MemBridge : Video-Language Pre-Training With Memory-Augmented Inter-Modality Bridge
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...
Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 32(2023) vom: 20., Seite 4073-4087 |
---|---|
1. Verfasser: | |
Weitere Verfasser: | , , , , , , , |
Format: | Online-Aufsatz |
Sprache: | English |
Veröffentlicht: |
2023
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |
Schlagworte: | Journal Article |
Zusammenfassung: | 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 |
---|---|
Beschreibung: | Date Revised 19.07.2023 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
ISSN: | 1941-0042 |
DOI: | 10.1109/TIP.2023.3283916 |