{"list":"other","total":98,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2206.10092","title":"BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection","created":"2022-06-21","cited_by_count":572},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"1907.06038","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","created":"2019-07-13","cited_by_count":252},{"id":"2108.06417","title":"Is Pseudo-Lidar needed for Monocular 3D Object detection?","created":"2021-08-13","cited_by_count":249},{"id":"2104.02323","title":"Objects are Different: Flexible Monocular 3D Object Detection","created":"2021-04-06","cited_by_count":185},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2107.13774","title":"Geometry Uncertainty Projection Network for Monocular 3D Object Detection","created":"2021-07-29","cited_by_count":156},{"id":"2003.00504","title":"MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships","created":"2020-03-01","cited_by_count":153},{"id":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140},{"id":"1903.09254","title":"CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification","created":"2019-03-21","cited_by_count":119},{"id":"2007.09548","title":"Kinematic 3D Object Detection in Monocular Video","created":"2020-07-19","cited_by_count":116},{"id":"2008.04582","title":"Rethinking Pseudo-LiDAR Representation","created":"2020-08-11","cited_by_count":109},{"id":"2203.10981","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","created":"2022-03-21","cited_by_count":109},{"id":"2307.04370","title":"Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey","created":"2023-07-10","cited_by_count":103},{"id":"2407.17140","title":"RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer","created":"2024-07-24","cited_by_count":91},{"id":"2108.11127","title":"AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection","created":"2021-08-25","cited_by_count":87},{"id":"2203.13310","title":"MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection","created":"2022-03-24","cited_by_count":86},{"id":"2103.12605","title":"MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation","created":"2021-03-23","cited_by_count":82},{"id":"2203.13608","title":"Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task","created":"2022-03-25","cited_by_count":81},{"id":"1805.11327","title":"Lightweight Probabilistic Deep Networks","created":"2018-05-29","cited_by_count":77},{"id":"1811.10742","title":"Joint Monocular 3D Vehicle Detection and Tracking","created":"2018-11-26","cited_by_count":77},{"id":"2303.08498","title":"BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection","created":"2023-03-15","cited_by_count":75},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75},{"id":"2410.13842","title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","created":"2024-10-17","cited_by_count":74},{"id":"2106.15796","title":"Monocular 3D Object Detection: An Extrinsic Parameter Free Approach","created":"2021-06-30","cited_by_count":69},{"id":"2201.10830","title":"MonoDistill: Learning Spatial Features for Monocular 3D Object Detection","created":"2022-01-26","cited_by_count":68},{"id":"2112.04628","title":"Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection","created":"2021-12-09","cited_by_count":67},{"id":"2506.17733","title":"YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception","created":"2025-06-21","cited_by_count":58},{"id":"2108.05793","title":"Progressive Coordinate Transforms for Monocular 3D Object Detection","created":"2021-08-12","cited_by_count":52},{"id":"2503.12067","title":"A Comprehensive Survey on Knowledge Distillation","created":"2025-03-15","cited_by_count":51},{"id":"2207.10758","title":"DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection","created":"2022-07-21","cited_by_count":48},{"id":"2211.07171","title":"Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection","created":"2022-11-14","cited_by_count":48},{"id":"2205.09373","title":"Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection","created":"2022-05-19","cited_by_count":46},{"id":"2207.08531","title":"DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection","created":"2022-07-18","cited_by_count":39},{"id":"2404.03181","title":"MonoCD: Monocular 3D Object Detection with Complementary Depths","created":"2024-04-04","cited_by_count":39},{"id":"2305.15694","title":"Learning Occupancy for Monocular 3D Object