Back to Search
Start Over
Transformers in computational visual media: A survey
- Source :
- Computational Visual Media, Vol 8, Iss 1, Pp 33-62 (2021)
- Publication Year :
- 2021
- Publisher :
- Springer Science and Business Media LLC, 2021.
-
Abstract
- Transformers, the dominant architecture for natural language processing, have also recently attracted much attention from computational visual media researchers due to their capacity for long-range representation and high performance. Transformers are sequence-to-sequence models, which use a self-attention mechanism rather than the RNN sequential structure. Thus, such models can be trained in parallel and can represent global information. This study comprehensively surveys recent visual transformer works. We categorize them according to task scenario: backbone design, high-level vision, low-level vision and generation, and multimodal learning. Their key ideas are also analyzed. Differing from previous surveys, we mainly focus on visual transformer methods in low-level vision and generation. The latest works on backbone design are also reviewed in detail. For ease of understanding, we precisely describe the main contributions of the latest works in the form of tables. As well as giving quantitative comparisons, we also present image results for low-level vision and generation tasks. Computational costs and source code links for various important works are also given in this survey to assist further development.
- Subjects :
- Source code
Computer science
media_common.quotation_subject
QA75.5-76.95
visual transformer
Computer Graphics and Computer-Aided Design
low-level vision
Task (project management)
Multimodal learning
Computer graphics
high-level vision
computational visual media (CVM)
Artificial Intelligence
Human–computer interaction
Electronic computers. Computer science
Key (cryptography)
image generation
Computer Vision and Pattern Recognition
multi-modal learning
Architecture
Representation (mathematics)
Transformer (machine learning model)
media_common
Subjects
Details
- ISSN :
- 20960662 and 20960433
- Volume :
- 8
- Database :
- OpenAIRE
- Journal :
- Computational Visual Media
- Accession number :
- edsair.doi.dedup.....7a6223265de3dd953f060f2d317684d8