Cited by 2,566Visual Attention and Saliency DetectionAdvanced Neural Network ApplicationsAdvanced Image and Video Retrieval Techniques

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 access

Guo, Meng-Hao, Xu, Tian-Xing, Liu, Jiang-Jiang, Liu, Zheng-Ning, Jiang, Peng-Tao, Mu, Tai-Jiang, Zhang, Song-Hai, Martin, Ralph R., Cheng, Ming-Ming, Hu, Shi-Min·2022·Computational Visual Media

DOI 10.1007/s41095-022-0271-y

Open this paper in CoChat — free account Open PDF

Abstract

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.

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

Crossref · 10.1007/s41095-022-0271-y

Cites

203 of 203 references verified0 citation errors · 0 not checkable

Statistics

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

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].”
BackgroundMethodResultInfluential
Attention Is All You Need
Vaswani, 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].”
BackgroundInfluential
Long Short-Term Memory
Hochreiter, 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.”
BackgroundInfluential
Adam: 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.”
Background
ImageNet: 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].”
Background
BERT: 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].”
Background
Going 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-citation
CBAM: 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
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
Pyramid Scene Parsing Network
Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.660 · Cited by 16,438 · cited 1×
“ANN [68] suggests that using all positional features as key and vectors is redundant and adopts spatial pyramid pooling [157, 158] to obtain a few representative key and value features to use instead, to reduce computation.”
Method
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPreprint
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 15,273
Untitled work
(2010) · International Conference on Machine Learning · Cited by 13,995
Layer NormalizationPreprint
Ba, J., Kiros, J., & Hinton, G. E. (2016) · arXiv.org · doi:10.48550/arxiv.1607.06450 · Cited by 13,762 · cited 1×
“ViT stacks a number of MHA layers with fully connected layers, layer normalization [162] and the GELU [163] activation function.”
Background
Control of goal-directed and stimulus-driven attention in the brain
Corbetta, M., & Shulman, G. L. (2002) · Nature Reviews Neuroscience · doi:10.1038/nrn755 · Cited by 12,881 · cited 1×
“M ETHODS for diverting attention to the most important regions of an image and disregarding irrelevant parts are called attention mechanisms; the human visual system uses one [1], [2], [3], [4] to assist in analyzing and understanding complex scenes efficiently and effectively.”
Background
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Aggregated Residual Transformations for Deep Neural Networks
Xie, S., Girshick, R., Dollar, P., Tu, Z., & He, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.634 · Cited by 12,465 · cited 2×
“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].”
Result
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
Proceedings of the 24th international conference on Machine learning
(2007) · doi:10.1145/1273496 · Cited by 11,869
Non-local Neural Networks
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596 · cited 12×
“[128] introduced self-attention into computer vision.”
BackgroundMethodInfluential
A model of saliency-based visual attention for rapid scene analysis
Itti, L., Christof Koch, A., & Niebur, E. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.730558 · Cited by 11,289 · cited 1×
“M ETHODS for diverting attention to the most important regions of an image and disregarding irrelevant parts are called attention mechanisms; the human visual system uses one [1], [2], [3], [4] to assist in analyzing and understanding complex scenes efficiently and effectively.”
Background
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., & Hu, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01155 · Cited by 9,641 · cited 6×
“[37] proposed the efficient channel attention (ECA) block which instead uses a 1D convolution to determine the interaction between channels, instead of dimensionality reduction.”
BackgroundMethodInfluential
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Deformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513 · cited 6×
“[7] proposed deformable convolutional networks (deformable ConvNets) to be invariant to geometric transformations, but they pay attention to the important regions in a different manner.”
BackgroundMethodInfluential
Dual Attention Network for Scene Segmentation
Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00326 · Cited by 7,351
Self-citation
Coordinate Attention for Efficient Mobile Network Design
Hou, Q., Zhou, D., & Feng, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01350 · Cited by 6,961
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687 · cited 2×
“Self-attention was firstly proposed in [33] and rapidly provided great advances in the field of natural language processing [33], [38], [39].”
Background
Deformable DETR: Deformable Transformers for End-to-End Object Detection
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020) · arXiv · doi:10.48550/arxiv.2010.04159 · Cited by 6,027
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., & Fu, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01234-2_18 · Cited by 6,003
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 2×
“Recently, MoCoV3 [84], DINO [180], BEiT [85] and MAE [169] have demonstrated that attention-based models are also well suited to visual tasks.”
Background
Attention U-Net: Learning Where to Look for the Pancreas
Oktay, O., Schlemper, J., Folgoc, L. L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N. Y., Kainz, B., et al. (2018) · arXiv · doi:10.48550/arxiv.1804.03999 · Cited by 5,458 · cited 2×
“[19] proposed a simple and yet effective mechanism, the attention gate (AG), to focus on targeted regions while suppressing feature activations in irrelevant regions.”
Background
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00061 · Cited by 5,259 · cited 3×
“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.”
Background
Untitled work
(1999) · Cited by 5,147
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021) · arXiv · doi:10.48550/arxiv.2105.15203 · Cited by 5,090 · cited 2×
“[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]…”
Untitled work
Han (2023) · doi:10.1109/tpami.2022.3152247 · Cited by 4,682
Self-citation
Proceedings of the 21st International Conference on Neural Information Processing Systems
Koller, D., Schuurmans, D., Bengio, Y., & Bottou, L. (2008) · Cited by 4,461
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196 · 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].”
