Core AI

DeepVideoMVS: Multi-View Stereo on Video With Recurrent Spatio-Temporal Fusion CVPR 2021 Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity IJCAI 2021 Densely Connected Multi-Dilated Convolutional Networks for Dense Prediction Tasks CVPR 2021 Depth-Aware Mirror Segmentation CVPR 2021 Differentiable Patch Selection for Image Recognition CVPR 2021 Differentiable SLAM-Net: Learning Particle SLAM for Visual Navigation CVPR 2021 Digital Gimbal: End-to-End Deep Image Stabilization With Learnable Exposure Times CVPR 2021 Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering EMNLP 2021 Discrete-Continuous Action Space Policy Gradient-Based Attention for Image-Text Matching CVPR 2021 Do Input Gradients Highlight Discriminative Features? NeurIPS 2021 Domain-Robust VQA With Diverse Datasets and Methods but No Target Labels CVPR 2021 DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-Scale Consistency CVPR 2021 Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration CVPR 2021 Dynamic Domain Adaptation for Efficient Inference CVPR 2021 Dynamic Metric Learning: Towards a Scalable Metric Space To Accommodate Multiple Semantic Scales CVPR 2021 Effectively Leveraging Attributes for Visual Similarity ICCV 2021 Efficient Certification of Spatial Robustness AAAI 2021 Efficient Generalized Spherical CNNs ICLR 2021 Efficient License Plate Recognition via Holistic Position Attention AAAI 2021 Efficiently Identifying Task Groupings for Multi-Task Learning NeurIPS 2021 Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding AAAI 2021 Efficient Training of Visual Transformers with Small Datasets NeurIPS 2021 Enhanced Regularizers for Attributional Robustness AAAI 2021 Enriching ImageNet With Human Similarity Judgments and Psychological Embeddings CVPR 2021 Ensembling With Deep Generative Views CVPR 2021