Multimodal NLP
Multimodal NLP is a family of natural-language-processing pipelines that combine text with one or more additional data modalities — most commonly images, but also audio and video — to perform understanding and generation tasks such as visual question answering, image captioning, and multimodal sentiment recognition. The field gained its modern form with CLIP (Radford et al., 2021) and has since advanced through architectures such as BLIP-2 (Li et al., 2023) that bridge frozen image encoders and large language models.
Изворни запис
Цитирани радови су копирани дословно из изворног записа методе. Из њих се не изводи верификација на нивоу тврдње.
- Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning Transferable Visual Models From Natural Language Supervision. Proceedings of the 38th International Conference on Machine Learning (ICML), 8748–8763. · URL
- Li, J., Li, D., Savarese, S., & Hoi, S. (2023). BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. Proceedings of the 40th International Conference on Machine Learning (ICML), 19730–19742. · URL
Куроване тврдње
Тврдње су сачуване у регистру доказа, свака са својом проценом.
Овај приказ не измишља процену тврдње када регистар нема ниједну.
Сродне методе
Генерисано из графа метода и приказано као машински предложене везе — не изводи се тврдња доказа.