conftrace_

multi-head self-attention

37 papers

Explore in graph

Also known as

MHSA

Co-occurring keywords

attention mechanism (4001) multi-head attention (172) transformer architecture (1560) neural machine translation (2310) attention head (146) feature extraction (1580) self-attention network (56) speech emotion recognition (270) neural network (6616) image-text retrieval (112)

Papers

TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models ICCV 2025
Understanding and Patching Compositional Reasoning in LLMs ACL 2024
Towards Speech Classification from Acoustic and Vocal Tract data in Real-time MRI INTERSPEECH 2024
Revisiting the Integration of Convolution and Attention for Vision Backbone NIPS 2024
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers NIPS 2024
Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models EMNLP 2024
Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection INTERSPEECH 2024
EIT: Enhanced Interactive Transformer ACL 2024
Exploring Self-Distillation Based Relational Reasoning Training for Document-Level Relation Extraction AAAI 2023
Scratching Visual Transformer's Back with Uniform Attention ICCV 2023
OctFormer: Efficient Octree-Based Transformer for Point Cloud Compression with Local Enhancement AAAI 2023
Branch-ECAPA-TDNN: A Parallel Branch Architecture to Capture Local and Global Features for Speaker Verification INTERSPEECH 2023
Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis MIDL 2022
Parametric Visual Program Induction with Function Modularization ICML 2022
Peripheral Vision Transformer NIPS 2022
Vision Shared and Representation Isolated Network for Person Search IJCAI 2022
Improving Speech Emotion Recognition Through Focus and Calibration Attention Mechanisms INTERSPEECH 2022
Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation EMNLP 2022
Shape From Polarization for Complex Scenes in the Wild CVPR 2022
Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction NAACL 2021
Detect Profane Language in Streaming Services to Protect Young Audiences ACL 2021
Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems NIPS 2021
Explainable Detection of Sarcasm in Social Media EACL 2021
Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation EMNLP 2021
MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding WACV 2020