{"total":122,"rows":[{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"area":null},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177,"area":null},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132,"area":null},{"id":"2110.02210","title":"Mix3D: Out-of-Context Data Augmentation for 3D Scenes","created":"2021-10-05","cited_by_count":126,"area":null},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108,"area":null},{"id":"2108.07058","title":"FaPN: Feature-aligned Pyramid Network for Dense Image Prediction","created":"2021-08-16","cited_by_count":81,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2101.06543","title":"GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving","created":"2021-01-16","cited_by_count":75,"area":null},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"area":null},{"id":"2103.17202","title":"GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection","created":"2021-03-31","cited_by_count":66,"area":null},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66,"area":null},{"id":"2103.13318","title":"Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types","created":"2021-03-24","cited_by_count":54,"area":null},{"id":"2111.12780","title":"Transferability Estimation using Bhattacharyya Class Separability","created":"2021-11-24","cited_by_count":54,"area":null},{"id":"2206.06363","title":"Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation","created":"2022-06-13","cited_by_count":54,"area":null},{"id":"2103.04233","title":"GANav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments","created":"2021-03-07","cited_by_count":51,"area":null},{"id":"2207.10758","title":"DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection","created":"2022-07-21","cited_by_count":48,"area":null},{"id":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","cited_by_count":41,"area":null},{"id":"2208.09480","title":"Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion","created":"2022-08-19","cited_by_count":35,"area":null},{"id":"2403.10075","title":"A survey of synthetic data augmentation methods in computer vision","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2103.16694","title":"Geometric Unsupervised Domain Adaptation for Semantic Segmentation","created":"2021-03-30","cited_by_count":33,"area":null},{"id":"2204.01403","title":"How stable are Transferability Metrics evaluations?","created":"2022-04-04","cited_by_count":30,"area":null},{"id":"2402.04376","title":"Scaling laws for learning with real and surrogate data","created":"2024-02-06","cited_by_count":27,"area":null},{"id":"2210.04458","title":"OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2304.02163","title":"GINA-3D: Learning to Generate Implicit Neural Assets in the Wild","created":"2023-04-04","cited_by_count":25,"area":null},{"id":"2305.16220","title":"On the Robustness of Segment Anything","created":"2023-05-25","cited_by_count":25,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2111.13011","title":"Transferability Metrics for Selecting Source Model Ensembles","created":"2021-11-25","cited_by_count":24,"area":null},{"id":"2103.02433","title":"Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms","created":"2021-03-03","cited_by_count":23,"area":null},{"id":"2204.13635","title":"SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion","created":"2022-04-28","cited_by_count":23,"area":null},{"id":"2212.02400","title":"Location-Aware Self-Supervised Transformers for Semantic Segmentation","created":"2022-12-05","cited_by_count":20,"area":null},{"id":"2404.13816","title":"Neural Radiance Field in Autonomous Driving: A Survey","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2504.21682","title":"Visual Text Processing: A Comprehensive Review and Unified Evaluation","created":"2025-04-30","cited_by_count":19,"area":null},{"id":"2103.13109","title":"A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios","created":"2021-03-24","cited_by_count":18,"area":null},{"id":"2401.10227","title":"A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting","created":"2024-01-18","cited_by_count":18,"area":"diffusion"},{"id":"2111.12137","title":"Learning Interactive Driving Policies via Data-driven Simulation","created":"2021-11-23","cited_by_count":17,"area":"driving"},{"id":"2501.13087","title":"Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation","created":"2025-01-22","cited_by_count":17,"area":"diffusion"},{"id":"2110.00464","title":"MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation","created":"2021-10-01","cited_by_count":16,"area":null},{"id":"2403.11496","title":"MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception","created":"2024-03-18","cited_by_count":16,"area":null},{"id":"2304.03526","title":"Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field","created":"2023-04-07","cited_by_count":15,"area":null},{"id":"2312.05277","title":"3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection","created":"2023-12-08","cited_by_count":15,"area":null},{"id":"2204.11642","title":"Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset","created":"2022-04-25","cited_by_count":13,"area":null},{"id":"2402.04519","title":"BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2110.08664","title":"Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review","created":"2021-10-16","cited_by_count":12,"area":null},{"id":"2204.08563","title":"Cylin-Painting: Seamless {360\\textdegree} Panoramic Image Outpainting and Beyond","created":"2022-04-18","cited_by_count":12,"area":null},{"id":"2403.20318","title":"SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects","created":"2024-03-29","cited_by_count":12,"area":null},{"id":"2409.11205","title":"HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios","created":"2024-09-17","cited_by_count":12,"area":null},{"id":"2107.09858","title":"Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation","created":"2021-07-21","cited_by_count":11,"area":null},{"id":"2412.01646","title":"Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2204.07414","title":"SOTVerse: A User-defined Task Space of Single Object Tracking","created":"2022-04-15","cited_by_count":10,"area":null},{"id":"2211.14054","title":"CAD2Render: A Modular Toolkit for GPU-accelerated Photorealistic Synthetic Data Generation for the Manufacturing Industry","created":"2022-11-25","cited_by_count":10,"area":null},{"id":"2407.21631","title":"RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion","created":"2024-07-31","cited_by_count":10,"area":null},{"id":"2207.09045","title":"ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation","created":"2022-07-19","cited_by_count":9,"area":null},{"id":"2301.08898","title":"Recurrent Generic Contour-based Instance Segmentation with Progressive