
|
| 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 03.10.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Recently, there exists an increased research interest in embodied artificial intelligence (EAI), which involves an agent learning to perform a specific task when dynamically interacting with the surrounding 3D environment. There into, a new challenge is that many unseen objects may appear due to the increased number of object categories in 3D scenes. It makes developing models with strong zero-shot generalization ability to new objects necessary. Existing work tries to achieve this goal by providing embodied agents with massive high-quality human annotations closely related to the task to be learned, while it is too costly in practice. Inspired by recent advances in pre-trained models in 2D visual tasks, we attempt to boost zero-shot generalization for embodied reasoning with vision-language pre-training that can encode common sense as general prior knowledge. To further improve its performance on a specific task, we rectify the pre-trained representation through masked scene graph modeling (MSGM) in a self-supervised manner, where the task-specific knowledge is learned from iterative message passing. Our method can improve a variety of representative embodied reasoning tasks by a large margin (e.g., over 5.0% w.r.t. answer accuracy on MP3D-EQA dataset that consists of many real-world scenes with a large number of new objects during testing), and achieve the new state-of-the-art performance
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhang, Xingxing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Siyang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhu, Jun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Bo
|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 33(2024) vom: 18., Seite 5370-5381
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnas
|
| 773 |
1 |
8 |
|g volume:33
|g year:2024
|g day:18
|g pages:5370-5381
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2024.3459800
|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 33
|j 2024
|b 18
|h 5370-5381
|