self-attention mechanism

Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring CVPR 2023 Efficient Mask Correction for Click-Based Interactive Image Segmentation CVPR 2023 Fine-grained Artificial Neurons in Audio-transformers for Disentangling Neural Auditory Encoding ACL 2023 Fine-Grained Position Helps Memorizing More, a Novel Music Compound Transformer Model with Feature Interaction Fusion AAAI 2023 GAFNet: A Global Fourier Self Attention Based Novel Network for Multi-Modal Downstream Tasks WACV 2023 HDFormer: High-order Directed Transformer for 3D Human Pose Estimation IJCAI 2023 HG-SL: Jointly Learning of Global and Local User Spreading Behavior for Fake News Early Detection AAAI 2023 Hierarchical Fusion for Online Multimodal Dialog Act Classification EMNLP 2023 High-Frequency Stereo Matching Network CVPR 2023 iColoriT: Towards Propagating Local Hints to the Right Region in Interactive Colorization by Leveraging Vision Transformer WACV 2023 Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering CVPR 2023 Lightweight Vision Transformer with Bidirectional Interaction NeurIPS 2023 Manifold-Preserving Transformers are Effective for Short-Long Range Encoding EMNLP 2023 Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals NeurIPS 2023 MixSynthFormer: A Transformer Encoder-like Structure with Mixed Synthetic Self-attention for Efficient Human Pose Estimation ICCV 2023 MSCFFN: A New FFN with Multi-Space Cross to Accelerate Transformer EMNLP 2023 OcTr: Octree-Based Transformer for 3D Object Detection CVPR 2023 Omni Aggregation Networks for Lightweight Image Super-Resolution CVPR 2023 On the Convergence of Encoder-only Shallow Transformers NeurIPS 2023 OutfitTransformer: Learning Outfit Representations for Fashion Recommendation WACV 2023 PESTO: A Post-User Fusion Network for Rumour Detection on Social Media ACL 2023 Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation AAAI 2023 Recurrent Attention Networks for Long-text Modeling ACL 2023 Robust Blind Watermarking Framework for Hybrid Networks Combining CNN and Transformer ACML 2023 Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer NeurIPS 2023