So sánh phương pháp

	Transformer Đa phương thức	Nhúng câu (Sentence Embeddings)
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2019–2021	2015–2019
Người khởi xướng	Lu et al. (ViLBERT); Radford et al. (CLIP)	Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019)
Loại	Cross-modal attention-based deep learning model	Representation learning / embedding
Công trình gốc	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.	Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3980–3990.
Tên gọi khác	multimodal attention model, cross-modal transformer, vision-language transformer, multi-modal fusion transformer	sentence vectors, sentence representations, SBERT, semantic sentence encoding
Liên quan	5	4
Tóm tắt	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.	Sentence Embeddings convert a sentence or short text into a single fixed-length dense vector that captures its semantic meaning. These vectors allow downstream tasks — semantic similarity, clustering, retrieval, and classification — to operate on numerical representations instead of raw text, making them one of the most versatile building blocks in modern NLP pipelines.