{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"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":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"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":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"id":"2206.10092","title":"BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection","created":"2022-06-21","cited_by_count":572},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"1803.03243","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","created":"2018-03-08","cited_by_count":443},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"1708.07819","title":"Semantic Foggy Scene Understanding with Synthetic Data","created":"2017-08-25","cited_by_count":403},{"id":"2206.01256","title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","created":"2022-06-02","cited_by_count":352},{"id":"1908.09492","title":"Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection","created":"2019-08-26","cited_by_count":350},{"id":"2203.17054","title":"BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection","created":"2022-03-31","cited_by_count":341},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"1812.04798","title":"Strong-Weak Distribution Alignment for Adaptive Object Detection","created":"2018-12-12","cited_by_count":270},{"id":"1907.06038","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","created":"2019-07-13","cited_by_count":252},{"id":"1905.12365","title":"Disentangling Monocular 3D Object Detection","created":"2019-05-29","cited_by_count":217},{"id":"2206.00630","title":"Unifying Voxel-based Representation with Transformer for 3D Object Detection","created":"2022-06-01","cited_by_count":202},{"id":"2104.02323","title":"Objects are Different: Flexible Monocular 3D Object Detection","created":"2021-04-06","cited_by_count":185},{"id":"1912.04799","title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","created":"2019-12-10","cited_by_count":169},{"id":"2206.15398","title":"PolarFormer: Multi-camera 3D Object Detection with Polar Transformer","created":"2022-06-30","cited_by_count":147},{"id":"1904.11245","title":"Exploring Object Relation in Mean Teacher for Cross-Domain Detection","created":"2019-04-25","cited_by_count":137},{"id":"2003.09152","title":"Exploring Categorical Regularization for Domain Adaptive Object Detection","created":"2020-03-20","cited_by_count":131},{"id":"1812.02781","title":"ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape","created":"2018-12-06","cited_by_count":123},{"id":"2003.12849","title":"Cross-domain Detection via Graph-induced Prototype Alignment","created":"2020-03-28","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":"2009.00155","title":"A Review of Single-Source Deep Unsupervised Visual Domain Adaptation","created":"2020-09-01","cited_by_count":96},{"id":"2209.10248","title":"BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo","created":"2022-09-21","cited_by_count":90},{"id":"2108.11127","title":"AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection","created":"2021-08-25","cited_by_count":87},{"id":"2107.11355","title":"Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency","created":"2021-07-23","cited_by_count":63},{"id":"2206.10965","title":"Polar Parametrization for Vision-based Surround-View 3D Detection","created":"2022-06-22","cited_by_count":53},{"id":"2107.12636","title":"Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers","created":"2021-07-27","cited_by_count":49},{"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":"2002.01619","title":"Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation","created":"2020-02-05","cited_by_count":43},{"id":"2006.11436","title":"BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud","created":"2020-06-19","cited_by_count":38},{"id":"1905.08955","title":"Domain Adaptation for Vehicle Detection from Bird's Eye View LiDAR Point Cloud Data","created":"2019-05-22","cited_by_count":35},{"id":"2205.01643","title":"MTTrans: Cross-Domain Object Detection with Mean-Teacher Transformer","created":"2022-05-03","cited_by_count":35},{"id":"1905.05618","title":"Monocular 3D Object Detection via Geometric Reasoning on Keypoints","created":"2019-05-14","cited_by_count":31},{"id":"2204.11590","title":"Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training","created":"2022-04-25","cited_by_count":22},{"id":"2301.08595","title":"MAVERIC: A Data-Driven Approach to Personalized Autonomous Driving","created":"2023-01-20","cited_by_count":22},{"id":"1301.3342","title":"Barnes-Hut-SNE","created":"2013-01-15","cited_by_count":14},{"id":"2111.07971","title":"Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation","created":"2021-11-15","cited_by_count":12},{"id":"2104.11021","title":"Cycle and Semantic Consistent Adversarial Domain Adaptation for Reducing Simulation-to-Real Domain Shift in LiDAR Bird's Eye View","created":"2021-04-22","cited_by_count":10},{"id":"2405.16486","title":"Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation","created":"2024-05-26","cited_by_count":10},{"id":"2208.12527","title":"Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer","created":"2022-08-26","cited_by_count":8},{"id":"2303.15486","title":"Unimodal Training-Multimodal Prediction: Cross-modal Federated Learning with Hierarchical Aggregation","created":"2023-03-27","cited_by_count":8},{"id":"2304.03650","title":"A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation","created":"2023-04-07","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":"2211.17126","title":"BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection","created":"2022-11-30","cited_by_count":5},{"id":"2401.07853","title":"VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness","created":"2024-01-15","cited_by_count":2}],"next_cursor":null}