{"list":"other","total":53,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"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":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"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":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"1907.06038","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","created":"2019-07-13","cited_by_count":252},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"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":"2007.09548","title":"Kinematic 3D Object Detection in Monocular Video","created":"2020-07-19","cited_by_count":116},{"id":"2203.10981","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","created":"2022-03-21","cited_by_count":109},{"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":"1911.11288","title":"Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors","created":"2019-11-26","cited_by_count":74},{"id":"2203.05662","title":"Point Density-Aware Voxels for LiDAR 3D Object Detection","created":"2022-03-10","cited_by_count":70},{"id":"2506.07310","title":"AllTracker: Efficient Dense Point Tracking at High Resolution","created":"2025-06-08","cited_by_count":58},{"id":"2007.13970","title":"Weakly Supervised 3D Object Detection from Point Clouds","created":"2020-07-28","cited_by_count":41},{"id":"2207.08531","title":"DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection","created":"2022-07-18","cited_by_count":39},{"id":"2207.12988","title":"Monocular 3D Object Detection with Depth from Motion","created":"2022-07-26","cited_by_count":38},{"id":"2012.04641","title":"Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos","created":"2020-12-08","cited_by_count":33},{"id":"2504.07958","title":"Detect Anything 3D in the Wild","created":"2025-04-10","cited_by_count":33},{"id":"2011.11858","title":"GMOT-40: A Benchmark for Generic Multiple Object Tracking","created":"2020-11-24","cited_by_count":32},{"id":"2411.16833","title":"Open Vocabulary Monocular 3D Object Detection","created":"2024-11-25","cited_by_count":23},{"id":"2104.08797","title":"MonoGRNet: A General Framework for Monocular 3D Object Detection","created":"2021-04-18","cited_by_count":20},{"id":"2203.08332","title":"WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection","created":"2022-03-16","cited_by_count":18},{"id":"2303.08686","title":"Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency","created":"2023-03-15","cited_by_count":18},{"id":"2302.07676","title":"DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes","created":"2023-02-15","cited_by_count":17},{"id":"2504.14687","title":"Seurat: From Moving Points to Depth","created":"2025-04-20","cited_by_count":13},{"id":"2403.17387","title":"Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection","created":"2024-03-26","cited_by_count":11},{"id":"2402.19144","title":"Weakly Supervised Monocular 3D Detection with a Single-View Image","created":"2024-02-29","cited_by_count":10},{"id":"2312.07530","title":"Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance","created":"2023-12-12","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":"2407.13748","title":"General Geometry-aware Weakly Supervised 3D Object Detection","created":"2024-07-18","cited_by_count":7},{"id":"2404.00149","title":"VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection","created":"2024-03-29","cited_by_count":6},{"id":"2310.14592","title":"Pre-Training LiDAR-Based 3D Object Detectors Through Colorization","created":"2023-10-23","cited_by_count":5},{"id":"2504.06801","title":"MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection","created":"2025-04-09","cited_by_count":4},{"id":"2501.09481","title":"MonoSOWA: Scalable monocular 3D Object detector Without human Annotations","created":"2025-01-16","cited_by_count":2}],"next_cursor":null}