Sammenlign metoder

	Multimodal tekstresumé	Multimodal Transformer
Fagområde	Dyb læring	Dyb læring
Familie	Machine learning	Machine learning
Oprindelsesår	2018	2019–2021
Ophavsperson	Zhu et al. (pioneering MSMO framework)	Lu et al. (ViLBERT); Radford et al. (CLIP)
Type	Generative / extractive NLP with visual input	Cross-modal attention-based deep learning model
Oprindelig kilde	Zhu, J., Li, H., Liu, T., Zhou, Y., Zhang, J., & Zong, C. (2018). MSMO: Multimodal Summarization with Multimodal Output. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), 4154–4164.	Lu, J., Batra, D., Parikh, D., & Lee, S. (2019). ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. Advances in Neural Information Processing Systems (NeurIPS), 32.
Aliasser	MMS, multimodal summarization, cross-modal summarization, vision-language summarization	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
Relaterede	5	5
Resumé	Multimodal text summarization generates a concise textual summary by jointly processing multiple input modalities — most commonly text and images, but also video frames or audio — using deep learning models that align visual and linguistic representations. The output is a natural-language summary that captures salient content from all available modalities.	A Multimodal Transformer extends the standard Transformer architecture to process and jointly reason over two or more input modalities — most commonly text and images, but also audio, video, or structured data. Cross-modal attention layers allow information from one modality to inform representations in another, enabling tasks such as visual question answering, image captioning, and multimodal sentiment analysis.