{"total":140,"rows":[{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087,"area":null},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982,"area":null},{"id":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315,"area":null},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2308.05736","title":"MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction","created":"2023-08-10","cited_by_count":193,"area":null},{"id":"2211.10581","title":"Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion","created":"2022-11-19","cited_by_count":162,"area":null},{"id":"2206.15398","title":"PolarFormer: Multi-camera 3D Object Detection with Polar Transformer","created":"2022-06-30","cited_by_count":147,"area":null},{"id":"2112.11010","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","created":"2021-12-21","cited_by_count":122,"area":null},{"id":"2308.02236","title":"FB-BEV: BEV Representation from Forward-Backward View Transformations","created":"2023-08-04","cited_by_count":98,"area":null},{"id":"2506.06659","title":"DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning","created":"2025-06-07","cited_by_count":94,"area":null},{"id":"2305.14018","title":"Sparse4D v2: Recurrent Temporal Fusion with Sparse Model","created":"2023-05-23","cited_by_count":93,"area":null},{"id":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75,"area":null},{"id":"2308.09616","title":"Far3D: Expanding the Horizon for Surround-view 3D Object Detection","created":"2023-08-18","cited_by_count":70,"area":null},{"id":"2311.11722","title":"Sparse4D v3: Advancing End-to-End 3D Detection and Tracking","created":"2023-11-20","cited_by_count":70,"area":null},{"id":"2506.06664","title":"Generalized Trajectory Scoring for End-to-end Multimodal Planning","created":"2025-06-07","cited_by_count":67,"area":null},{"id":"2302.03802","title":"Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking","created":"2023-02-07","cited_by_count":54,"area":null},{"id":"2206.10965","title":"Polar Parametrization for Vision-based Surround-View 3D Detection","created":"2022-06-22","cited_by_count":53,"area":null},{"id":"2401.06197","title":"Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications","created":"2024-01-11","cited_by_count":50,"area":null},{"id":"2304.00967","title":"Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction","created":"2023-04-03","cited_by_count":49,"area":null},{"id":"2401.09112","title":"Stream Query Denoising for Vectorized HD Map Construction","created":"2024-01-17","cited_by_count":43,"area":null},{"id":"2312.03341","title":"Online Vectorized HD Map Construction using Geometry","created":"2023-12-06","cited_by_count":42,"area":null},{"id":"2310.06753","title":"TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning","created":"2023-10-10","cited_by_count":41,"area":null},{"id":"2301.02364","title":"Object as Query: Lifting any 2D Object Detector to 3D Detection","created":"2023-01-06","cited_by_count":38,"area":null},{"id":"2402.03634","title":"Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection","created":"2024-02-06","cited_by_count":36,"area":null},{"id":"2312.01696","title":"BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection","created":"2023-12-04","cited_by_count":35,"area":null},{"id":"2403.07746","title":"Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception","created":"2024-03-12","cited_by_count":35,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"area":null},{"id":"2405.08909","title":"ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association","created":"2024-05-14","cited_by_count":33,"area":null},{"id":"2211.04800","title":"Designing Network Design Strategies Through Gradient Path Analysis","created":"2022-11-09","cited_by_count":32,"area":null},{"id":"2307.11477","title":"SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection","created":"2023-07-21","cited_by_count":30,"area":null},{"id":"2408.04804","title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","created":"2024-08-09","cited_by_count":29,"area":null},{"id":"2207.08536","title":"UniFusion: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View","created":"2022-07-18","cited_by_count":25,"area":null},{"id":"2308.01804","title":"QUEST: Query Stream for Practical Cooperative Perception","created":"2023-08-03","cited_by_count":23,"area":null},{"id":"2301.04467","title":"FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection","created":"2023-01-10","cited_by_count":21,"area":null},{"id":"2203.15331","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2212.05505","title":"Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection","created":"2022-12-11","cited_by_count":19,"area":null},{"id":"2307.13510","title":"HeightFormer: Explicit Height Modeling without Extra Data for Camera-only 3D Object Detection in Bird's Eye View","created":"2023-07-25","cited_by_count":19,"area":null},{"id":"2412.12725","title":"RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion","created":"2024-12-17","cited_by_count":19,"area":null},{"id":"2301.10766","title":"On the Adversarial Robustness of Camera-based 3D Object Detection","created":"2023-01-25","cited_by_count":15,"area":null},{"id":"2107.12679","title":"MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GAN","created":"2021-07-27","cited_by_count":14,"area":null},{"id":"2305.04609","title":"SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation","created":"2023-05-08","cited_by_count":13,"area":null},{"id":"2208.10895","title":"A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey","created":"2022-08-23","cited_by_count":12,"area":null},{"id":"2306.17602","title":"S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations","created":"2023-06-30","cited_by_count":12,"area":null},{"id":"2307.12274","title":"FDCT: Fast Depth Completion for Transparent Objects","created":"2023-07-23","cited_by_count":12,"area":null},{"id":"2403.06093","title":"Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors","created":"2024-03-10","cited_by_count":12,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2503.22436","title":"NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving","created":"2025-03-28","cited_by_count":12,"area":null},{"id":"2408.01471","title":"Enhancing Online Road Network Perception and Reasoning with Standard Definition Maps","created":"2024-08-01","cited_by_count":11,"area":null},{"id":"2409.01816","title":"GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection","created":"2024-09-03","cited_by_count":11,"area":null},{"id":"2209.13507","title":"CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection","created":"2022-09-27","cited_by_count":10,"area":null},{"id":"2306.09590","title":"The 