{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"1604.00449","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","created":"2016-04-02","cited_by_count":588},{"id":"1610.07584","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","created":"2016-10-24","cited_by_count":558},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"1607.02565","title":"Direct Sparse Odometry","created":"2016-07-09","cited_by_count":485},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"1911.06971","title":"BSP-Net: Generating Compact Meshes via Binary Space Partitioning","created":"2019-11-16","cited_by_count":206},{"id":"1603.08637","title":"Learning a Predictable and Generative Vector Representation for Objects","created":"2016-03-29","cited_by_count":173},{"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":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157},{"id":"1811.11187","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","created":"2018-11-27","cited_by_count":142},{"id":"1806.00557","title":"CubeSLAM: Monocular 3D Object SLAM","created":"2018-06-01","cited_by_count":102},{"id":"1804.04011","title":"QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM","created":"2018-04-10","cited_by_count":86},{"id":"2006.12250","title":"Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images","created":"2020-06-22","cited_by_count":79},{"id":"1608.05137","title":"IM2CAD","created":"2016-08-18","cited_by_count":78},{"id":"1811.10742","title":"Joint Monocular 3D Vehicle Detection and Tracking","created":"2018-11-26","cited_by_count":77},{"id":"1808.02201","title":"Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image","created":"2018-08-07","cited_by_count":69},{"id":"2012.02177","title":"DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion","created":"2020-12-03","cited_by_count":68},{"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":"2005.05125","title":"FroDO: From Detections to 3D Objects","created":"2020-05-11","cited_by_count":51},{"id":"1712.01812","title":"Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene","created":"2017-12-05","cited_by_count":50},{"id":"2004.12989","title":"CoReNet: Coherent 3D scene reconstruction from a single RGB image","created":"2020-04-27","cited_by_count":45},{"id":"2003.12622","title":"SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans","created":"2020-03-27","cited_by_count":44},{"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":"2108.09368","title":"Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image","created":"2021-08-20","cited_by_count":39},{"id":"2012.04641","title":"Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos","created":"2020-12-08","cited_by_count":33},{"id":"2012.11575","title":"From Points to Multi-Object 3D Reconstruction","created":"2020-12-21","cited_by_count":29},{"id":"2108.10165","title":"ODAM: Object Detection, Association, and Mapping using Posed RGB Video","created":"2021-08-23","cited_by_count":22},{"id":"1805.03225","title":"A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Images","created":"2018-05-08","cited_by_count":19},{"id":"2007.13727","title":"Associative3D: Volumetric Reconstruction from Sparse Views","created":"2020-07-27","cited_by_count":18},{"id":"2012.05360","title":"MOLTR: Multiple Object Localisation, Tracking, and Reconstruction from Monocular RGB Videos","created":"2020-12-09","cited_by_count":18},{"id":"2108.00355","title":"ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description","created":"2021-08-01","cited_by_count":10},{"id":"1806.08498","title":"Visual-Inertial Object Detection and Mapping","created":"2018-06-22","cited_by_count":5},{"id":"1812.05583","title":"Scene Recomposition by Learning-based ICP","created":"2018-12-13","cited_by_count":5}],"next_cursor":null}