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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 6×
“ResNeSt [115] also adopts this attention mechanism to improve the CNN backbone in a more general way, giving excellent results on ResNet [146] and ResNeXt [176].”
BackgroundMethodResultInfluentialVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 4×
“Transformers have had great success in natural language processing [33], [38], [149], [150], [152], [161].”
BackgroundInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 9×
“Given an input feature map X and the previous time step LSTM hidden state ht−1 ∈ Rd, a spatial attention mechanism pays more attention to the semantically useful regions, guided by LSTM hidden state ht−1.”
BackgroundInfluentialAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 3×
“SGD [104] and Adam [72] are well-suited for optimizing convolutional neural networks.”
BackgroundImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“ViT demonstrates that a pure attention-based network can achieve better results than a convolutional neural network especially for large datasets such as JFT-300 [164] and ImageNet-21K [165].”
BackgroundBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 3×
“Transformers have had great success in natural language processing [33], [38], [149], [150], [152], [161].”
BackgroundGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534 · cited 4×
“Recently, various pure deep self-attention networks (visual transformers) [27], [34], [44], [45], [46], [47], [48], [49] have appeared, showing the huge potential of attention-based models.”
BackgroundInfluentialSelf-citationCBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 1×
“Large-scale attention-based pre-trained models have had great success in natural language processing [85], [179].”
Background
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
Items 901–1,000 of 1,001
Att 2 CPC: Attention-Guided Lossy Attribute Compression of Point Clouds
Liu, K., You, K., Gao, P., & Paul, M. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3486676 · Cited by 7
“2) Point-Based Method: Thanks to PointNet [35] and Point-Net++ [36], point-based methods that directly operate on points have been widely studied and examined [27], [37], [38], [39].”
Enhanced Attention-Based Multimodal Deep Learning for Product Categorization on E-Commerce Platform
Hung, L. V., Binh, P. V., Nhat, P. M., & Hieu, N. D. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-74127-2_8 · Cited by 7
A salient feature establishment tactic for cassava disease recognition
Zhang, J., Zhang, B., Chen, Z., Nyalala, I., Chen, K., & Gao, J. (2024) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2024.11.004 · Cited by 7
AMMUNet: Multiscale Attention Map Merging for Remote Sensing Image Segmentation
Yang, Y., Zheng, S., Wang, X., Ao, W., & Liu, Z. (2024) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2024.3506718 · Cited by 7
“However, despite their successes, Transformer-based approaches suffer from a significant limitation: the necessity for window-based operations to mitigate computational demands of global self-attention mechanisms [13], [14].”
Self-citationSpace–Frequency and Global–Local Attentive Networks for Sequential Deepfake Detection
Zhang, G., Li, Q., Gao, M., Guo, S., Jeon, G., & Abdelmoniem, A. M. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3541346 · Cited by 7
“Among the attention mechanisms, spatial and channel attention are considered the most representative and have been extensively explored in the literature [17].”
SpecViT: A Custom Vision-Transformer based Approach for Audio Deepfake Detection
Modak, S., Das, A. K., & Naskar, R. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889022 · Cited by 8
“The attention mechanism allows each token to attend to other tokens, enabling the model to learn contextual representations effectively [27], [12], [22].”
Fan, X., Niu, G., Liu, R., Qin, J., Yi, X., Tu, J., Li, X., & Huang, M. (2025) · Journal of Environmental Management · doi:10.1016/j.jenvman.2025.125094 · Cited by 7
Tian, C., Yang, J., Li, P., Zhang, S., & Mi, S. (2022) · Medical Physics · doi:10.1002/mp.15580 · Cited by 7
Self-citationMulti-scale aggregation networks with flexible receptive fields for melanoma segmentation
Zhang, J., Pan, W., Wang, B., Chen, Q., & Cheng, Y. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103950 · Cited by 7
Traffic Sign Detection Based on Lightweight Multiscale Feature Fusion Network
Lin, S., Zhang, Z., Tao, J., Zhang, F., Fan, X., & Lu, Q.-C. (2022) · Sustainability · doi:10.3390/su142114019 · Cited by 7
“As can be seen from the structure in Figure 4, the input feature map of the attention module [40] generated the channel domain attention feature map after the channel atten ‐ tion branch.”