BackgroundMethodResultInfluential
Residual Attention Network for Image Classification
Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., & Tang, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.683 · Cited by 4,073 · cited 10×
“Attention mechanisms have become an indispensable technique in the field of computer vision in the era of deep learning.”
BackgroundMethodInfluential
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P. H. S., et al. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00681 · Cited by 4,008 · cited 2×
“[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]…”
Background
Group Normalization
Wu, Y., & He, K. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01198-w · Cited by 3,601
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595 · cited 2×
“Three more specific surveys [141], [142], [143] summarize the development of visual transformers while our paper reviews attention mechanisms in vision more generally, not just selfattention mechanisms.”
Background
Gaussian Error Linear Units (GELUs)
Hendrycks, D., & Gimpel, K. (2016) · arXiv · doi:10.48550/arxiv.1606.08415 · Cited by 3,537 · cited 2×
“normalization [163], and the GELU [164] activation function.”
Background
Selective Kernel Networks
Li, X., Wang, W., Hu, X., & Yang, J. J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00060 · Cited by 3,472 · cited 2×
“[114] to propose an automatic selection operation called selective kernel (SK) convolution.”
Background
Recurrent Models of Visual AttentionPreprint
Mnih, V., Heess, N., Graves, A., & Kavukcuoglu, K. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.6247 · Cited by 3,393 · cited 7×
“[88] proposed a deep recurrent network, similar to RAM [31], capable of processing a multi-resolution crop of the input image, called a glimpse, for multiple object recognition task.”
BackgroundMethodInfluential
Transformer-XL: Attentive language models beyond a fixed-length context
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1285 · Cited by 3,169 · cited 1×
“Self-attention was proposed and has had great success in the field of natural language processing (NLP) [33], [38], [39], [149], [150], [151], [152].”
Background
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10578-9_23 · Cited by 3,034 · cited 1×
“ANN [68] suggests that using all positional features as key and vectors is redundant and adopts spatial pyramid pooling [157, 158] to obtain a few representative key and value features to use instead, to reduce computation.”
Method
Point Transformer
Zhao, H., Jiang, L., Jia, J., Torr, P. H. S., & Koltun, V. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01595 · Cited by 3,005
Deformable ConvNets V2: More Deformable, Better Results
Zhu, X., Hu, H., Lin, S., & Dai, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00953 · Cited by 2,943 · cited 3×
“features is the major characteristic of the second phase; DCNs [7, 36] are representative works.”
Background
CvT: Introducing Convolutions to Vision Transformers
Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., & Zhang, L. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00009 · Cited by 2,795 · cited 3×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Background
Self-Attention with Relative Position Representations
Shaw, P., Uszkoreit, J., & Vaswani, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2074 · Cited by 2,505 · cited 1×
“They also explore the behavior of positional embedding and show that relative positional embeddings [161] are suitable.”
Background
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.97 · Cited by 2,484 · 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].”
Background
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E. H., Feng, J., & Yan, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00060 · Cited by 2,415 · cited 3×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Background
On the momentum term in gradient descent learning algorithms
Ning Qian, A. (1999) · Neural Networks · doi:10.1016/s0893-6080(98)00116-6 · Cited by 2,318 · cited 1×
“SGD [181] and Adam [182] are well-suited for optimizing convolutional neural networks.”
Background
Pre-Trained Image Processing Transformer
Chen, H., Wang, Y., Guo, T., Xu, C., Deng, Y., Liu, Z., Ma, S., Xu, C., Xu, C., & Gao, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01212 · Cited by 2,308 · cited 2×
“[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
GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond
Cao, Y., Xu, J., Lin, S., Wei, F., & Hu, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00246 · Cited by 2,307 · cited 3×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Background
PCT: Point cloud transformer
Guo, M.-H., Cai, J.-X., Liu, Z.-N., Mu, T.-J., Martin, R. R., & Hu, S.-M. (2021) · Computational Visual Media · doi:10.1007/s41095-021-0229-5 · Cited by 2,100 · 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-citation
SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning
Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., & Chua, T. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.667 · Cited by 2,089 · cited 7×
“SCACNN [17] CVPR2017 ICap a)compute channel attention map and spatial attention map using visual features and previous hidden state b) stack channel attention and spatial attention in serial a) focus the network on discriminative regions b) emphasize important channels c) capture global information d) avoid high compu…”
BackgroundMethodInfluential
MLP-Mixer: An all-MLP Architecture for Vision
Tolstikhin, I., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2105.01601 · Cited by 2,087
ResNeSt: Split-Attention Networks
Zhang, H., Wu, C., Zhang, Z., Zhu, Y., Lin, H., Zhang, Z., Sun, Y., He, T., Mueller, J. W., Manmatha, R., et al. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00309 · Cited by 2,074 · cited 1×
“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].”
Result
Proceedings of The 32nd International Conference on Machine Learning
Germain, M., Gregor, K., Murray, I., & Larochelle, H. (2015) · Cited by 2,020
Second-Order Attention Network for Single Image Super-Resolution
Dai, T., Cai, J., Zhang, Y., Xia, S.-T., & Zhang, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01132 · Cited by 2,010 · cited 1×
“segmentation [156, 40], face recognition [145, 126], person re-identification [78, 14], action recognition [128, 37], few-show learning [103, 58], medical image processing [99, 47], image generation [46, 159], pose estimation [27], super resolution [30, 164], 3D vision [137, 48], and multi-modal task [116, 141].”
Background
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., & He, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00143 · Cited by 1,923
Self-citation
Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network
