Open Access
Peer-Reviewed
Review Papers
A Decade of Transformer Architectures in Computational Vision: Comprehensive Survey and Future Horizons
From Vision Transformers (ViT) to Multi-Modal Spatial-Temporal Diffusion Backbones
Abstract
Since the introduction of attention mechanisms to computer vision, transformer-based neural architectures have redefined the state of the art in image classification, semantic segmentation, 3D point cloud processing, and generative synthesis. This survey systematically reviews over 180 key contributions over the past ten years, categorizing architectural paradigms by attention formulation, tokenization mechanics, and compute efficiency trade-offs.
Keywords
Vision Transformers
Deep Learning
Computer Vision
Multi-Modal Systems
Literature Review
Declarations & Ethics
Funding:
Supported by the US National Science Foundation (NSF Award IIS-2104928).
Conflicts of Interest:
The authors declare no competing financial or institutional interests.
Peer Review:
Double-blind peer reviewed by international subject specialists.
License:
Creative Commons Attribution 4.0 International (CC BY 4.0).
How to Cite This Article
APA / MLA / BibTeX
Rostova, et al. (2026). A Decade of Transformer Architectures in Computational Vision: Comprehensive Survey and Future Horizons. Journal of Advanced Computing and Applied Sciences, 4(2). https://doi.org/10.1234/jcas.2026.040203
Rostova, et al. "A Decade of Transformer Architectures in Computational Vision: Comprehensive Survey and Future Horizons." Journal of Advanced Computing and Applied Sciences, vol. 4, no. 2, 2026. https://doi.org/10.1234/jcas.2026.040203
Rostova, et al. "A Decade of Transformer Architectures in Computational Vision: Comprehensive Survey and Future Horizons." Journal of Advanced Computing and Applied Sciences 4, no. 2 (2026). https://doi.org/10.1234/jcas.2026.040203