MethodLuo, Y., Wang, J., Yang, X., Yu, Z., & Tan, Z. (2022) · Remote Sensing · doi:10.3390/rs14215415 · Cited by 7
V2ReID: Vision-Outlooker-Based Vehicle Re-Identification
Qian, Y., Barthélemy, J., Iqbal, U., & Perez, P. (2022) · Sensors · doi:10.3390/s22228651 · Cited by 7
Fu, M., Wang, Q., Wang, J., Sun, L., Ma, Z., Zhang, C., Guan, W., Liu, Q., Wang, D., & Li, W. (2023) · Applied Sciences · doi:10.3390/app13021066 · Cited by 7
Lightweight Pedestrian Detection Based on Feature Multiplexed Residual Network
Sha, M., Zeng, K., Tao, Z., Wang, Z., & Liu, Q. (2023) · Electronics · doi:10.3390/electronics12040918 · Cited by 7
“Other researchers have improved the detection performance of lightweight models by designing attention mechanisms [31].”
BackgroundТерепищий, С. О. (2023) · Humanities science current issues · doi:10.24919/2308-4863/60-4-31 · Cited by 17
Deep Triply Attention Network for RGBT Tracking
Yang, R., Wang, X., Zhu, Y., & Tang, J. (2023) · Cognitive Computation · doi:10.1007/s12559-023-10158-z · Cited by 7
“For more related works, we refer to the following survey papers [28, 29].”
BackgroundCNNs with Multi-Level Attention for Domain Generalization
Ballas, A., & Diou, C. (2023) · International Conference on Multimedia Retrieval · doi:10.1145/3591106.3592263 · Cited by 7
“Since their outstanding success in several NLP tasks, Transformers and self-attention mechanisms have slowly but steadily gained ground in the Computer Vision community [13], achieving significant advances in the field [17, 42, 44].”
BackgroundMWFormer: Mesh Understanding with Window-based Transformer
Peng, H.-Y., Guo, M.-H., Liu, Z.-N., Yang, Y., & Mu, T. (2023) · Computers & Graphics · doi:10.1016/j.cag.2023.07.028 · Cited by 7
Self-citationDetection Mature Bud for Daylily Based on Faster R-CNN Integrated With CBAM
Feng, J., Zhao, X., Zhu, T., Li, T., Qiu, Z., & Li, Z. (2023) · IEEE Access · doi:10.1109/access.2023.3299595 · Cited by 7
“There are four kinds of attention mechanisms: channel attention, spatial attention, temporal attention and branch attention [29].”
BackgroundIntrinsic feature extraction for unsupervised domain adaptation
Cao, X., Guo, Y., Yang, W., Luo, X., & Xie, S. (2023) · International Journal of Web Information Systems · doi:10.1108/ijwis-04-2023-0062 · Cited by 7
Fire Safety Detection Based on CAGSA-YOLO Network
Wang, X., Cai, L., Zhou, S., Jin, Y., Lin, T., & Zhao, Y. (2023) · Fire · doi:10.3390/fire6080297 · Cited by 7
On Content-Aware Post-Processing: Adapting Statistically Learned Models to Dynamic Content
Zhang, Y., Ding, G., Ding, D., Ma, Z., & Zhu Li, B. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3612925 · Cited by 7
“Its essential idea is to capture long-range dependencies in embedded data through global self-attention [17].”
BackgroundCruz-Guerrero, I. A., Mejia-Rodriguez, A. R., Ortega, S., Fabelo, H. A., Callicó, G. M., Jo, J. A., & Campos-Delgado, D. U. (2023) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2023.08.027 · Cited by 7
Wang, F., Chu, X., & Zhang, B. (2023) · Ocean Dynamics · doi:10.1007/s10236-023-01591-7 · Cited by 7
“To address this issue, the output of the CNN feature extraction module is taken as the input of the self-attention mechanism (SA) (Guo et al. 2022; Nie et al. 2021) that can automatically assign weight according to the subimage correlation.”