Peng, C., Zhang, X., Yu, G., Luo, G., & Sun, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.189 · Cited by 1,750
A Structured Self-attentive Sentence Embedding
Lin, Z., Feng, M., Santos, C. N. D., Yu, M., Xiang, B., Zhou, B., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.03130 · Cited by 1,743 · cited 2×
“Transformers have had great success in natural language processing [33], [38], [149], [150], [152], [161].”
Background
An Empirical Study of Training Self-Supervised Vision Transformers
Chen, X., Xie, S., & He, K. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00950 · Cited by 1,648 · cited 3×
“Recently, MoCoV3 [84], DINO [180], BEiT [85] and MAE [169] have demonstrated that attention-based models are also well suited to visual tasks.”
Background
Dynamic Convolution: Attention Over Convolution Kernels
Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., & Liu, Z. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01104 · Cited by 1,633 · cited 1×
“[116] proposed dynamic convolution, a novel operator design that increases representational power with negligible additional computational cost and does not change the width or depth of the network in parallel with CondConv [174].”
BackgroundSelf-citation
FcaNet: Frequency Channel Attention Networks
Qin, Z., Zhang, P., Wu, F. Q., & Li, X. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00082 · Cited by 1,587 · cited 3×
“[57] rethought global information captured from the viewpoint of compression and analysed global average pooling in the frequency domain.”
Background
Context Encoding for Semantic Segmentation
Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00747 · Cited by 1,528
Relation Networks for Object Detection
Hu, H., Gu, J., Zhang, Z., Dai, J., & Wei, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00378 · Cited by 1,524
Training Very Deep NetworksPreprint
Srivastava, R. K., Greff, K., & Schmidhuber, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.06228 · Cited by 1,504 · cited 3×
“Combine different branches Highway Network [113] NeurIPS2015 Cls linear layer → sigmoid (A) (0, 1) S (I), (II)”
BackgroundInfluential
DRAW: A Recurrent Neural Network For Image GenerationPreprint
Gregor, K., Danihelka, I., Graves, A., Rezende, D. J., & Wierstra, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.04623 · Cited by 1,498 · cited 4×
“RAM pioneered the use of RNNs for visual attention, and was followed by many other RNN-based methods [21], [35], [88].”
BackgroundMethodInfluential
Harmonious Attention Network for Person Re-identification
Li, W., Zhu, X., & Gong, S. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00243 · Cited by 1,497
Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition
Fu, J., Zheng, H., & Mei, T. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.476 · Cited by 1,469 · cited 1×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Going Deeper with Convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2014) · arXiv · doi:10.48550/arxiv.1409.4842 · Cited by 1,461 · cited 1×
“For instance, GoogleNet [178] conforms to the above formula, but does not belong to the attention mechanisms.”
Background
Proceedings of the 2nd International Conference on Neural Information Processing Systems
Touretzky, D. S. (1989) · Cited by 1,439
Transformer in Transformer
Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., & Wang, Y. (2021) · arXiv · doi:10.48550/arxiv.2103.00112 · Cited by 1,394 · cited 2×
“[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]…”
BEiT: BERT Pre-Training of Image Transformers
Bao, H., Dong, L., Piao, S., & Wei, F. (2021) · arXiv · doi:10.48550/arxiv.2106.08254 · Cited by 1,392 · cited 4×
“Recently, MoCoV3 [84], DINO [180], BEiT [85] and MAE [169] have demonstrated that attention-based models are also well suited to visual tasks.”
BackgroundInfluential
Attention Augmented Convolutional Networks
Bello, I., Zoph, B., Le, Q. V., Vaswani, A., & Shlens, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00338 · Cited by 1,347 · cited 2×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Method
Eye movements in natural behavior
Hayhoe, M., & Ballard, D. H. (2005) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2005.02.009 · Cited by 1,321 · cited 1×
“M ETHODS for diverting attention to the most important regions of an image and disregarding irrelevant parts are called attention mechanisms; the human visual system uses one [1], [2], [3], [4] to assist in analyzing and understanding complex scenes efficiently and effectively.”
Background
Rotate to Attend: Convolutional Triplet Attention Module
Misra, D., Nalamada, T., Arasanipalai, A. U., & Hou, Q. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00318 · Cited by 1,287 · cited 9×
“Attention mechanisms have become an indispensable technique in the field of computer vision in the era of deep learning.”
BackgroundInfluential
BAM: Bottleneck Attention ModulePreprint
Park, J., Woo, S., Lee, J., & Kweon, I. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.06514 · Cited by 1,272 · cited 4×
“[6], [117]) or generate a joint 3-D channel, height, width attention mask directly (e.”
BackgroundInfluential
Going deeper with Image Transformers
Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., & Jegou, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00010 · Cited by 1,259 · 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…”
Background
PSANet: Point-wise Spatial Attention Network for Scene Parsing
Zhao, H., Yi, Z., Liu, S., Shi, J., Loy, C. C., Lin, D., & Jia, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_17 · Cited by 1,243 · cited 3×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
BackgroundMethod
Proceedings of the 24th International Conference on Neural Information Processing Systems
Shawe-Taylor, J. S., Zemel, R. S., Bartlett, P. L., Pereira, F. B., & Weinberger, K. Q. (2011) · Cited by 1,184
SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks
Yang, L., Zhang, R., Li, L., & Xie, X. (2021) · International Conference on Machine Learning · Cited by 1,130
The Dynamic Representation of Scenes
Rensink, R. A. (2000) · Visual Cognition · doi:10.1080/135062800394667 · Cited by 1,089
ParseNet: Looking Wider to See BetterPreprint
Liu, W., Rabinovich, A., & Berg, A. C. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.04579 · Cited by 1,056 · cited 1×
“Due to the localisation of the convolutional operation, CNNs have inherently narrow receptive fields [155, 156], which limits the ability of CNNs to understand scenes globally.”
Background
Learning Multi-attention Convolutional Neural Network for Fine-Grained Image Recognition
Zheng, H., Fu, J., Mei, T., & Luo, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.557 · Cited by 1,045 · 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]…”
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
