The DOI matches its Crossref record; 203 of the 213 references it cites were found in a registry or an index.
Attention mechanisms in computer vision: A survey
Open accessAbstract
Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system. Such an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input image. Attention mechanisms have achieved great success in many visual tasks, including image classification, object detection, semantic segmentation, video understanding, image generation, 3D vision, multimodal tasks, and self-supervised learning. In this survey, we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach, such as channel attention, spatial attention, temporal attention, and branch attention; a related repository https://github.com/MenghaoGuo/Awesome-Vision-Attentions is dedicated to collecting related work. We also suggest future directions for attention mechanism research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The evolution of LMs has led to the proliferation of various attention mechanisms (Guo et al. 2022).”
From Large language models (LLMs): survey, technical frameworks, and future challenges (2024) · cites this paper as Guo et al. 2022
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Items 201–203 of 203
Graph-Based Global Reasoning NetworksPreprint
Chen, Y., Rohrbach, M., Yan, Z., Yan, S., Feng, J., & Kalantidis, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.12814 · Cited by 13 · cited 2×
“GloRe [71] understands self-attention from a graph learning perspective.”
BackgroundFuseFormer: Fusing Fine-Grained Information in Transformers for Video InpaintingPreprint
Liu, R. Z. Z., Deng, H., Huang, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.02974 · Cited by 7 · cited 2×
“Following ViT, many transformer-based architectures such as PCT [27], IPT [79], T2T-ViT [44], DeepViT [167], SETR [81], PVT [45], CaiT [168], TNT [82], Swin-transformer [46], Query2Label [83], MoCoV3 [84], BEiT [85], SegFormer [86], FuseFormer [169], and MAE [170] have appeared, with excellent results for many kind of…”
BackgroundSampling Equivariant Self-attention Networks for Object Detection in Aerial ImagesPreprint
Yang, G.-Y., Li, X., Martin, R. R., & Hu, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.03420 · Cited by 3 · cited 1×
“[8], [9], [15], [21], [31], [32], [34], [35] , [22], [26], [62], [63], [64], [65], [66], [67] , [41], [68], [69], [70], [71], [72], [73], [74] , [8], [34], [42], [43], [75], [76], [77], [78] , [27], [44], [45], [46], [79], [80], [81], [82] , [61], [83], [84], [85], [86], [87], [88], [89] , [47], [90], [91], [92], [93]…”
Self-citation
Research works printed but not linked: 6
- Zhang, S. Y.; Yan, S. P.; He, X. M. LatentGNN: Learning efficient non-local relations for visual recognition. In: Proceedings of the 36th International Conference on Machine Learning, 7374–7383, 2019.
- Liu, S.; Li, F.; Zhang, H.; Yang, X.; Qi, X.; Su, H.; Zhu, J.; Zhang, L. DAB-DETR: Dynamic anchor boxes are better queries for DETR. arXiv preprint arXiv:2201.12329, 2022. · arXiv
- Guo, M.-H.; Lu, C.-Z.; Liu, Z.-N.; Cheng, M.-M.; Hu, S.-M. Visual attention network. arXiv preprint arXiv:2202.09741, 2022. · arXiv
- Han, K.; Wang, Y.; Chen, H.; Chen, X.; Guo, J.; Liu, Z.; Tang, Y.; Xiao, A.; Xu, C.; Xu, Y.; et al. A survey on visual transformer. arXiv preprint arXiv:2012.12556, 2020. · arXiv
- Bahdanau, D.; Cho, K.; Bengio, Y. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014. · arXiv
- Foret, P.; Kleiner, A.; Mobahi, H.; Neyshabur, B. Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.01412, 2020. · arXiv
Cited by
Sorted by citations
Transformers in medical imaging: A survey
Shamshad, F., Khan, S., Zamir, S. W., Khan, M. H., Hayat, M., Khan, F. S., & Fu, H. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102802 · Cited by 1,506
Guo, M.-H., Lu, C.-Z., Liu, Z.-N., Cheng, M., & Hu, S. (2023) · Computational Visual Media · doi:10.1007/s41095-023-0364-2 · Cited by 1,235
“For vision tasks, different channels often represent different objects [43], [65].”
BackgroundInfluentialSelf-citationLarge Selective Kernel Network for Remote Sensing Object Detection
Li, Y., Hou, Q., Zheng, Z., Cheng, M., Yang, J. J., & Li, X. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01540 · Cited by 1,022
“The attention mechanism [21] is a simple but effective way to enhance neural representations for various tasks.”
BackgroundSelf-citationBeyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks
Guo, M.-H., Liu, Z.-N., Mu, T., & Hu, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3211006 · Cited by 703
Self-citationConvolutional Neural Networks: A Survey
Krichen, M. (2023) · Computers · doi:10.3390/computers12080151 · Cited by 623
“Attention mechanisms are a powerful tool for improving the performance of CNNs [178–182].”
Metadata
- Authors
- Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M.
- Affiliations
- Tsinghua University (CN)
- TKLNDST, College of Computer Science, Nankai University, Tianjin 300350, China
- Nankai University (CN)
- Cardiff University (GB)
- Corresponding author
- Hu, Shi-Min
- ORCID
- Venue
- Computational Visual Media
- Publisher
- Tsinghua University Press
- Published
- 2022-09
- Volume
- 8
- Issue
- 3
- Pages
- 331-368
- ISSN
- 2096-0433 (ISSN-L)
- 2096-0662
- OpenAlex
- W3212386989
- Cited by
- 2,566
- References
- 213
- Citations by year
- 2026: 404 · 2025: 687 · 2024: 739 · 2023: 576 · 2022: 159
- FWCI
- 176.50
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Computational Visual Media (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62132012, 61521002)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- attention mechanism, visual attention, channel attention, spatial attention, temporal attention, image classification, object detection, semantic segmentation, video understanding, image generation, 3D vision, multimodal tasks, self-supervised learning, human visual system
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
