{"list":"other","total":52,"rows":[{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"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":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"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":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"2206.01256","title":"PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images","created":"2022-06-02","cited_by_count":352},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"2207.02202","title":"CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers","created":"2022-07-05","cited_by_count":227},{"id":"2008.10559","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","created":"2020-08-24","cited_by_count":188},{"id":"2003.03488","title":"ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions","created":"2020-03-07","cited_by_count":184},{"id":"2203.05740","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","created":"2022-03-11","cited_by_count":180},{"id":"2111.12293","title":"PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization","created":"2021-11-24","cited_by_count":179},{"id":"2111.13824","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","created":"2021-11-27","cited_by_count":151},{"id":"2308.09244","title":"SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos","created":"2023-08-18","cited_by_count":150},{"id":"2212.08254","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","created":"2022-12-16","cited_by_count":137},{"id":"2303.05367","title":"Rethinking Range View Representation for LiDAR Segmentation","created":"2023-03-09","cited_by_count":128},{"id":"2203.04050","title":"BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs","created":"2022-03-08","cited_by_count":123},{"id":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108},{"id":"2012.09242","title":"S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds","created":"2020-12-16","cited_by_count":102},{"id":"2103.14326","title":"Bidirectional Projection Network for Cross Dimension Scene Understanding","created":"2021-03-26","cited_by_count":95},{"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":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87},{"id":"2403.16440","title":"RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection","created":"2024-03-25","cited_by_count":82},{"id":"2212.07048","title":"PD-Quant: Post-Training Quantization based on Prediction Difference Metric","created":"2022-12-14","cited_by_count":73},{"id":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72},{"id":"2308.04556","title":"FocalFormer3D : Focusing on Hard Instance for 3D Object Detection","created":"2023-08-08","cited_by_count":58},{"id":"2308.16896","title":"PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction","created":"2023-08-31","cited_by_count":52},{"id":"2312.03774","title":"OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries","created":"2023-12-06","cited_by_count":48},{"id":"2404.04561","title":"Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Prediction","created":"2024-04-06","cited_by_count":48},{"id":"2403.14418","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","created":"2024-03-21","cited_by_count":44},{"id":"2303.17895","title":"EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection","created":"2023-03-31","cited_by_count":38},{"id":"2403.01644","title":"OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction","created":"2024-03-03","cited_by_count":32},{"id":"2407.12951","title":"AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer","created":"2024-07-17","cited_by_count":29},{"id":"2403.11761","title":"BEVCar: Camera-Radar Fusion for BEV Map and Object Segmentation","created":"2024-03-18","cited_by_count":27},{"id":"2411.13918","title":"Quantization without Tears","created":"2024-11-21","cited_by_count":25},{"id":"2405.10591","title":"GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision","created":"2024-05-17","cited_by_count":21},{"id":"2404.02517","title":"HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras","created":"2024-04-03","cited_by_count":16},{"id":"2404.01925","title":"Improving Bird's Eye View Semantic Segmentation by Task Decomposition","created":"2024-04-02","cited_by_count":13},{"id":"2409.04979","title":"RCBEVDet++: Toward High-accuracy Radar-Camera Fusion 3D Perception Network","created":"2024-09-08","cited_by_count":11},{"id":"2406.07037","title":"PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Driving","created":"2024-06-11","cited_by_count":9},{"id":"2411.05292","title":"SimpleBEV: Improved LiDAR-Camera Fusion Architecture for 3D Object Detection","created":"2024-11-08","cited_by_count":8},{"id":"2305.12853","title":"Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection","created":"2023-05-22","cited_by_count":7},{"id":"2403.08748","title":"Real-time 3D semantic occupancy prediction for autonomous vehicles using memory-efficient sparse convolution","created":"2024-03-13","cited_by_count":7},{"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},{"id":"2410.11228","title":"TEOcc: Radar-camera Multi-modal Occupancy Prediction via Temporal Enhancement","created":"2024-10-15","cited_by_count":5}],"next_cursor":null}