Song, S., Lan, C., Xing, J., Zeng, W., & Liu, J. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11212 · Cited by 1,027
Self-citation
Untitled work
(2020) · International Conference on Machine Learning · Cited by 1,012
Exploring Self-Attention for Image Recognition
Zhao, H., Jia, J., & Koltun, V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01009 · Cited by 1,002 · cited 4×
“PSANet formulates information aggregation as: zi = ∑ j∈Ω(i) F (xi, xj ,∆ij)xj (55) where ∆ij indicates the positional relationship between i and j.”
MethodInfluential
Stand-Alone Self-Attention in Vision Models
Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., & Shlens, J. (2019) · arXiv · doi:10.48550/arxiv.1906.05909 · Cited by 977 · cited 7×
“SASA [43] NeurIPS2019 Cls, Det Dot product between query and key -> softmax.”
BackgroundMethodInfluential
CoAtNet: Marrying Convolution and Attention for All Data Sizes
Dai, Z., Liu, H., Le, Q. V., & Tan, M. (2021) · arXiv · doi:10.48550/arxiv.2106.04803 · Cited by 925 · cited 1×
“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.”
Background
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
Hou, Q., Zhang, L., Cheng, M., & Feng, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00406 · Cited by 888
Self-citation
An Attentive Survey of Attention Models
Chaudhari, S., Mithal, V., Polatkan, G., & Ramanath, R. (2021) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3465055 · Cited by 860 · cited 1×
“[141] provided a survey of attention models in deep neural networks which concentrates on their application to natural language processing, while our work focuses on computer vision.”
Background
Multiple Object Recognition with Visual Attention
Ba, J., Mnih, V., & Kavukcuoglu, K. (2014) · arXiv · doi:10.48550/arxiv.1412.7755 · Cited by 808 · cited 3×
“[88] proposed a deep recurrent network, similar to RAM [31], capable of processing a multi-resolution crop of the input image, called a glimpse, for multiple object recognition task.”
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training
Touvron, H., Bojanowski, P., Caron, M., Cord, M., El-Nouby, A., Grave, E., Izacard, G., Joulin, A., Synnaeve, G., Verbeek, J., et al. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3206148 · Cited by 807 · cited 2×
“A similar idea can be found in LatentGNN [72], MLP-Mixer [159], and ResMLP [160].”
Result
Asymmetric Non-Local Neural Networks for Semantic Segmentation
Zhu, Z., Xu, M., Bai, S., Huang, T., & Bai, X. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00068 · Cited by 760 · cited 3×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Method
Multi-context Attention for Human Pose Estimation
Chu, X., Yang, W. P., Ouyang, W., Ma, C., Yuille, A., & Wang, X. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.601 · Cited by 752 · cited 1×
“, image classification [5, 6], object detection [7, 8], semantic segmentation [9, 10], face recognition [11, 12], person re-identification [13, 14], action recognition [15, 16], few-shot learning [17, 18], medical image processing [19, 20], image generation [21, 22], pose estimation [23], super resolution [24, 25], 3D…”
Background
Expectation-Maximization Attention Networks for Semantic Segmentation
Li, X., Zhong, Z., Wu, J., Yang, Y., Lin, Z., & Liu, H. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00926 · Cited by 741 · cited 2×
“It was followed by a series of works such as EMANet [40], CCNet [41], HamNet [42] and the Stand-Alone Network [43], which improved speed, quality of results, and generalization capability.”
BackgroundMethod
PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling
Yan, X., Zheng, C., Li, Z., Wang, S., & Cui, S. R. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00563 · Cited by 709
Relation-Aware Global Attention for Person Re-Identification
Zhang, Z., Lan, C., Zeng, W., Jin, X., & Chen, Z. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00325 · Cited by 706 · cited 11×
“Unlike coordinate attention and DANet, which emphasise capturing long-range context, in relation-aware global attention (RGA) [101], Zhang et al. stress the importance of global structural information provided by pairwise relations, and uses it to produce attention maps.”
BackgroundMethodInfluential
Beyond 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 · cited 2×
“EANet [75] proposes that self-attention should only consider correlation in a single sample and should ignore potential relationships between different samples.”
BackgroundSelf-citation
Rethinking Attention with Performers
Choromanski, K., Likhosherstov, V., Dohan, D., Song, X., Gane, A., Sarlos, T., Hawkins, P., Davis, J., Mohiuddin, A., Kaiser, L., et al. (2020) · arXiv · doi:10.48550/arxiv.2009.14794 · Cited by 695 · cited 2×
“Transformers have had great success in natural language processing [33], [38], [149], [150], [152], [161].”
Background
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
Lee, J., Lee, Y., Kim, J., Kosiorek, A. R., Choi, S., & Teh, Y. W. (2018) · arXiv · doi:10.48550/arxiv.1810.00825 · Cited by 691
An Empirical Study of Spatial Attention Mechanisms in Deep Networks
Zhu, X., Cheng, D., Zhang, Z., Lin, S., & Dai, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00679 · Cited by 659 · cited 2×
“[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]…”
Method
Local Relation Networks for Image Recognition
Hu, H., Zhang, Z., Xie, Z., & Lin, S. C.-F. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00356 · Cited by 636 · cited 2×
“[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]…”
Action Recognition using Visual AttentionPreprint
Sharma, S., Kiros, R., & Salakhutdinov, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.04119 · Cited by 623 · 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]…”
End-to-End Comparative Attention Networks for Person Re-Identification
Liu, H., Feng, J., Qi, M., Jiang, J., & Yan, S. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2700762 · Cited by 611 · 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]…”
Segmentation Transformer: Object-Contextual Representations for Semantic SegmentationPreprint
Yuan, Y., Chen, X., Chen, X., & Wang, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.11065 · Cited by 608 · cited 2×
“OCRNet [73] proposes the concept of object-contextual representation which is a weighted aggregation of all object regions’ representations in the same category, such as a weighted average of all car region representations.”
Background
ABD-Net: Attentive but Diverse Person Re-Identification
Chen, T., Ding, S., Xie, J., Yuan, Y., Chen, W., Yang, Y., Ren, Z., & Wang, Z. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00844 · Cited by 604 · cited 1×
“[130, 101, 123, 86, 96, 17, 84], [108, 40, 61, 166, 148, 152, 135] , [122, 14, 19, 62, 78]”
Gather-Excite: Exploiting Feature Context in Convolutional Neural NetworksPreprint
