← Techniques
Deep Learning › Techniques ›

Attention Mechanism

117 directly classified papers

Papers per year

Papers

Self-Supervised Implicit Glyph Attention for Text Recognition CVPR 2023
Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers CVPR 2023
Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention EMNLP 2023
Improving Span Representation by Efficient Span-Level Attention EMNLP 2023
Syntax Matters: Towards Spoken Language Understanding via Syntax-Aware Attention EMNLP 2023
Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning INTERSPEECH 2022
Bi-Directional Object-Context Prioritization Learning for Saliency Ranking CVPR 2022
DisARM: Displacement Aware Relation Module for 3D Detection CVPR 2022
FourierFormer: Transformer Meets Generalized Fourier Integral Theorem NIPS 2022
Fast Vision Transformers with HiLo Attention NIPS 2022
Partial Class Activation Attention for Semantic Segmentation CVPR 2022
Long-range Sequence Modeling with Predictable Sparse Attention ACL 2022
MixFormer: Mixing Features Across Windows and Dimensions CVPR 2022
Dynamic Head: Unifying Object Detection Heads With Attentions CVPR 2021
Gaussian Context Transformer CVPR 2021
EDNet: Efficient Disparity Estimation With Cost Volume Combination and Attention-Based Spatial Residual CVPR 2021
Understanding How Encoder-Decoder Architectures Attend NIPS 2021
Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention AAAI 2021
Context-Aware Interaction Network for Question Matching EMNLP 2021
Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience EMNLP 2021
On Scalar Embedding of Relative Positions in Attention Models AAAI 2021
Self-Supervised Attention-Aware Reinforcement Learning AAAI 2021
Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification AAAI 2021
Attention Calibration for Transformer in Neural Machine Translation ACL 2021
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification ACL 2021