Scene Understanding

Relation-aware Instance Refinement for Weakly Supervised Visual Grounding CVPR 2021 ResT: An Efficient Transformer for Visual Recognition NeurIPS 2021 Rethinking 360deg Image Visual Attention Modelling With Unsupervised Learning. ICCV 2021 Revisiting Street-to-Aerial View Image Geo-Localization and Orientation Estimation WACV 2021 RGB-D Scene Recognition based on Object-Scene Relation (Student Abstract) AAAI 2021 Rich Context Aggregation With Reflection Prior for Glass Surface Detection CVPR 2021 Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting With Their Explanations CVPR 2021 Robust Instance Segmentation Through Reasoning About Multi-Object Occlusion CVPR 2021 Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments CVPR 2021 Scene-Aware Generative Network for Human Motion Synthesis CVPR 2021 Scene Context-Aware Salient Object Detection ICCV 2021 Scene Essence CVPR 2021 Scene-Intuitive Agent for Remote Embodied Visual Grounding CVPR 2021 Scene Text Retrieval via Joint Text Detection and Similarity Learning CVPR 2021 Segmentation-Grounded Scene Graph Generation ICCV 2021 Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views AAAI 2021 SemIE: Semantically-Aware Image Extrapolation ICCV 2021 Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus AAAI 2021 SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition NeurIPS 2021 Single-Shot Scene Reconstruction CoRL 2021 SketchAA: Abstract Representation for Abstract Sketches ICCV 2021 SOFT: Softmax-free Transformer with Linear Complexity NeurIPS 2021 Spatially-Varying Outdoor Lighting Estimation From Intrinsics CVPR 2021 Specificity-Preserving RGB-D Saliency Detection ICCV 2021 SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition AAAI 2021