Accommodating Audio Modality in CLIP for Multimodal Processing
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (8) · 9641-9649
DOI: 10.1609/aaai.v37i8.26153 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Ludan Ruan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref).
Abstract (Originalsprache)
Multimodal processing has attracted much attention lately especially with the success of pre-training. However, the exploration has mainly focused on vision-language pre-training, as introducing more modalities can greatly complicate model design and optimization. In this paper, we extend the state-of-the-art Vision-Language model CLIP to accommodate the audio modality for Vision-Language-Audio multimodal processing. Specifically, we apply inter-modal and intra-modal contrastive learning to explore the correlation between audio and other modalities in addition to the inner characteristics of the audio modality. Moreover, we further design an audio type token to dynamically learn different audio information type for different scenarios, as both verbal and nonverbal heterogeneous information is conveyed in general audios. Our proposed CLIP4VLA model is validated in different downstream tasks including video retrieval and video captioning, and achieves the state-of-the-art performance on the benchmark datasets of MSR-VTT, VATEX, and Audiocaps.The corresponding code and checkpoints will be released at https://github.com/ludanruan/CLIP4VLA.
Zitieren
APA
Ruan, L., Hu, A., Song, Y., Zhang, L., Zheng, S., & Jin, Q. (2023). Accommodating Audio Modality in CLIP for Multimodal Processing. Proceedings of the AAAI Conference on Artificial Intelligence, 37(8), 9641-9649. https://doi.org/10.1609/aaai.v37i8.26153
Vancouver
Ruan L, Hu A, Song Y, Zhang L, Zheng S, Jin Q. Accommodating Audio Modality in CLIP for Multimodal Processing. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(8):9641-9649. doi:10.1609/aaai.v37i8.26153
BibTeX
@article{Ruan2023,
author = {Ruan, Ludan and Hu, Anwen and Song, Yuqing and Zhang, Liang and Zheng, Sipeng and Jin, Qin},
title = {Accommodating Audio Modality in CLIP for Multimodal Processing},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {8},
pages = {9641--9649},
doi = {10.1609/aaai.v37i8.26153}
}
EUVIMED