Hu, J., Shen, L., Albanie, S., Sun, G., & Vedaldi, A. (2018) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.48550/arxiv.1810.12348 · Cited by 593 · cited 8×
“Inspired by SENet, Hu et al. [61] designed GENet to capture long-range spatial contextual information by providing a recalibration function in the spatial domain.”
BackgroundMethodInfluential
CondConv: Conditionally Parameterized Convolutions for Efficient InferencePreprint
Yang, B., Bender, G., Le, Q. V., & Ngiam, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.04971 · Cited by 582
Tell Me Where to Look: Guided Attention Inference Network
Li, K., Wu, Z., Peng, K., Ernst, J., & Fu, Y. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00960 · Cited by 564
Graph-Based Global Reasoning Networks
Chen, Y., Rohrbach, M., Yan, Z., Shuicheng, Y., Feng, J., & Kalantidis, Y. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00052 · Cited by 554 · cited 2×
“GloRe [71] understands self-attention from a graph learning perspective.”
Background
Improving Convolutional Networks With Self-Calibrated Convolutions
Liu, J., Hou, Q., Cheng, M., Wang, C., & Feng, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01011 · Cited by 535 · cited 4×
“Motivated by the success of group convolution, Liu et at [86] presented self-calibrated convolution as a means to enlarge the receptive field at each spatial location.”
BackgroundMethodInfluentialSelf-citation
Recalibrating Fully Convolutional Networks With Spatial and Channel “Squeeze and Excitation” Blocks
Roy, A. G., Navab, N., & Wachinger, C. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2867261 · Cited by 534
Pedestrian Alignment Network for Large-scale Person Re-Identification
Zheng, Z., Zheng, L., & Yang, Y. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2873599 · Cited by 525 · cited 1×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Global Second-Order Pooling Convolutional Networks
Gao, Z., Xie, J., Wang, Q., & Li, P. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00314 · Cited by 524 · cited 4×
“[54] proposed to improve the squeeze module by using a global second-order pooling (GSoP) block to model high-order statistics while gathering global information.”
BackgroundMethodInfluential
CCNet: Criss-Cross Attention for Semantic Segmentation
Huang, Z., Wang, X., Wei, Y., Huang, L., Shi, H., Liu, W., & Huang, T. S. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3007032 · Cited by 524
OCNet: Object Context Network for Scene ParsingPreprint
Yuan, Y., Huang, L., Guo, J., Zhang, C., Chen, X., & Wang, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.00916 · Cited by 520 · cited 3×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
BackgroundMethod
Attention-Aware Compositional Network for Person Re-identification
Xu, J., Zhao, R., Zhu, F., Wang, H., & Ouyang, W. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00226 · Cited by 517
Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition
Zheng, H., Fu, J., Zha, Z.-J., & Luo, J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00515 · Cited by 507 · cited 1×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
VideoLSTM convolves, attends and flows for action recognition
Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., & Snoek, C. G. M. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.10.011 · Cited by 492
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton DataPreprint
Song, S., Lan, C., Xing, J., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.06067 · Cited by 481 · cited 6×
“[130], [132], [133], [134], [135], [136], [137], [138], [139]”
BackgroundInfluential
Modeling Point Clouds With Self-Attention and Gumbel Subset Sampling
Yang, J., Zhang, Q., Ni, B., Li, L., Liu, J., Zhou, M., & Tian, Q. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00344 · Cited by 477 · cited 1×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Self-citation
Untitled work
(2021) · International Conference on Learning Representations · Cited by 449
Mixed High-Order Attention Network for Person Re-Identification
Chen, B., Deng, W., & Hu, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00046 · Cited by 437 · cited 2×
“segmentation [156, 40], face recognition [145, 126], person re-identification [78, 14], action recognition [128, 37], few-show learning [103, 58], medical image processing [99, 47], image generation [46, 159], pose estimation [27], super resolution [30, 164], 3D vision [137, 48], and multi-modal task [116, 141].”
Background
Diversified Visual Attention Networks for Fine-Grained Object Classification
Zhao, B., Wu, X., Feng, J., Peng, Q., & Yan, S. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2648498 · Cited by 428 · cited 1×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Deformable Convolutional NetworksPreprint
Dai, J., Qi, H., Xiong, Y., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.06211 · Cited by 428 · cited 6×
“[7] proposed deformable convolutional networks (deformable ConvNets) to be invariant to geometric transformations, but they pay attention to the important regions in a different manner.”
BackgroundMethodInfluential
Neural Aggregation Network for Video Face Recognition
Yang, J., Ren, P., Zhang, D., Chen, D., Wen, F., Li, H., & Hua, G. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.554 · Cited by 423 · cited 1×
“, image classification [5, 6], object detection [7, 8], semantic segmentation [9, 10], face recognition [11, 12], person re-identification [13, 14], action recognition [15, 16], few-shot learning [17, 18], medical image processing [19, 20], image generation [21, 22], pose estimation [23], super resolution [24, 25], 3D…”
Background
Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification
Wang, C., Zhang, Q., Huang, C., Liu, W., & Wang, X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01225-0_23 · Cited by 421 · cited 1×
“[130, 101, 123, 86, 96, 17, 84], [108, 40, 61, 166, 148, 152, 135] , [122, 14, 19, 62, 78]”
STAT: Spatial-Temporal Attention Mechanism for Video Captioning
Yan, C. C., Tu, Y., Wang, X., Zhang, Y., Hao, X., Zhang, Y., & Dai, Q. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2924576 · Cited by 412 · cited 1×
“[130], [132], [133], [134], [135], [136], [137], [138], [139]”
TAM: Temporal Adaptive Module for Video Recognition
Liu, Z., Wang, L., Wu, W., Qian, C., & Lü, T. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01345 · Cited by 405 · cited 9×
“Combine local attention and global attention TAM [173] Arxiv2020 Action a) local: global spatial average pooling → 1D Convs, b) global: global spatial average pooling → MLP → adaptive convolution (A) (0, 1) S (II), (III)”
BackgroundInfluentialSelf-citation
Object-Part Attention Model for Fine-Grained Image Classification
Peng, Y., He, X., & Zhao, J. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2774041 · Cited by 399 · cited 1×
