Techniques

Towards Defending against Adversarial Examples via Attack-Invariant Features ICML 2021 Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework CVPR 2021 Towards Extremely Compact RNNs for Video Recognition With Fully Decomposed Hierarchical Tucker Structure CVPR 2021 Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization ICCV 2021 Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter NAACL 2021 Towards Stable and Robust AdderNets NeurIPS 2021 Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration AAAI 2021 Towards Visually Explaining Video Understanding Networks With Perturbation WACV 2021 Tractable structured natural-gradient descent using local parameterizations ICML 2021 Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network AAAI 2021 Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs ICLR 2021 Training Graph Neural Networks with 1000 Layers ICML 2021 Training independent subnetworks for robust prediction ICLR 2021 Training Neural Networks with Fixed Sparse Masks NeurIPS 2021 Training with Quantization Noise for Extreme Model Compression ICLR 2021 TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph EMNLP 2021 Transformer Based End-to-End Mispronunciation Detection and Diagnosis Interspeech 2021 Transformer Interpretability Beyond Attention Visualization CVPR 2021 Transformer in Transformer NeurIPS 2021 Transformer Tracking CVPR 2021 TreeBERT: A tree-based pre-trained model for programming language UAI 2021 Tripartite Information Mining and Integration for Image Matting ICCV 2021 Triple M: A Practical Text-to-Speech Synthesis System with Multi-Guidance Attention and Multi-Band Multi-Time LPCNet Interspeech 2021 Truly Shift-Invariant Convolutional Neural Networks CVPR 2021 TUDa at WMT21: Sentence-Level Direct Assessment with Adapters EMNLP 2021