|
|
|
|
LEADER |
01000naa a22002652 4500 |
001 |
NLM359376991 |
003 |
DE-627 |
005 |
20231226080736.0 |
007 |
cr uuu---uuuuu |
008 |
231226s2023 xx |||||o 00| ||eng c |
024 |
7 |
|
|a 10.1109/TIP.2023.3283916
|2 doi
|
028 |
5 |
2 |
|a pubmed24n1197.xml
|
035 |
|
|
|a (DE-627)NLM359376991
|
035 |
|
|
|a (NLM)37436853
|
040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
041 |
|
|
|a eng
|
100 |
1 |
|
|a Yang, Jiahao
|e verfasserin
|4 aut
|
245 |
1 |
0 |
|a MemBridge
|b Video-Language Pre-Training With Memory-Augmented Inter-Modality Bridge
|
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 Revised 19.07.2023
|
500 |
|
|
|a published: Print-Electronic
|
500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
520 |
|
|
|a Video-language pre-training has attracted considerable attention recently for its promising performance on various downstream tasks. Most existing methods utilize the modality-specific or modality-joint representation architectures for the cross-modality pre-training. Different from previous methods, this paper presents a novel architecture named Memory-augmented Inter-Modality Bridge (MemBridge), which uses the learnable intermediate modality representations as the bridge for the interaction between videos and language. Specifically, in the transformer-based cross-modality encoder, we introduce the learnable bridge tokens as the interaction approach, which means the video and language tokens can only perceive information from bridge tokens and themselves. Moreover, a memory bank is proposed to store abundant modality interaction information for adaptively generating bridge tokens according to different cases, enhancing the capacity and robustness of the inter-modality bridge. Through pre-training, MemBridge explicitly models the representations for more sufficient inter-modality interaction. Comprehensive experiments show that our approach achieves competitive performance with previous methods on various downstream tasks including video-text retrieval, video captioning, and video question answering on multiple datasets, demonstrating the effectiveness of the proposed method. The code has been available at https://github.com/jahhaoyang/MemBridge
|
650 |
|
4 |
|a Journal Article
|
700 |
1 |
|
|a Li, Xiangyang
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Zheng, Mao
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Wang, Zihan
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Zhu, Yongqing
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Guo, Xiaoqian
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Yuan, Yuchen
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Chai, Zifeng
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Jiang, Shuqiang
|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 32(2023) vom: 20., Seite 4073-4087
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
773 |
1 |
8 |
|g volume:32
|g year:2023
|g day:20
|g pages:4073-4087
|
856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2023.3283916
|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 32
|j 2023
|b 20
|h 4073-4087
|