Porovnat metody

	Multimodální odpovídání na otázky	Multimodální Transformer
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2015	2019–2021
Tvůrce	Antol, S. et al. (VQA team, Facebook AI Research / Virginia Tech)	Lu et al. (ViLBERT); Radford et al. (CLIP)
Typ	Supervised multimodal learning	Cross-modal attention-based deep learning model
Původní zdroj	Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C. L., & Parikh, D. (2015). VQA: Visual Question Answering. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2425–2433.	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.
Další názvy	Multimodal QA, Cross-modal question answering, Visual question answering, VQA	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer
Příbuzné	5	5
Shrnutí	Multimodal question answering (Multimodal QA) is a class of deep-learning methods that answer natural-language questions by jointly reasoning over information from multiple modalities — most commonly text and images, but also video, audio, and structured tables. Introduced prominently through the VQA benchmark in 2015, it has since expanded into a broad research area powering document understanding, medical diagnosis assistance, and embodied AI.	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.