{"list":"other","total":67,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2112.09127","title":"ICON: Implicit Clothed humans Obtained from Normals","created":"2021-12-16","cited_by_count":283},{"id":"2004.04572","title":"ARCH: Animatable Reconstruction of Clothed Humans","created":"2020-04-08","cited_by_count":257},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"1908.06903","title":"Multi-Garment Net: Learning to Dress 3D People from Images","created":"2019-08-19","cited_by_count":245},{"id":"1801.01615","title":"Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies","created":"2018-01-05","cited_by_count":239},{"id":"1803.04758","title":"Video Based Reconstruction of 3D People Models","created":"2018-03-13","cited_by_count":238},{"id":"2007.03858","title":"PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction","created":"2020-07-08","cited_by_count":231},{"id":"2104.03953","title":"SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes","created":"2021-04-08","cited_by_count":221},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"1812.07003","title":"3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans","created":"2018-12-17","cited_by_count":217},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2104.03313","title":"SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks","created":"2021-04-07","cited_by_count":181},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"1903.05885","title":"Learning to Reconstruct People in Clothing from a Single RGB Camera","created":"2019-03-14","cited_by_count":168},{"id":"2008.09062","title":"Monocular Expressive Body Regression through Body-Driven Attention","created":"2020-08-20","cited_by_count":155},{"id":"1912.03207","title":"NASA: Neural Articulated Shape Approximation","created":"2019-12-06","cited_by_count":149},{"id":"2201.12792","title":"SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video","created":"2022-01-30","cited_by_count":144},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142},{"id":"2003.13867","title":"3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation","created":"2020-03-30","cited_by_count":141},{"id":"2104.07267","title":"ContactOpt: Optimizing Contact to Improve Grasps","created":"2021-04-15","cited_by_count":139},{"id":"2108.11515","title":"Robust High-Resolution Video Matting with Temporal Guidance","created":"2021-08-25","cited_by_count":137},{"id":"2006.08586","title":"Coherent Reconstruction of Multiple Humans from a Single Image","created":"2020-06-15","cited_by_count":136},{"id":"2302.11566","title":"Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition","created":"2023-02-22","cited_by_count":134},{"id":"2007.11432","title":"Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction","created":"2020-07-22","cited_by_count":133},{"id":"2004.03686","title":"Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation","created":"2020-04-07","cited_by_count":113},{"id":"2010.12447","title":"LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration","created":"2020-10-23","cited_by_count":108},{"id":"2108.08807","title":"Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing","created":"2021-08-19","cited_by_count":102},{"id":"1804.06023","title":"DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor","created":"2018-04-17","cited_by_count":95},{"id":"1901.04111","title":"Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views","created":"2019-01-14","cited_by_count":83},{"id":"2008.08474","title":"Human Body Model Fitting by Learned Gradient Descent","created":"2020-08-19","cited_by_count":81},{"id":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75},{"id":"2105.00261","title":"DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras","created":"2021-05-01","cited_by_count":67},{"id":"2303.04805","title":"X-Avatar: Expressive Human Avatars","created":"2023-03-08","cited_by_count":66},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64},{"id":"2211.15601","title":"Fast-SNARF: A Fast Deformer for Articulated Neural Fields","created":"2022-11-28","cited_by_count":55},{"id":"2108.10378","title":"Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras","created":"2021-08-23","cited_by_count":33},{"id":"2111.14672","title":"Human Performance Capture from Monocular Video in the Wild","created":"2021-11-29","cited_by_count":26},{"id":"2205.10767","title":"Human Instance Matting via Mutual Guidance and Multi-Instance Refinement","created":"2022-05-22","cited_by_count":25},{"id":"2110.02330","title":"Shape-aware Multi-Person Pose Estimation from Multi-View Images","created":"2021-10-05","cited_by_count":24},{"id":"2210.05567","title":"Global Spectral Filter Memory Network for Video Object Segmentation","created":"2022-10-11","cited_by_count":22},{"id":"2104.09283","title":"Multi-person Implicit Reconstruction from a Single Image","created":"2021-04-19","cited_by_count":13},{"id":"2207.13353","title":"One-Trimap Video Matting","created":"2022-07-27","cited_by_count":12}],"next_cursor":null}