Scene Understanding

TransforMatcher: Match-to-Match Attention for Semantic Correspondence CVPR 2022 TransGeo: Transformer Is All You Need for Cross-View Image Geo-Localization CVPR 2022 Unsupervised Homography Estimation With Coplanarity-Aware GAN CVPR 2022 Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints AAAI 2022 Virtual Correspondence: Humans as a Cue for Extreme-View Geometry CVPR 2022 Vision Transformers provably learn spatial structure NeurIPS 2022 Visual Commonsense in Pretrained Unimodal and Multimodal Models NAACL 2022 Visual correspondence-based explanations improve AI robustness and human-AI team accuracy NeurIPS 2022 Visual Correspondence Hallucination ICLR 2022 Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows COLING 2022 Visual Semantic Parsing: From Images to Abstract Meaning Representation CoNLL 2022 Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition AAAI 2022 Weakly but Deeply Supervised Occlusion-Reasoned Parametric Road Layouts CVPR 2022 What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning IJCAI 2022 When does dough become a bagel? Analyzing the remaining mistakes on ImageNet NeurIPS 2022 3D-FRONT: 3D Furnished Rooms With layOuts and semaNTics ICCV 2021 3DP3: 3D Scene Perception via Probabilistic Programming NeurIPS 2021 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds ICCV 2021 Adaptive-Attentive Geolocalization From Few Queries: A Hybrid Approach WACV 2021 AI-Empowered Decision Support for COVID-19 Social Distancing AAAI 2021 Attentional Pyramid Pooling of Salient Visual Residuals for Place Recognition ICCV 2021 Audio-Visual Floorplan Reconstruction ICCV 2021 Back to the Feature: Learning Robust Camera Localization From Pixels To Pose CVPR 2021 Bayesian Deep Graph Matching for Correspondence Identification in Collaborative Perception RSS 2021 Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable Instances AISTATS 2021