{"list":"other","total":51,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"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":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"1901.02970","title":"Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation","created":"2019-01-09","cited_by_count":495},{"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":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"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":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243},{"id":"1703.10896","title":"BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth","created":"2017-03-31","cited_by_count":225},{"id":"1804.04610","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","created":"2018-04-12","cited_by_count":218},{"id":"2107.14160","title":"Probabilistic and Geometric Depth: Detecting Objects in Perspective","created":"2021-07-29","cited_by_count":191},{"id":"2303.06615","title":"Iterative Geometry Encoding Volume for Stereo Matching","created":"2023-03-12","cited_by_count":190},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"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":"2012.09988","title":"Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations","created":"2020-12-18","cited_by_count":155},{"id":"2102.12145","title":"GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator","created":"2021-02-24","cited_by_count":148},{"id":"1811.11187","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","created":"2018-11-27","cited_by_count":142},{"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":"2108.11127","title":"AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection","created":"2021-08-25","cited_by_count":87},{"id":"2103.12605","title":"MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation","created":"2021-03-23","cited_by_count":82},{"id":"2303.12787","title":"EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation","created":"2023-03-22","cited_by_count":79},{"id":"2203.01929","title":"CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation","created":"2022-03-03","cited_by_count":70},{"id":"2112.01988","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","created":"2021-12-03","cited_by_count":67},{"id":"2007.13034","title":"Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve","created":"2020-07-26","cited_by_count":65},{"id":"2206.15436","title":"Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset","created":"2022-06-30","cited_by_count":59},{"id":"1608.07711","title":"3D Object Proposals using Stereo Imagery for Accurate Object Class Detection","created":"2016-08-27","cited_by_count":58},{"id":"2204.03635","title":"Zero-Shot Category-Level Object Pose Estimation","created":"2022-04-07","cited_by_count":57},{"id":"2109.09163","title":"CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation","created":"2021-09-19","cited_by_count":49},{"id":"1906.04201","title":"End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans","created":"2019-06-10","cited_by_count":40},{"id":"2012.04641","title":"Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos","created":"2020-12-08","cited_by_count":33},{"id":"2108.10165","title":"ODAM: Object Detection, Association, and Mapping using Posed RGB Video","created":"2021-08-23","cited_by_count":22},{"id":"2110.00464","title":"MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation","created":"2021-10-01","cited_by_count":16},{"id":"2112.04477","title":"Tracking People by Predicting 3D Appearance, Location & Pose","created":"2021-12-08","cited_by_count":15},{"id":"2306.09011","title":"CAD-Estate: Large-scale CAD Model Annotation in RGB Videos","created":"2023-06-15","cited_by_count":14},{"id":"2104.00613","title":"The surprising impact of mask-head architecture on novel class segmentation","created":"2021-04-01","cited_by_count":13}],"next_cursor":null}