← Keywords

self-attention mechanism

350 papers

Explore in graph

Also known as

MHSA SACC CSA SA SAM

Co-occurring keywords

transformer architecture (1555) vision transformer (1091) attention mechanism (3975) transformer model (1988) neural network (6616) representation learning (6174) text classification (6776) graph neural network (3945) neural network optimization (1293) computational efficiency (358)

Papers

ClusterFormer: Neural Clustering Attention for Efficient and Effective Transformer ACL 2022
Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze? ACL 2022
Microphone Array Channel Combination Algorithms for Overlapped Speech Detection INTERSPEECH 2022
Beyond Fixation: Dynamic Window Visual Transformer CVPR 2022
Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection INTERSPEECH 2022
Lite Vision Transformer With Enhanced Self-Attention CVPR 2022
Syntax-guided Localized Self-attention by Constituency Syntactic Distance EMNLP 2022
Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT ACL 2022
A Hybrid Knowledge and Transformer-Based Model for Event Detection with Automatic Self-Attention Threshold, Layer and Head Selection EMNLP 2022
Composition, Attention, or Both? EMNLP 2022
Fine-Tuning Pre-trained Transformers into Decaying Fast Weights EMNLP 2022
Input-specific Attention Subnetworks for Adversarial Detection ACL 2022
Geometry-Contrastive Transformer for Generalized 3D Pose Transfer AAAI 2022
SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation NIPS 2022
Multiview Human Body Reconstruction from Uncalibrated Cameras NIPS 2022
Fast Vision Transformers with HiLo Attention NIPS 2022
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse NIPS 2022
Transformers from an Optimization Perspective NIPS 2022
CSWin Transformer: A General Vision Transformer Backbone With Cross-Shaped Windows CVPR 2022
Cross Aggregation Transformer for Image Restoration NIPS 2022
Geodesic Self-Attention for 3D Point Clouds NIPS 2022
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention NAACL 2022
Measuring the Mixing of Contextual Information in the Transformer EMNLP 2022
Structure-Aware Transformer for Graph Representation Learning ICML 2022
QUALIFIER: Question-Guided Self-Attentive Multimodal Fusion Network for Audio Visual Scene-Aware Dialog WACV 2022