Architectures

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization NeurIPS 2021 TransFER: Learning Relation-Aware Facial Expression Representations With Transformers ICCV 2021 Transfer Learning with Shallow Decoders: BSC at WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task EMNLP 2021 Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it? EMNLP 2021 TransForensics: Image Forgery Localization With Dense Self-Attention ICCV 2021 Transformer-Based Acoustic Modeling for Streaming Speech Synthesis Interspeech 2021 Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation Interspeech 2021 Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction ICCV 2021 Transformer-Based Direct Hidden Markov Model for Machine Translation ACL 2021 Transformer-Based Dual Relation Graph for Multi-Label Image Recognition ICCV 2021 Transformer Based End-to-End Mispronunciation Detection and Diagnosis Interspeech 2021 Transformer-based Lexically Constrained Headline Generation EMNLP 2021 Transformer-based Multi-Task Learning for Adverse Effect Mention Analysis in Tweets NAACL 2021 Transformer-based Screenplay Summarization Using Augmented Learning Representation with Dialogue Information NAACL 2021 Transformer Feed-Forward Layers Are Key-Value Memories EMNLP 2021 TransformerFusion: Monocular RGB Scene Reconstruction using Transformers NeurIPS 2021 Transformer Interpretability Beyond Attention Visualization CVPR 2021 Transformer in Transformer NeurIPS 2021 Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking CVPR 2021 Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence EMNLP 2021 Transformer protein language models are unsupervised structure learners ICLR 2021 Transformers Generalize DeepSets and Can be Extended to Graphs & Hypergraphs NeurIPS 2021 Transformer Tracking CVPR 2021 Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors NAACL 2021 TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up NeurIPS 2021