“, image classification [5, 6], object detection [7, 8], semantic segmentation [9, 10], face recognition [11, 12], person re-identification [13, 14], action recognition [15, 16], few-shot learning [17, 18], medical image processing [19, 20], image generation [21, 22], pose estimation [23], super resolution [24, 25], 3D…”
Background
DeepViT: Towards Deeper Vision Transformer
Zhou, D., Kang, B., Jin, X., Yang, L., Lian, X., Jiang, Z., Hou, Q., & Feng, J. (2021) · arXiv · doi:10.48550/arxiv.2103.11886 · Cited by 398 · cited 1×
“Following ViT, many transformer-based architectures such as PCT [27], IPT [79], T2T-ViT [44], DeepViT [166], SETR [81], PVT [45], CaiT [167], TNT [82], Swintransformer [46], Query2Label [83], MoCoV3 [84], BEiT [85], SegFormer [86], FuseFormer [168] and MAE [169] have appeared, with excellent results for many kind of v…”
Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-identification
Li, S., Bąk, S., Carr, P., & Wang, X. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00046 · Cited by 387
SRM: A Style-Based Recalibration Module for Convolutional Neural Networks
Lee, H., Kim, H., & Nam, H. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00194 · Cited by 379 · cited 8×
“[5], [37], [53], [54], [55], [56], [57], [58] [25], [59], [60] Spatial attention Generate attention mask across spatial domains and use it to select important spatial regions (e.”
BackgroundInfluential
Disentangled Non-local Neural Networks
Yin, M., Yao, Z., Cao, Y., Li, X., Zhang, Z., Lin, S. C.-F., & Hu, H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58555-6_12 · Cited by 370
Gated Channel Transformation for Visual Recognition
Yang, Z., Zhu, L., Wu, Y., & Yang, Y. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01181 · Cited by 367 · cited 8×
“To overcome the above problems, Yang et al. [56] propose the gated channel transformation (GCT) to efficiently collect information while explicitly modeling channel-wise relationships.”
BackgroundMethodInfluential
Attentional ShapeContextNet for Point Cloud Recognition
Xie, S., Liu, S., Chen, Z., & Tu, Z. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00484 · Cited by 359 · cited 3×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
BackgroundMethod
Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification
Xu, S., Cheng, Y., Gu, K., Yang, Y., Chang, S., & Zhou, P. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.507 · Cited by 351
VOLO: Vision Outlooker for Visual Recognition
Yuan, L., Hou, Q., Jiang, Z., Feng, J., & Yan, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3206108 · Cited by 350 · cited 2×
“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.”
Background
Single Shot Text Detector with Regional Attention
He, P. L., Huang, W., He, T., Zhu, Q., Qiao, Y., & Li, X. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.331 · Cited by 347 · cited 1×
“, image classification [5, 6], object detection [7, 8], semantic segmentation [9, 10], face recognition [11, 12], person re-identification [13, 14], action recognition [15, 16], few-shot learning [17, 18], medical image processing [19, 20], image generation [21, 22], pose estimation [23], super resolution [24, 25], 3D…”
Background
Early and Late Mechanisms of Surround Suppression in Striate Cortex of Macaque
Webb, B. S., Dhruv, N. T., Solomon, S. G., Tailby, C., & Lennie, P. (2005) · Journal of Neuroscience · doi:10.1523/jneurosci.3414-05.2005 · Cited by 337 · cited 1×
“Motivated by the spatial suppression phenomenon [176], they propose that a neuron which shows suppression effects should be emphasized and define an energy function for each neuron as:”
Background
Attentional Pooling for Action RecognitionPreprint
Girdhar, R., & Ramanan, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.01467 · Cited by 311 · 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]…”
Co-Occurrent Features in Semantic Segmentation
Zhang, H., Zhang, H., Wang, C., & Xie, J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00064 · Cited by 302 · cited 2×
“[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]…”
Method
Revisiting Unreasonable Effectiveness of Data in Deep Learning EraPreprint
Sun, C., Shrivastava, A., Singh, S., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.02968 · Cited by 300 · 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].”
Background
Global-Local Temporal Representations for Video Person Re-Identification
Li, J., Zhang, S. S., Wang, J., Gao, W., & Tian, Q. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00406 · Cited by 279 · cited 8×
“It adopts an adaptive kernel instead of self-attention to capture global contextual information, with lower time complexity than GLTR [172].”
BackgroundMethodInfluentialSelf-citation
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., & Dai, J. (2020) · International Conference on Learning Representations · Cited by 276
$A^2$-Nets: Double Attention NetworksPreprint
Chen, Y., Kalantidis, Y., Li, J., Yan, S., & Feng, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.11579 · Cited by 261 · cited 2×
“[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]…”
Method
Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification
Yang, J., Zheng, W., Yang, Q., Chen, Y.-C., & Tian, Q. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00335 · Cited by 260 · cited 9×
“Flattening spatial and temporal dimensions into a sequence, STGCN applies the GCN to capture the spatiotemporal relationships of patches across different frames.”
BackgroundMethodInfluential
Hierarchical LSTMs with Adaptive Attention for Visual Captioning
Gao, L., Li, X., Song, J., & Shen, H. T. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2894139 · Cited by 249 · cited 1×
“[130], [132], [133], [134], [135], [136], [137], [138], [139]”
Query2Label: A Simple Transformer Way to Multi-Label ClassificationPreprint
Liu, S., Zhang, L., Yang, X., Su, H., & Zhu, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10834 · Cited by 242 · cited 2×
“[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]…”
Background
Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease ClassificationPreprint
Guan, Q., Huang, Y., Zhong, Z., Zheng, Z., Zheng, L., & Yang, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.09927 · Cited by 235 · cited 2×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Background
STA: Spatial-Temporal Attention for Large-Scale Video-Based Person Re-Identification
Fu, Y., Wang, X., Wei, Y., & Huang, T. S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018287 · Cited by 230 · cited 10×
“, [132]), to focus on informative regions.”
BackgroundMethodInfluential
Video Person Re-identification with Competitive Snippet-Similarity Aggregation and Co-attentive Snippet Embedding
Chen, D., Li, H., Xiao, T., Yi, S., & Wang, X. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00128 · Cited by 227
