Scene Understanding

Bidirectional Projection Network for Cross Dimension Scene Understanding CVPR 2021 CANet: A Context-Aware Network for Shadow Removal ICCV 2021 CASTing Your Model: Learning To Localize Improves Self-Supervised Representations CVPR 2021 CATs: Cost Aggregation Transformers for Visual Correspondence NeurIPS 2021 Classification by Attention: Scene Graph Classification with Prior Knowledge AAAI 2021 Co-Attention for Conditioned Image Matching CVPR 2021 CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation IJCAI 2021 Context-Aware Scene Graph Generation With Seq2Seq Transformers ICCV 2021 Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting CVPR 2021 Cross-view Geo-localization with Layer-to-Layer Transformer NeurIPS 2021 CT-Net: Complementary Transfering Network for Garment Transfer With Arbitrary Geometric Changes CVPR 2021 Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images CVPR 2021 DeepGaze IIE: Calibrated Prediction in and Out-of-Domain for State-of-the-Art Saliency Modeling ICCV 2021 DeepPanoContext: Panoramic 3D Scene Understanding With Holistic Scene Context Graph and Relation-Based Optimization ICCV 2021 Deep Texture Recognition via Exploiting Cross-Layer Statistical Self-Similarity CVPR 2021 DenserNet: Weakly Supervised Visual Localization Using Multi-Scale Feature Aggregation AAAI 2021 Detecting Human-Object Interaction With Mixed Supervision WACV 2021 Detecting Persuasive Atypicality by Modeling Contextual Compatibility ICCV 2021 DI-Fusion: Online Implicit 3D Reconstruction With Deep Priors CVPR 2021 Disentangled Contour Learning for Quadrilateral Text Detection WACV 2021 Disentangled Motif-aware Graph Learning for Phrase Grounding AAAI 2021 DOLG: Single-Stage Image Retrieval With Deep Orthogonal Fusion of Local and Global Features ICCV 2021 Domain-Robust VQA With Diverse Datasets and Methods but No Target Labels CVPR 2021 Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval IJCAI 2021 Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language NeurIPS 2021