Attention guided approach for food type and state recognition
Alahmari, S. S., Gardner, M. R., & Salem, T. (2024) · Food and Bioproducts Processing · doi:10.1016/j.fbp.2024.02.005 · Cited by 8
Zheng, W., Yan, L., & Wang, F. (2024) · Artificial Intelligence · doi:10.1016/j.artint.2024.104147 · Cited by 8
ETANet: An Efficient Triple-Attention Network for Salient Object Detection
Ngo, T.-T., Huh, E., & Hong, C. S. (2023) · International Conference on Information Networking · doi:10.1109/icoin56518.2023.10048982 · Cited by 7
“Attention mechanism has been introduced in many deep-learning models for feature recalibration in computer vision tasks [10].”
IsoVEM: Isotropic Reconstruction for Volume Electron Microscopy Based on TransformerPreprint
He, J., Zhang, Y., Sun, W., Yang, G., & Sun, F. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.11.22.567807 · Cited by 7
“53 As shown in Extended Data Fig.”
Efficient Channel-Temporal Attention for Boosting RF Fingerprinting
Gu, H., Su, L., Wang, Y., Zhang, W., & Ran, C. (2024) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2024.3362695 · Cited by 6
“Attention mechanisms were first introduced into deep neural networks by researchers in the field of natural language processing, inspired by human cognitive system, to achieve information filtering or enhancement [40].”
BackgroundPANet: Pluralistic Attention Network for Few-Shot Image Classification
Cao, W., Li, T., Liu, Q., & He, Z. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11638-5 · Cited by 7
Cascaded Aggregation Convolution Network for Salient Grain Pests Detection
Yu, J., Chen, S., Liu, N., Zhai, F., & Pan, Q. (2024) · Insects · doi:10.3390/insects15070557 · Cited by 8
“With the development of computer vision [5] and emerging deep learning techniques [6], modern approaches based on image processing and recognition can provide rapid, economic, and precise solutions for grain pest identification and detection.”
DeepCheck: multitask learning aids in assessing microbial genome quality
Guo, W., Wu, N., Zhao, K., Yang, S., Wang, L., & Liu, Y. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae539 · Cited by 6
“Specifically, in the DeepCheck framework, we use the residual network structure [21] and the attention mechanism [22, 23] to construct a feature extractor for extracting task-specific features from inputgenomic information.”
MethodMobile-YOLO-SDD: A Lightweight YOLO for Real-time Steel Defect Detection
Luo, S., Xu, Y., Zhu, M., Zhang, C., Kong, C., Jin, J., Li, T., Jiang, X., & Guo, B. (2024) · Procedia CIRP · doi:10.1016/j.procir.2024.10.040 · Cited by 8
MST-GNN: graph neural network with multi-granularity in space and time for traffic prediction
Zhao, X., Yu, W., & Zhang, Y. (2024) · GeoInformatica · doi:10.1007/s10707-024-00532-w · Cited by 6
Mi, X., Li, S., Ye, Z., Dai, Z., Ding, B., Sun, B., Shen, Y., & Xiao, Z. (2024) · Frontiers in Immunology · doi:10.3389/fimmu.2024.1478201 · Cited by 6
Bayoudh, K., & Mtibaa, A. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03696-y · Cited by 6
Multiserver Federated Learning for Building Energy Prediction With Wind Speed
Wang, R., Fan, Y., Yun, H., Rayhana, R., Bai, L., & Liu, Z. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3522628 · Cited by 6
Self-citationObject detection of mural images based on improved YOLOv8
Wang, P., Fan, X., Yang, Q., Tian, S., & Yu, L. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01687-8 · Cited by 6
“Attention mechanism [17] is a core technology in deep learning, which efficiently allocates information processing resources by simulating human’s selective attention to information.”
