Skip to content
conftrace_

scene understanding

871 papers

Papers

Point2Seq: Detecting 3D Objects As Sequences CVPR 2022 Point Cloud Pre-Training With Natural 3D Structures CVPR 2022 Rainy WCity: A Real Rainfall Dataset with Diverse Conditions for Semantic Driving Scene Understanding IJCAI 2022 Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer CoRL 2022 SBEVNet: End-to-End Deep Stereo Layout Estimation WACV 2022 Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models CoRL 2022 Shape From Polarization for Complex Scenes in the Wild CVPR 2022 Spatial Commonsense Graph for Object Localisation in Partial Scenes CVPR 2022 Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds IJCAI 2022 "The Pedestrian Next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping CVPR 2022 There’s a Time and Place for Reasoning Beyond the Image ACL 2022 TNS: Terrain Traversability Mapping and Navigation System for Autonomous Excavators RSS 2022 Towards Diverse and Natural Scene-Aware 3D Human Motion Synthesis CVPR 2022 Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints AAAI 2022 Vehicle Trajectory Prediction Works, but Not Everywhere CVPR 2022 ACDC: The Adverse Conditions Dataset With Correspondences for Semantic Driving Scene Understanding ICCV 2021 ADA-AT/DT: An Adversarial Approach for Cross-Domain and Cross-Task Knowledge Transfer WACV 2021 Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality CVPR 2021 Audio-Visual Floorplan Reconstruction ICCV 2021 AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection ICCV 2021 Back-Tracing Representative Points for Voting-Based 3D Object Detection in Point Clouds CVPR 2021 Benchmarking Unsupervised Object Representations for Video Sequences JMLR 2021 Bidirectional Projection Network for Cross Dimension Scene Understanding CVPR 2021 CASTing Your Model: Learning To Localize Improves Self-Supervised Representations CVPR 2021 CoCoNets: Continuous Contrastive 3D Scene Representations CVPR 2021