{"list":"other","total":51,"rows":[{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"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":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2302.04264","title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development","created":"2023-02-08","cited_by_count":600},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"1708.06500","title":"Sparsity Invariant CNNs","created":"2017-08-22","cited_by_count":326},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"2006.14480","title":"One Thousand and One Hours: Self-driving Motion Prediction Dataset","created":"2020-06-25","cited_by_count":240},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173},{"id":"2408.16760","title":"OmniRe: Omni Urban Scene Reconstruction","created":"2024-08-29","cited_by_count":161},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142},{"id":"2104.00563","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","created":"2021-02-19","cited_by_count":131},{"id":"2312.17655","title":"Visual Point Cloud Forecasting enables Scalable Autonomous Driving","created":"2023-12-29","cited_by_count":99},{"id":"2205.00613","title":"MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries","created":"2022-05-02","cited_by_count":91},{"id":"2304.14340","title":"SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection","created":"2023-04-27","cited_by_count":83},{"id":"1903.01568","title":"The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes","created":"2019-03-04","cited_by_count":80},{"id":"2302.13130","title":"Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting","created":"2023-02-25","cited_by_count":78},{"id":"2308.09616","title":"Far3D: Expanding the Horizon for Surround-view 3D Object Detection","created":"2023-08-18","cited_by_count":70},{"id":"1909.07541","title":"A*3D Dataset: Towards Autonomous Driving in Challenging Environments","created":"2019-09-17","cited_by_count":65},{"id":"2111.13672","title":"Immortal Tracker: Tracklet Never Dies","created":"2021-11-26","cited_by_count":42},{"id":"2401.09101","title":"PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency","created":"2024-01-17","cited_by_count":42},{"id":"2003.02371","title":"A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI","created":"2020-03-04","cited_by_count":40},{"id":"2403.11193","title":"Neural Markov Random Field for Stereo Matching","created":"2024-03-17","cited_by_count":40},{"id":"2006.07864","title":"Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection","created":"2020-06-14","cited_by_count":39},{"id":"2308.14713","title":"R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras","created":"2023-08-28","cited_by_count":39},{"id":"2206.04129","title":"Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions","created":"2022-06-08","cited_by_count":35},{"id":"2308.03755","title":"FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels","created":"2023-08-07","cited_by_count":34},{"id":"2211.09445","title":"aiMotive Dataset: A Multimodal Dataset for Robust Autonomous Driving with Long-Range Perception","created":"2022-11-17","cited_by_count":29},{"id":"2308.06635","title":"3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking","created":"2023-08-12","cited_by_count":21},{"id":"2501.08643","title":"MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors","created":"2025-01-15","cited_by_count":19},{"id":"2507.13162","title":"Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models","created":"2025-07-17","cited_by_count":17},{"id":"2508.04611","title":"BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment","created":"2025-08-06","cited_by_count":15},{"id":"2508.13995","title":"Self-Supervised Sparse Sensor Fusion for Long Range Perception","created":"2025-08-19","cited_by_count":8},{"id":"2011.00674","title":"Highway Driving Dataset for Semantic Video Segmentation","created":"2020-11-02","cited_by_count":5}],"next_cursor":null}