Recurrent Spatial-Temporal Attention Network for Action Recognition in Videos
Du, W., Wang, Y., & Qiao, Y. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2778563 · Cited by 220 · cited 7×
“[16] introduced spatiotemporal attention to adaptively identify key features in a global way.”
BackgroundInfluential
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
Xie, Q., Lai, Y., Wu, J., Wang, Z., Zhang, Y., Xu, K., & Wang, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01046 · Cited by 217
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and BeyondPreprint
Cao, Y., Xu, J., Lin, S. C.-F., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.11492 · Cited by 212 · cited 3×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Background
Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
Li, X., Yang, Y., Zhao, Q., Shen, T., Lin, Z., & Liu, H. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00897 · Cited by 205
Spatio-temporal Channel Correlation Networks for Action Classification
Diba, A., Fayyaz, M., Sharma, V., Arzani, M. M., Yousefzadeh, R., Gall, J., & Gool, L. V. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01225-0_18 · Cited by 201
Masked Autoencoders Are Scalable Vision LearnersPreprint
He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.06377 · Cited by 200 · cited 4×
“Recently, MoCoV3 [84], DINO [180], BEiT [85] and MAE [169] have demonstrated that attention-based models are also well suited to visual tasks.”
BackgroundInfluential
Second-Order Non-Local Attention Networks for Person Re-Identification
Bryan, B., Gong, Y., Zhang, Y., & Poellabauer, C. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00386 · Cited by 197 · cited 1×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
Liu, R. Z. Z., Deng, H., Huang, Y., Shi, X., Lu, L., Sun, W., Wang, X., Dai, J., & Li, H. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01378 · Cited by 171 · 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…”
Background
Bilinear Attention Networks for Person Retrieval
Fang, P., Zhou, J., Roy, S. K., Petersson, L., & Harandi, M. T. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00812 · Cited by 170 · cited 1×
“[147] claimed that previous attention models only use first-order information and disregard higher-order statistical information.”
Method
Compact Generalized Non-local NetworkPreprint
Yue, K., Sun, M., Yuan, Y., Zhou, F., Ding, E., & Xu, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.13125 · Cited by 165 · 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]…”
PVNet
You, H., Feng, Y., Ji, R., & Gao, Y. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240702 · Cited by 161
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial NetworksPreprint
Xu, T., Zhang, P., Huang, Q., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.10485 · Cited by 159 · cited 1×
“image classification [5], [6], object detection [7], [8], semantic segmentation [9], [10], face recognition [11], [12], person re-identification [13], [14], action recognition [15], [16], few-show learning [17], [18], medical image processing [19], [20], image generation [21], [22], pose estimation [23], super resolut…”
BackgroundSelf-citation
Transformers in computational visual media: A survey
Xu, Y., Wei, H., Lin, M., Deng, Y., Sheng, K., Zhang, M., Tang, F., Dong, W., Huang, F., & Xu, C. (2021) · Computational Visual Media · doi:10.1007/s41095-021-0247-3 · Cited by 144 · cited 2×
“Three more specific surveys [141], [142], [143] summarize the development of visual transformers while our paper reviews attention mechanisms in vision more generally, not just selfattention mechanisms.”
Background
Is Attention Better Than Matrix Decomposition?Preprint
Geng, Z., Guo, M.-H., Chen, H., Li, X., Wei, K., & Lin, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.04553 · Cited by 140 · cited 4×
“HamNet [42] models capturing global relationships as a low-rank completion problem and designs a series of white-box methods to capture global context using matrix decomposition.”
MethodInfluentialSelf-citation
Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-Based Person Re-Identification
Zhang, Z., Lan, C., Zeng, W., & Chen, Z. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01042 · Cited by 137
Survey on the attention based RNN model and its applications in computer visionPreprint
Wang, F., & Tax, D. M. J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1601.06823 · Cited by 128 · cited 1×
“[124] present a survey of attention models in computer vision, but it only considers RNN-based attention models, which form just a part of our survey.”
Background
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
Chen, X., Hsieh, C.-J., & Gong, B. (2021) · arXiv · doi:10.48550/arxiv.2106.01548 · Cited by 128 · cited 1×
“[184] significantly improved visual transformers by using a novel optimizer, the sharpness-aware minimizer (SAM) [185].”
Background
SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds
Shi, H., Lin, G., Wang, H., Hung, T.-Y., & Wang, Z. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00463 · Cited by 106 · cited 1×
“[66, 158, 181, 73, 150, 125, 105, 35] [25, 111, 164]”
Interpretable Spatio-Temporal Attention for Video Action Recognition
Meng, L., Zhao, B., Chang, B., Huang, G. M., Sun, W. M., Tung, F., & Sigal, L. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00189 · Cited by 104 · cited 1×
“[130], [132], [133], [134], [135], [136], [137], [138], [139]”
Multi-Context Attention for Human Pose EstimationPreprint
Chu, X., Yang, W. P., Ouyang, W., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07432 · Cited by 100 · cited 1×
“, image classification [5, 6], object detection [7, 8], semantic segmentation [9, 10], face recognition [11, 12], person re-identification [13, 14], action recognition [15, 16], few-shot learning [17, 18], medical image processing [19, 20], image generation [21, 22], pose estimation [23], super resolution [24, 25], 3D…”
Background
An Empirical Study of Spatial Attention Mechanisms in Deep NetworksPreprint
Zhu, X., Cheng, D., Zhang, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.05873 · Cited by 100 · cited 2×
“[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]…”
Method
You Look Twice: GaterNet for Dynamic Filter Selection in CNNs
Chen, Z., Li, Y., Samy Bengio, A., & Si, S. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00939 · Cited by 98 · cited 1×
“[5], [37], [53], [54], [55], [56], [57], [58] [25], [59], [60] Spatial attention Generate attention mask across spatial domains and use it to select important spatial regions (e.”
Background
SCAN: Self-and-Collaborative Attention Network for Video Person Re-Identification
Zhang, R., Li, J., Sun, H., Ge, Y., Luo, P., Wang, X., & Lin, L. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2911488 · Cited by 92