Detection","created":"2023-05-25","cited_by_count":36},{"id":"2406.03459","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","created":"2024-06-05","cited_by_count":36},{"id":"2308.09421","title":"MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection","created":"2023-08-18","cited_by_count":33},{"id":"2409.08475","title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","created":"2024-09-13","cited_by_count":32},{"id":"2212.01247","title":"CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion","created":"2022-12-02","cited_by_count":31},{"id":"2203.02112","title":"Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving","created":"2022-03-04","cited_by_count":30},{"id":"2203.08563","title":"MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection","created":"2022-03-16","cited_by_count":30},{"id":"2208.05768","title":"MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition","created":"2022-08-11","cited_by_count":30},{"id":"2207.10047","title":"Densely Constrained Depth Estimator for Monocular 3D Object Detection","created":"2022-07-20","cited_by_count":27},{"id":"2204.00754","title":"Homography Loss for Monocular 3D Object Detection","created":"2022-04-02","cited_by_count":24},{"id":"2211.01142","title":"OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection","created":"2022-11-02","cited_by_count":24},{"id":"2204.11590","title":"Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training","created":"2022-04-25","cited_by_count":22},{"id":"2410.19590","title":"MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors","created":"2024-10-25","cited_by_count":22},{"id":"2302.10549","title":"MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts","created":"2023-02-21","cited_by_count":21},{"id":"2312.14474","title":"MonoLSS: Learnable Sample Selection For Monocular 3D Detection","created":"2023-12-22","cited_by_count":19},{"id":"2303.13018","title":"MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer","created":"2023-03-23","cited_by_count":18},{"id":"2310.02815","title":"CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity","created":"2023-10-04","cited_by_count":18},{"id":"2405.07696","title":"MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders","created":"2024-05-13","cited_by_count":16},{"id":"2408.11958","title":"CARLA Drone: Monocular 3D Object Detection from a Different Perspective","created":"2024-08-21","cited_by_count":12},{"id":"2403.17387","title":"Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection","created":"2024-03-26","cited_by_count":11},{"id":"2507.23567","title":"3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection","created":"2025-07-31","cited_by_count":11},{"id":"2404.04910","title":"MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection","created":"2024-04-07","cited_by_count":10},{"id":"2305.07270","title":"SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection","created":"2023-05-12","cited_by_count":9},{"id":"2405.09883","title":"RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception","created":"2024-05-16","cited_by_count":9},{"id":"2304.01289","title":"Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver","created":"2023-04-03","cited_by_count":8},{"id":"2401.01075","title":"Depth-discriminative Metric Learning for Monocular 3D Object Detection","created":"2024-01-02","cited_by_count":8},{"id":"2211.16779","title":"Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection","created":"2022-11-30","cited_by_count":7},{"id":"2504.17371","title":"Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset","created":"2025-04-24","cited_by_count":7},{"id":"2205.11664","title":"Towards Model Generalization for Monocular 3D Object Detection","created":"2022-05-23","cited_by_count":6},{"id":"2508.02067","title":"YOLOv1 to YOLOv11: A Comprehensive Survey of Real-Time Object Detection Innovations and Challenges","created":"2025-08-04","cited_by_count":5},{"id":"2504.11014","title":"GATE3D: Generalized Attention-based Task-synergized Estimation in 3D*","created":"2025-04-15","cited_by_count":4},{"id":"2401.15319","title":"You Only Look Bottom-Up for Monocular 3D Object Detection","created":"2024-01-27","cited_by_count":3},{"id":"2404.05280","title":"MOSE: Boosting Vision-based Roadside 3D Object Detection with Scene Cues","created":"2024-04-08","cited_by_count":3},{"id":"2503.13743","title":"MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models","created":"2025-03-17","cited_by_count":2},{"id":"2504.16443","title":"Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Any Convex Parametric Shapes","created":"2025-04-23","cited_by_count":2},{"id":"2511.19301","title":"IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection","created":"2025-11-24","cited_by_count":2},{"id":"2408.00438","title":"MonoMM: A Multi-scale Mamba-Enhanced Network for Real-time Monocular 3D Object Detection","created":"2024-08-01","cited_by_count":1}],"next_cursor":null}