Learning","created":"2023-01-21","cited_by_count":9,"area":null},{"id":"2212.05315","title":"Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation","created":"2022-12-10","cited_by_count":8,"area":null},{"id":"2308.13331","title":"A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentation","created":"2023-08-25","cited_by_count":8,"area":null},{"id":"2309.16127","title":"Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation","created":"2023-09-28","cited_by_count":8,"area":null},{"id":"2402.03082","title":"Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2402.18918","title":"SNE-RoadSegV2: Advancing Heterogeneous Feature Fusion and Fallibility Awareness for Freespace Detection","created":"2024-02-29","cited_by_count":8,"area":null},{"id":"2109.13432","title":"Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency","created":"2021-09-28","cited_by_count":7,"area":null},{"id":"2303.01899","title":"Quantifying the LiDAR Sim-to-Real Domain Shift: A Detailed Investigation Using Object Detectors and Analyzing Point Clouds at Target-Level","created":"2023-03-03","cited_by_count":7,"area":null},{"id":"2308.09065","title":"Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression","created":"2023-08-17","cited_by_count":7,"area":null},{"id":"2506.20601","title":"Video Perception Models for 3D Scene Synthesis","created":"2025-06-25","cited_by_count":7,"area":null},{"id":"2108.08923","title":"CenterPoly: real-time instance segmentation using bounding polygons","created":"2021-08-19","cited_by_count":6,"area":null},{"id":"2111.12927","title":"Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion","created":"2021-11-25","cited_by_count":6,"area":null},{"id":"2408.13175","title":"Identifying Crucial Objects in Blind and Low-Vision Individuals' Navigation","created":"2024-08-23","cited_by_count":6,"area":null},{"id":"2411.19274","title":"On-chip Hyperspectral Image Segmentation with Fully Convolutional Networks for Scene Understanding in Autonomous Driving","created":"2024-11-28","cited_by_count":6,"area":null},{"id":"2508.11185","title":"CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector","created":"2025-08-15","cited_by_count":6,"area":null},{"id":"2105.00114","title":"Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames","created":"2021-04-30","cited_by_count":5,"area":null},{"id":"2112.06596","title":"SAC-GAN: Structure-Aware Image Composition","created":"2021-12-13","cited_by_count":5,"area":null},{"id":"2311.04617","title":"Image Patch-Matching with Graph-Based Learning in Street Scenes","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2407.16777","title":"A Dataset for Crucial Object Recognition in Blind and Low-Vision Individuals' Navigation","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2106.13963","title":"OffRoadTranSeg: Semi-Supervised Segmentation using Transformers on OffRoad environments","created":"2021-06-26","cited_by_count":4,"area":null},{"id":"2203.01087","title":"Vision-based Large-scale 3D Semantic Mapping for Autonomous Driving Applications","created":"2022-03-02","cited_by_count":4,"area":null},{"id":"2403.13804","title":"Learning from Synthetic Data for Visual Grounding","created":"2024-03-20","cited_by_count":4,"area":"synth"},{"id":"2501.12269","title":"Benchmarking Image Perturbations for Testing Automated Driving Assistance Systems","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2409.17376","title":"Optical Lens Attack on Deep Learning Based Monocular Depth Estimation","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2103.05902","title":"Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss","created":"2021-03-10","cited_by_count":2,"area":null},{"id":"2208.07943","title":"TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments","created":"2022-08-16","cited_by_count":2,"area":null},{"id":"2303.12743","title":"DR.CPO: Diversified and Realistic 3D Augmentation via Iterative Construction, Random Placement, and HPR Occlusion","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2305.19421","title":"Data and Knowledge for Overtaking Scenarios in Autonomous Driving","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2308.02790","title":"Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation","created":"2023-08-05","cited_by_count":2,"area":"distill"},{"id":"2309.13438","title":"Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms","created":"2023-09-23","cited_by_count":2,"area":null},{"id":"2404.15256","title":"TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimation","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2405.14278","title":"SCMix: Stochastic Compound Mixing for Open Compound Domain Adaptation in Semantic Segmentation","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2511.11882","title":"Lacking Data? No worries! How synthetic images can alleviate image scarcity in wildlife surveys: a case study with muskox (Ovibos moschatus)","created":"2025-11-14","cited_by_count":2,"area":null},{"id":"2202.01421","title":"Characterization of Semantic Segmentation Models on Mobile Platforms for Self-Navigation in Disaster-Struck Zones","created":"2022-02-03","cited_by_count":1,"area":null},{"id":"2209.08685","title":"Meta-simulation for the Automated Design of Synthetic Overhead Imagery","created":"2022-09-19","cited_by_count":1,"area":null},{"id":"2311.15415","title":"GAN-Based LiDAR Intensity Simulation","created":"2023-11-26","cited_by_count":1,"area":null},{"id":"2402.12551","title":"Landmark-based Localization using Stereo Vision and Deep Learning in GPS-Denied Battlefield Environment","created":"2024-02-19","cited_by_count":1,"area":null},{"id":"2402.17653","title":"Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2407.06513","title":"Computer vision tasks for intelligent aerospace missions: An overview","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2411.00192","title":"Optical Lens Attack on Monocular Depth Estimation for Autonomous Driving","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2501.02143","title":"SafeAug: Safety-Critical Driving Data Augmentation from Naturalistic Datasets","created":"2025-01-03","cited_by_count":1,"area":null},{"id":"2510.04770","title":"Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2510.09171","title":"Instance-Level Generation for Representation Learning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2606.20110","title":"FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model","created":"2026-06-18","cited_by_count":1,"area":"diffusion"},{"id":"2103.16758","title":"Evaluation of Multimodal Semantic Segmentation using RGB-D Data","created":"2021-03-31","cited_by_count":0,"area":null},{"id":"2106.15409","title":"Efficient Realistic Data Generation Framework leveraging Deep Learning-based Human Digitization","created":"2021-06-28","cited_by_count":0,"area":null},{"id":"2109.10083","title":"PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation","created":"2021-09-21","cited_by_count":0,"area":null}],"next_cursor":"100"}