Hierarchical Pyramid Diverse Attention Networks for Face Recognition
Wang, Q., Wu, T., Zheng, H., & Guo, G. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00835 · Cited by 92 · cited 1×
“, image classification [5, 6], object detection [7, 8], semantic segmentation [9, 10], face recognition [11, 12], person re-identification [13, 14], action recognition [15, 16], few-shot learning [17, 18], medical image processing [19, 20], image generation [21, 22], pose estimation [23], super resolution [24, 25], 3D…”
Background
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksPreprint
Guo, M.-H., Liu, Z.-N., Mu, T., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.02358 · Cited by 83 · cited 2×
“EANet [75] proposes that self-attention should only consider correlation in a single sample and should ignore potential relationships between different samples.”
BackgroundSelf-citation
L2G Auto-encoder
Liu, X., Han, Z., Wen, X., Liu, Y.-S., & Zwicker, M. (2019) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3343031.3350960 · Cited by 79 · 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]…”
Beyond the classical receptive field: The effect of contextual stimuli
Spillmann, L., Dresp, B., & Tseng, C. (2015) · Journal of Vision · doi:10.1167/15.9.7 · Cited by 78 · cited 1×
“Research in the neuroscience community suggests that visual cortical neurons adaptively adjust the sizes of their receptive fields (RFs) according to the input stimulus [174].”
Background
Point TransformerPreprint
Zhao, H., Jiang, L., Jia, J., Torr, P. H. S., & Koltun, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.09164 · Cited by 75
VideoLSTM Convolves, Attends and Flows for Action RecognitionPreprint
Li, Z., Gavves, E., Jain, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.01794 · Cited by 63
Learning what and where to attendPreprint
Linsley, D. A., Shiebler, D., Eberhardt, S., & Serre, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.08819 · Cited by 62
Single Shot Text Detector with Regional AttentionPreprint
He, P. L., Huang, W., He, T., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.00138 · Cited by 58 · cited 1×
“, image classification [5, 6], object detection [7, 8], semantic segmentation [9, 10], face recognition [11, 12], person re-identification [13, 14], action recognition [15, 16], few-shot learning [17, 18], medical image processing [19, 20], image generation [21, 22], pose estimation [23], super resolution [24, 25], 3D…”
Background
Attentional PointNet for 3D-Object Detection in Point Clouds
Paigwar, A., Erkent, Ö., Wolf, C., & Laugier, C. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00169 · Cited by 55 · cited 1×
“[97, 46, 139, 70, 128, 36, 11, 156] , [137, 143, 63, 161, 159, 6, 177, 80] , [67, 180, 10, 23, 24, 163, 155, 151] , [44, 49, 106, 64, 168, 18, 11, 36] , [48, 16, 169, 153, 174, 127, 53, 92] , [89, 21, 5, 134, 65, 171, 2, 109] , [45, 82, 157, 91, 100, 129, 146, 131] , [138, 85, 175, 76, 166, 133, 167, 172] , [41, 1, 17…”
Decoupled Spatial-Temporal Transformer for Video InpaintingPreprint
Liu, R. Z. Z., Deng, H., Huang, Y., Shi, X., Lu, L., Sun, W., Wang, X., Dai, J., & Li, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.06637 · Cited by 49 · cited 1×
“[130], [132], [133], [134], [135], [136], [137], [138], [139]”
SRM : A Style-based Recalibration Module for Convolutional Neural NetworksPreprint
Lee, H., Kim, H., & Nam, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.10829 · Cited by 42 · cited 8×
“[5], [37], [53], [54], [55], [56], [57], [58] [25], [59], [60] Spatial attention Generate attention mask across spatial domains and use it to select important spatial regions (e.”
BackgroundInfluential
FcaNet: Frequency Channel Attention NetworksPreprint
Qin, Z., Zhang, P., Wu, F. Q., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.11879 · Cited by 39 · cited 3×
“[57] rethought global information captured from the viewpoint of compression and analysed global average pooling in the frequency domain.”
Background
CF-SIS: Semantic-Instance Segmentation of 3D Point Clouds by Context Fusion with Self-Attention
Wen, X., Han, Z., Youk, G., & Liu, Y.-S. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413829 · Cited by 33 · 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]…”
GTA: Global Temporal Attention for Video Action Understanding
He, B., Yang, X., Wu, Z., Chen, H., Lim, S.-N., & Shrivastava, A. (2021) · British Machine Vision Conference (BMVC) · doi:10.5244/c.35.296 · Cited by 27
TAM: Temporal Adaptive Module for Video RecognitionPreprint
Liu, Z., Wang, L., Wu, W., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.06803 · Cited by 23 · cited 9×
“Combine local attention and global attention TAM [173] Arxiv2020 Action a) local: global spatial average pooling → 1D Convs, b) global: global spatial average pooling → MLP → adaptive convolution (A) (0, 1) S (II), (III)”
BackgroundInfluentialSelf-citation
VOLO: Vision Outlooker for Visual RecognitionPreprint
Yuan, L., Hou, Q., Jiang, Z., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.13112 · Cited by 22 · cited 2×
“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.”
Background
Can attention enable MLPs to catch up with CNNs?
Guo, M.-H., Liu, Z.-N., Mu, T., Liang, D., Martin, R. R., & Hu, S. (2021) · Computational Visual Media · doi:10.1007/s41095-021-0240-x · Cited by 20
Self-citation
READ: Reciprocal Attention Discriminator for Image-to-Video Re-identification
Shim, M., Ho, H.-I., Kim, J., & Wee, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58568-6_20 · Cited by 16 · cited 1×
“[130], [132], [133], [134], [135], [136], [137], [138], [139]”
GTA: Global Temporal Attention for Video Action UnderstandingPreprint
He, B., Yang, X., Wu, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.08510 · Cited by 16 · cited 1×
“[130], [132], [133], [134], [135], [136], [137], [138], [139]”

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

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
Visual attention network
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-citation
Large 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-citation
Beyond 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-citation
Convolutional 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].”

See all 2,566

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: Guo, Meng-Hao
Xu, Tian-Xing
Liu, Zheng-Ning
Jiang, Peng-Tao
Mu, Tai-Jiang
Zhang, Song-Hai
Cheng, Ming-Ming
Hu, Shi-Min
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
DOI: 10.1007/s41095-022-0271-y
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
Licence: cc-by
creativecommons.org/licenses/by/4.0 (tdm)
creativecommons.org/licenses/by/4.0 (vor)
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

Attention mechanisms in computer vision: A survey

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks