Attention mechanism in neural networks: where it comes and where it goes

D Soydaner - Neural Computing and Applications, 2022 - Springer
A long time ago in the machine learning literature, the idea of incorporating a mechanism
inspired by the human visual system into neural networks was introduced. This idea is …

Attention, please! A survey of neural attention models in deep learning

A de Santana Correia, EL Colombini - Artificial Intelligence Review, 2022 - Springer
In humans, Attention is a core property of all perceptual and cognitive operations. Given our
limited ability to process competing sources, attention mechanisms select, modulate, and …

Normalized and geometry-aware self-attention network for image captioning

L Guo, J Liu, X Zhu, P Yao, S Lu… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Self-attention (SA) network has shown profound value in image captioning. In this paper, we
improve SA from two aspects to promote the performance of image captioning. First, we …

RKT: relation-aware self-attention for knowledge tracing

S Pandey, J Srivastava - Proceedings of the 29th ACM international …, 2020 - dl.acm.org
The world has transitioned into a new phase of online learning in response to the recent
Covid19 pandemic. Now more than ever, it has become paramount to push the limits of …

CAAN: Context-aware attention network for visual question answering

C Chen, D Han, CC Chang - Pattern Recognition, 2022 - Elsevier
Understanding multimodal information is the key to visual question answering (VQA) tasks.
Most existing approaches use attention mechanisms to acquire fine-grained information …

Atloc: Attention guided camera localization

B Wang, C Chen, CX Lu, P Zhao, N Trigoni… - Proceedings of the …, 2020 - ojs.aaai.org
Deep learning has achieved impressive results in camera localization, but current single-
image techniques typically suffer from a lack of robustness, leading to large outliers. To …

Context-guided bert for targeted aspect-based sentiment analysis

Z Wu, DC Ong - Proceedings of the AAAI conference on artificial …, 2021 - ojs.aaai.org
Aspect-based sentiment analysis (ABSA) and Targeted ASBA (TABSA) allow finer-grained
inferences about sentiment to be drawn from the same text, depending on context. For …

Convolutional self-attention networks

B Yang, L Wang, D Wong, LS Chao, Z Tu - arxiv preprint arxiv …, 2019 - arxiv.org
Self-attention networks (SANs) have drawn increasing interest due to their high
parallelization in computation and flexibility in modeling dependencies. SANs can be further …

Modeling intra-relation in math word problems with different functional multi-head attentions

J Li, L Wang, J Zhang, Y Wang, BT Dai… - Proceedings of the 57th …, 2019 - aclanthology.org
Several deep learning models have been proposed for solving math word problems (MWPs)
automatically. Although these models have the ability to capture features without manual …

Spatial-temporal convolutional graph attention networks for citywide traffic flow forecasting

X Zhang, C Huang, Y Xu, L **a - Proceedings of the 29th ACM …, 2020 - dl.acm.org
Traffic flow prediction plays an important role in many spatial-temporal data applications, eg,
traffic management and urban planning. Various deep learning techniques are developed to …