1st-place Solution for CVPR 2023 OpenLane Topology in Autonomous Driving Challenge","created":"2023-06-16","cited_by_count":10,"area":null},{"id":"2106.05047","title":"Salient Object Ranking with Position-Preserved Attention","created":"2021-06-09","cited_by_count":9,"area":null},{"id":"2403.10353","title":"SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras","created":"2024-03-15","cited_by_count":9,"area":null},{"id":"2407.14923","title":"RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategies","created":"2024-07-20","cited_by_count":9,"area":null},{"id":"2408.06832","title":"FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving","created":"2024-08-13","cited_by_count":9,"area":null},{"id":"2410.19872","title":"Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2506.07725","title":"ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2510.10287","title":"Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking","created":"2025-10-11","cited_by_count":9,"area":null},{"id":"2203.00748","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","created":"2022-03-01","cited_by_count":8,"area":null},{"id":"2304.03105","title":"Geometric-aware Pretraining for Vision-centric 3D Object Detection","created":"2023-04-06","cited_by_count":8,"area":null},{"id":"2411.19860","title":"SpaRC: Sparse Radar-Camera Fusion for 3D Object Detection","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2108.04584","title":"UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2206.02424","title":"Slim-neck by GSConv: A lightweight-design for real-time detector architectures","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2301.05711","title":"OA-DET3D: Embedding Object Awareness as a General Plug-in for Multi-Camera 3D Object Detection","created":"2023-01-13","cited_by_count":7,"area":null},{"id":"2504.12643","title":"RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2510.10660","title":"Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mapping","created":"2025-10-12","cited_by_count":7,"area":null},{"id":"2402.18573","title":"Towards Unified 3D Object Detection via Algorithm and Data Unification","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2409.03460","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2307.16412","title":"RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection","created":"2023-07-31","cited_by_count":5,"area":null},{"id":"2402.11791","title":"SDGE: Stereo Guided Depth Estimation for 360$^\\circ$ Camera Sets","created":"2024-02-19","cited_by_count":5,"area":null},{"id":"2408.11196","title":"Robust Long-Range Perception Against Sensor Misalignment in Autonomous Vehicles","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2408.16200","title":"PolarBEVDet: Exploring Polar Representation for Multi-View 3D Object Detection in Bird's-Eye-View","created":"2024-08-29","cited_by_count":5,"area":null},{"id":"2504.04631","title":"Systematic Literature Review on Vehicular Collaborative Perception -- A Computer Vision Perspective","created":"2025-04-06","cited_by_count":5,"area":null},{"id":"2508.07089","title":"ForeSight: Multi-View Streaming Joint Object Detection and Trajectory Forecasting","created":"2025-08-09","cited_by_count":5,"area":null},{"id":"2110.10343","title":"EBJR: Energy-Based Joint Reasoning for Adaptive Inference","created":"2021-10-20","cited_by_count":4,"area":null},{"id":"2305.04170","title":"YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification","created":"2023-05-07","cited_by_count":4,"area":null},{"id":"2403.12562","title":"PePR: Performance Per Resource Unit as a Metric to Promote Small-Scale Deep Learning in Medical Image Analysis","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2407.15354","title":"Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detection","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2408.15388","title":"Panoptic Perception for Autonomous Driving: A Survey","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2410.23085","title":"S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2504.03258","title":"TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2103.15244","title":"Rethinking ResNets: Improved Stacking Strategies With High Order Schemes","created":"2021-03-28","cited_by_count":3,"area":null},{"id":"2206.08026","title":"DeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial Markers","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2407.13137","title":"OE-BevSeg: An Object Informed and Environment Aware Multimodal Framework for Bird's-eye-view Vehicle Semantic Segmentation","created":"2024-07-18","cited_by_count":3,"area":null},{"id":"2412.18884","title":"HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2504.18586","title":"A Decade of You Only Look Once (YOLO) for Object Detection: A Review","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2508.00744","title":"Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2509.13681","title":"FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Cameras","created":"2025-09-17","cited_by_count":3,"area":null},{"id":"2602.23172","title":"Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2109.12342","title":"TreeNet: A lightweight One-Shot Aggregation Convolutional Network","created":"2021-09-25","cited_by_count":2,"area":null},{"id":"2112.13809","title":"Improving Deep Image Matting via Local Smoothness Assumption","created":"2021-12-27","cited_by_count":2,"area":null},{"id":"2302.13002","title":"Introducing Depth into Transformer-based 3D Object Detection","created":"2023-02-25","cited_by_count":2,"area":null},{"id":"2305.01183","title":"Faster OreFSDet : A Lightweight and Effective Few-shot Object Detector for Ore Images","created":"2023-05-02","cited_by_count":2,"area":null},{"id":"2310.10353","title":"Multimodal Object Query Initialization for 3D Object Detection","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2406.02147","title":"S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2407.12491","title":"Hierarchical and Decoupled BEV Perception Learning Framework for Autonomous Driving","created":"2024-07-17","cited_by_count":2,"area":null},{"id":"2410.10267","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2411.06780","title":"SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2412.08763","title":"Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AI","created":"2024-12-11","cited_by_count":2,"area":null},{"id":"2504.19115","title":"Towards Latency-Aware 3D Streaming Perception for Autonomous Driving","created":"2025-04-27","cited_by_count":2,"area":null}],"next_cursor":"100"}