Liu, Z., Deng, Z., Li, S., Liu, J. H., Qin, X., Xiao, Z., & Wang, Q. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107623 · Cited by 6
Self-citationLi, X., Kong, D., Li, X., Chen, X., & Zhu, Y. (2025) · Measurement · doi:10.1016/j.measurement.2025.117043 · Cited by 6
Priya, J., & Raja, S. K. S. (2025) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt-2024-0439 · Cited by 6
“Attention mechanisms were later introduced and popularly adopted during the past decade in computer vision for duplicating human visual systems and their e ff ectiveness has been impressively demonstrated [32].”
Image‐Based Breast Cancer Histopathology Classification and Diagnosis Using Deep Learning Approaches
Aldakhil, L. A., Alhasson, H. F., Alharbi, S. S., Khan, R. U., & Qamar, A. M. (2025) · Applied Computational Intelligence and Soft Computing · doi:10.1155/acis/7011984 · Cited by 7
“Attention mechanisms’ efec-tiveness in augmenting computer vision tasks’ performance has garnered substantial empirical support in recent years [60].”
Zhu, L., & Zhao, R. (2025) · Scientific Reports · doi:10.1038/s41598-024-84961-5 · Cited by 6
“The introduction of the attention mechanism into computer vision aims to emulate human information processing methods 21 .”
Li, M., Lan, J., Zhang, Y., & Huang, K. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3562966 · Cited by 6
“Unlike traditional convolution-based methods, transformers utilize an attention mechanism [13], [14], [15], [16] to process information from all positions, effectively capturing input sequence dependencies and acquiring global information from the first layer.”
MAF-MixNet: Few-Shot Tea Disease Detection Based on Mixed Attention and Multi-Path Feature Fusion
Zhang, W., Tan, K., Wang, H., Hu, D., & Pu, H. (2025) · Plants · doi:10.3390/plants14081259 · Cited by 7
“This mechanism is achieved by assigning different importance weights to different parts of the input, such as channels, space, time sequence, and other dimensions [12].”
Medical image segmentation model based on local enhancement driven global optimization
Xu, L., Halike, A., Sen, G., & Sha, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-02393-1 · Cited by 6
Supply chain demand forecasting based on multi-time scale data fusion network
Chen, Y., Zhang, H., Yan, X., & Miao, Q. (2025) · Computers & Industrial Engineering · doi:10.1016/j.cie.2025.111324 · Cited by 6
BSE-YOLO: An Enhanced Lightweight Multi-Scale Underwater Object Detection Model
Wang, Y., Ye, H., & Shu, X. (2025) · Sensors · doi:10.3390/s25133890 · Cited by 9
Multiscale Edge Enhancement and Progressive Change-Aware Network for Remote Sensing Change Detection
Xing, Y., Hu, J., Jia, Y., & Huang, R. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3584959 · Cited by 6
“Attention mechanisms [44] have attracted considerable research interest in various visual tasks, including image fusion [45], [46], detection [47], [48], and semantic segmentation [49].”
Juwita, J., Hassan, G. M., Akhtar, N., & Datta, A. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108224 · Cited by 6
Du, W., & Yang, S. (2025) · Frontiers of Chemical Science and Engineering · doi:10.1007/s11705-025-2587-5 · Cited by 6
Panda, S. L., Kumar, B. S., Sahoo, U. K., & Maiti, S. (2025) · IEEE Transactions on Radar Systems · doi:10.1109/trs.2025.3591065 · Cited by 6
“In order to improve the e ff ectiveness of the base U-Net, several attention modules [21] such as squeeze and excitation (SE) net [22], e ffi cient channel attention (ECA)-Net [23], and style-based recalibration module (Srm) [24] are integrated with it [25], [26], [27].”
Liu, M., Yi, X.-Y., Chen, Y.-Z., Li, M. H., Zhang, Y.-Y., Zhang, C. J. P., Huang, J., & Ming, W. (2025) · The Lancet Digital Health · doi:10.1016/j.landig.2025.100894 · Cited by 6
PHFuse: Unsupervised color visible and infrared image fusion with preserved hue
Zhuang, C., Kuang, H., Wang, H., Wen, C., Liu, C., & Yuan, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-15158-7 · Cited by 6
“In image processing tasks related to deep learning, attention modules imitate human visual and focus on salient areas by dynamically adjusting the weights of input image features 36 .”
Han, S., Sun, S., Pang, K., Li, J., Tian, F., Zhen, D., Feng, G., & Niu, P. (2025) · Journal of the Brazilian Society of Mechanical Sciences and Engineering · doi:10.1007/s40430-025-05822-4 · Cited by 6
SRMamba: Mamba for super-resolution of LiDAR point clouds
Chen, C., Qin, X., Hu, J., Yuan, X., & Ge, W. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114396 · Cited by 6
KUŞ, İ., Koçak, C., & Keleş, A. (2025) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2025.200615 · Cited by 11
Tracking with attention: A review of transformer-based object tracking
Khoshnevis, S. A., & Amirkhani, A. (2025) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2025.102263 · Cited by 6
Attention-enhanced dual-stage deep learning for automated tunnel crack detection and quantification
Chen, Z., Wang, J., & Dai, J. (2026) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1016/j.cacaie.2026.100020 · Cited by 6
Tang, Y., Liu, B., Wang, G., & Li, H. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104604 · Cited by 6
Intensification of extreme climatic events in Central Asia’s arid regions amid climate change
Li, D., Li, Y., Jing, Y., Guo, H., Liu, Y., Wan, Y., & Qingdong, S. H. I. (2026) · Journal of Hydrology · doi:10.1016/j.jhydrol.2026.135465 · Cited by 6
Fingerprint Feature Extraction Using CNN with Multiple Attention Mechanisms
Sasuga, N., Ito, K., & Aoki, T. (2022) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb54206.2022.10007957 · Cited by 6
“Attention mechanisms have been introduced into the field of computer vision to emulate the human visual system, which focuses on specific regions, and have been demonstrated to be effective in a wide range of applications such as image classification, object detection, and semantic segmentation [8].”
BackgroundZhang, Y., Li, Z., Ma, C., Zhang, Y., & Li, J. (2023) · Sensing and Imaging · doi:10.1007/s11220-023-00416-7 · Cited by 6
“It has brought significant performance improvement in many visual tasks such as image classification, object detection/tracking and image segmentation [9, 47].”
Tengxi, W. (2023) · IEEE Access · doi:10.1109/access.2023.3309007 · Cited by 6
“[34] optimized a multivariate LSTM neural network with a variable attention mechanism by measuring the importance of each variable to the target and then optimizing the network by assigning weights to it, and the results showed that the LSTM optimized by the attention mechanism has”
MethodRandom hand gesture authentication via efficient Temporal Segment Set Network
Lin, Y., Song, W., & Kang, W. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2023.103985 · Cited by 6
Scene text visual question answering by using YOLO and STN
Nourali, K., & Dolkhani, E. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-023-10081-6 · Cited by 6
“Each grid cell is responsible for detecting the object by predicting bounding boxes and removing the low probability of them of distant spatial locations for reconstructing the local missing pixels (Guo et al., 2022).”
Yutra, A. Z., Zheng, J., Li, X., & Hasen, A. E. (2023) · doi:10.1145/3638584.3638608 · Cited by 6
Nguyen, M.-H. (2024) · Bioengineering · doi:10.3390/bioengineering11040316 · Cited by 8
“According to the review of Guo et al. [12], the attention module is a successful solution to learning non-local features.”
MethodMIN-MEF: Multiscale Interaction Network for Multiexposure Image Fusion
Yang, Y., Wang, M., Huang, S., & Wan, W. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3386922 · Cited by 6
“Although CBAM uses convolutions to capture local relations, it falls short in modeling long-range dependencies [30].”
