Core AI

There and Back Again: Revisiting Backpropagation Saliency Methods CVPR 2020 They Are Not All Alike: Answering Different Spatial Questions Requires Different Grounding Strategies EMNLP 2020 Towards Deeper Graph Neural Networks with Differentiable Group Normalization NeurIPS 2020 Towards Embodied Scene Description RSS 2020 Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional Networks CVPR 2020 Towards Large Yet Imperceptible Adversarial Image Perturbations With Perceptual Color Distance CVPR 2020 Towards Learning Affine-Invariant Representations via Data-Efficient CNNs WACV 2020 Towards Robust Image Classification Using Sequential Attention Models CVPR 2020 Towards Visually Explaining Variational Autoencoders CVPR 2020 TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model CVPR 2020 UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders CVPR 2020 Understanding Adversarial Examples From the Mutual Influence of Images and Perturbations CVPR 2020 Unified Dynamic Convolutional Network for Super-Resolution With Variational Degradations CVPR 2020 Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs CVPR 2020 Unsupervised Learning of Dense Visual Representations NeurIPS 2020 Unsupervised Representation Learning for Gaze Estimation CVPR 2020 VD-BERT: A Unified Vision and Dialog Transformer with BERT EMNLP 2020 ViBE: Dressing for Diverse Body Shapes CVPR 2020 Video Object Grounding Using Semantic Roles in Language Description CVPR 2020 Video Panoptic Segmentation CVPR 2020 ViLBERTScore: Evaluating Image Caption Using Vision-and-Language BERT EMNLP 2020 Visual Chirality CVPR 2020 Visual Commonsense R-CNN CVPR 2020 Visually Grounded Continual Learning of Compositional Phrases EMNLP 2020 Visually Imbalanced Stereo Matching CVPR 2020