BackgroundMethodInfluentialXu, Y., Guo, J., Yang, N., Zhu, C., Zheng, T., Zhao, W., Liu, J., & Song, J. H. (2024) · Frontiers in Oncology · doi:10.3389/fonc.2024.1353446 · Cited by 8
Self-citationExploring the influence of attention for whole-image mammogram classification
Berghouse, M., Bebis, G., & Tavakkoli, A. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105062 · Cited by 6
Wang, W., Mu, T., Li, Q., Li, H., & Yang, Q. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3407953 · Cited by 6
“Inspiredbythathumanvisionselectivelypaysat-tention to regions with significant features [51], attention mechanisms have become prevalent in this field.”
BackgroundSelf-citationZhang, L., Ma, Z., Zhou, J., Li, K., Li, M., Wang, H., Zhang, Q., Wang, C., & Lu, K. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3426382 · Cited by 6
“Attentional mechanisms show superiority in multiple visual tasks [21], [22], [23] that enables network training to focus on the focal region in the whole visual space.”
BackgroundGraph Attention Based Feature Fusion For Collaborative Perception
Ahmed, A. N., Mercelis, S., & Anwar, A. (2024) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55156.2024.10588712 · Cited by 6
CATIL: Customized adversarial training based on instance loss
Zhang, Z., Xia, H., Kang, Z. H., Zhang, R., & Shi, X. (2024) · Information Sciences · doi:10.1016/j.ins.2024.121420 · Cited by 6
Spatiotemporal Object Detection for Improved Aerial Vehicle Detection in Traffic Monitoring
Telegraph, K., & Kyrkou, C. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3454566 · Cited by 10
“The progress of attention-based models in computer vision in the deep learning era can be divided into four phases [44].”
BackgroundGPAC-YOLOv8: lightweight target detection for fire scenarios
Wang, Y., & Kou, Z. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad7a17 · Cited by 6
Zhang, L., Fu, Z., Guo, H., Feng, Y., Sun, Y., & Wang, Z. (2024) · Electronics · doi:10.3390/electronics13183721 · Cited by 6
“Attention-based approaches, including those dependent on spatial-and channel-based attention, are commonly used to extract important information from strip steel images by focusing on the most relevant information while suppressing irrelevant details [1].”
CollabGAT: Collaborative Perception Using Graph Attention Network
Ahmed, A. N., Mercelis, S., & Anwar, A. (2024) · IEEE Access · doi:10.1109/access.2024.3468432 · Cited by 6
“This incites salient features and suppresses insignificant ones guiding the model on which channels to focus on [24].”
BackgroundMethodInfluentialA scalable attention network for lightweight image super-resolution
Fang, J., Chen, X., Zhao, J., & Zeng, K. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102185 · Cited by 6
“An attention mechanism adaptively adjusts the weights of features, guiding the network to concentrate on important information (Guo et al., 2022).”
Li, M., Lan, J., Wang, L., Zhang, Y., & Huang, K. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3466397 · Cited by 6
Traffic signal current prediction algorithm based on CNN and LSTM
Feng, W., Qi, S., Guo, J., Zuo, X., Chen, Y., & Zhu, Y. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad8e7a · Cited by 6
“Dot-product attention is a self-attention mechanism utilized in deep neural networks, which selects and emphasizes the most relevant input data to enhance model performance [30].”
Recognition and Analysis of Painting Styles with the Help of Computer Vision Techniques
Cheng, J., Yang, L., & Tong, S. (2024) · Informatica · doi:10.31449/inf.v48i21.6891 · Cited by 6
RGAM: A refined global attention mechanism for medical image segmentation
Ning, G., Liu, P., Dai, C., Sun, M., Zhou, Q., & Li, Q. (2024) · IET Computer Vision · doi:10.1049/cvi2.12323 · Cited by 6
Deep Learning Integration of Multi-Model Forecast Precipitation Considering Long Lead Times
Fang, W., Qin, H., Lin, Q., Jia, B., Yang, Y., & Shen, K. (2024) · Remote Sensing · doi:10.3390/rs16234489 · Cited by 6
Spatio-temporal attention-based hybrid deep network for time series prediction of industrial process
Dong, L., Zhou, X., & Li, S. (2024) · Applied Intelligence · doi:10.1007/s10489-024-06033-5 · Cited by 6
Double Attention: An Optimization Method for the Self-Attention Mechanism Based on Human Attention
Zhang, Z., Li, B., Yan, C., Furuichi, K., & Todo, Y. (2025) · Biomimetics · doi:10.3390/biomimetics10010034 · Cited by 6
Zuo, Y., Zhang, Y., Zhang, Q., & Zhang, W. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06257-z · Cited by 6
Payatsuporn, T., Kantavat, P., Tangnuntachai, N., Tipparawong, N., Techapapa, W., Kijsirikul, B., & Keelawat, S. (2025) · IEEE Access · doi:10.1109/access.2025.3532505 · Cited by 6
“Some networks combine with an attention mechanism to emphasize channel feature weights [6], [7].”
Neural Optimisation of Fixed Beamformers With Flexible Geometric Constraints
Yan, L., Huang, W., Abhayapala, T. D., Feng, J., & Kleijn, W. B. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3533372 · Cited by 6
“This has shown superior performance than the ReLU and ELU functions in computer vision, natural language processing, and speech tasks [55], [56], [57], [58].”
Cross-Scale Feature Interaction Network for Semantic Segmentation in Side-Scan Sonar Images
Wang, Z., You, Z., Xu, N., Wang, B., & Huang, D.-S. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3534285 · Cited by 6
“As the core component of the semantic segmentation network, the visual attention mechanism [33] plays an important role in extracting global context information, constructing feature long-range dependencies, and completing multiscale feature extraction.”
Global context enhanced resolution networks for sapphire scratch detection and classification
Zhao, G., Lin, Y., Zheng, X., Chen, B., Wang, S., Lin, Z., Lu, Y., Chen, Z., & Guo, W. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2025.112522 · Cited by 6
Decoupled pixel-wise correction for abdominal multi-organ segmentation
Yu, X., Ding, L., Zhang, D., Wu, J., Liang, M., Zheng, J., & Pang, W. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01796-x · Cited by 6
Wang, S., Han, W., Jian, J., Chang, X., & Zeng, L. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3546955 · Cited by 6
“By introducing an AM, neural networks can automatically learn and selectively focus on important information in the input, thereby enhancing the performance and generalization of the model [27].”
Zhang, C., Ji, X., & Cai, L. (2025) · Applied Sciences · doi:10.3390/app15084591 · Cited by 10
“Recent work by Mu et al. [14] and Guo et al. [15] further enhanced feature extraction through multi-level fusion and attention mechanisms.”
Fan, T., Li, H., & Feng, F. (2025) · Journal of Energy Storage · doi:10.1016/j.est.2025.117396 · Cited by 6
Joint domain transfer elasticity metric network for cross-domain small sample fault diagnosis
Shang, Z., Du, X., Pan, C., Liu, F., & Wang, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130936 · Cited by 6
Sun, Z., Yang, J., Zheng, Y., Liu, P., Ma, C., Hu, D., Ying, Y. B., & Xie, L. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110848 · Cited by 6
A hybrid network integrating convolution and transformer for thymoma segmentation
Li, J., Sun, W., Feng, X.-L., von Deneen, K. M., Wang, W., Cui, G., & Zhang, Y. (2022) · Intelligent Medicine · doi:10.1016/j.imed.2022.06.003 · Cited by 6
Cascaded U-Net with Training Wheel Attention Module for Change Detection in Satellite Images
Adil, E., Yang, X., Huang, P., Liu, X., Tan, W., & Yang, J. (2022) · Remote Sensing · doi:10.3390/rs14246361 · Cited by 6
“According to [53], the attention process can be formulated as Attention = f g x , x , where g x is used to generate attention which is a region to be attended and f g x , x is a process that combines x with attention g x .”
BackgroundMethod
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
