{"list":"other","total":82,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2107.07511","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","created":"2021-07-15","cited_by_count":792},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","created":"2017-05-08","cited_by_count":401},{"id":"2202.13415","title":"Conformal prediction beyond exchangeability","created":"2022-02-27","cited_by_count":355},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324},{"id":"2210.01776","title":"DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking","created":"2022-10-04","cited_by_count":313},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"1711.08229","title":"Integral Human Pose Regression","created":"2017-11-22","cited_by_count":256},{"id":"1611.07828","title":"Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose","created":"2016-11-23","cited_by_count":221},{"id":"1904.03345","title":"Semantic Graph Convolutional Networks for 3D Human Pose Regression","created":"2019-04-06","cited_by_count":204},{"id":"2002.08871","title":"Fast Differentiable Sorting and Ranking","created":"2020-02-20","cited_by_count":197},{"id":"2111.13606","title":"Conditional Image Generation with Score-Based Diffusion Models","created":"2021-11-26","cited_by_count":197},{"id":"2203.00859","title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","created":"2022-03-02","cited_by_count":159},{"id":"2111.12707","title":"MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation","created":"2021-11-24","cited_by_count":151},{"id":"2207.06389","title":"ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech","created":"2022-07-13","cited_by_count":149},{"id":"2208.08401","title":"Conformal Inference for Online Prediction with Arbitrary Distribution Shifts","created":"2022-08-17","cited_by_count":128},{"id":"2210.10254","title":"Safe Planning in Dynamic Environments using Conformal Prediction","created":"2022-10-19","cited_by_count":119},{"id":"1704.02447","title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","created":"2017-04-08","cited_by_count":115},{"id":"1905.11885","title":"Differentiable Ranks and Sorting using Optimal Transport","created":"2019-05-28","cited_by_count":113},{"id":"2110.09192","title":"Learning Optimal Conformal Classifiers","created":"2021-10-18","cited_by_count":112},{"id":"2202.05265","title":"Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging","created":"2022-02-10","cited_by_count":107},{"id":"2103.16385","title":"Graph Stacked Hourglass Networks for 3D Human Pose Estimation","created":"2021-03-30","cited_by_count":95},{"id":"2007.09389","title":"SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach","created":"2020-07-18","cited_by_count":94},{"id":"2103.14304","title":"Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation","created":"2021-03-26","cited_by_count":94},{"id":"1904.05547","title":"Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network","created":"2019-04-11","cited_by_count":92},{"id":"2205.04382","title":"FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects","created":"2022-05-09","cited_by_count":91},{"id":"2307.16895","title":"Conformal PID Control for Time Series Prediction","created":"2023-07-31","cited_by_count":88},{"id":"2107.13788","title":"Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows","created":"2021-07-29","cited_by_count":85},{"id":"2111.11755","title":"Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance","created":"2021-11-23","cited_by_count":84},{"id":"2303.11579","title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","created":"2023-03-21","cited_by_count":82},{"id":"2203.07628","title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","created":"2022-03-15","cited_by_count":80},{"id":"2302.07869","title":"Improved Online Conformal Prediction via Strongly Adaptive Online Learning","created":"2023-02-15","cited_by_count":78},{"id":"1904.01324","title":"Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking","created":"2019-04-02","cited_by_count":76},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75},{"id":"2102.08898","title":"Few-shot Conformal Prediction with Auxiliary Tasks","created":"2021-02-17","cited_by_count":53},{"id":"2107.07797","title":"Conditional Directed Graph Convolution for 3D Human Pose Estimation","created":"2021-07-16","cited_by_count":52},{"id":"2011.00980","title":"3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data","created":"2020-11-02","cited_by_count":50},{"id":"2302.03791","title":"How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control","created":"2023-02-07","cited_by_count":50},{"id":"2401.08570","title":"RoHM: Robust Human Motion Reconstruction via Diffusion","created":"2024-01-16","cited_by_count":48},{"id":"2211.09325","title":"TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation","created":"2022-11-17","cited_by_count":47},{"id":"1912.09251","title":"Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities","created":"2019-12-14","cited_by_count":41},{"id":"2111.04814","title":"Planar Robot Casting with Real2Sim2Real Self-Supervised Learning","created":"2021-11-08","cited_by_count":39},{"id":"2205.09095","title":"Achieving Risk Control in Online Learning Settings","created":"2022-05-18","cited_by_count":39},{"id":"2103.15507","title":"Context Modeling in 3D Human Pose Estimation: A Unified Perspective","created":"2021-03-29","cited_by_count":37},{"id":"2306.12893","title":"FlowBot++: Learning Generalized Articulated Objects Manipulation via Articulation Projection","created":"2023-06-22","cited_by_count":34},{"id":"2303.12246","title":"Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation","created":"2023-03-22","cited_by_count":33},{"id":"1511.06692","title":"Direct Prediction of 3D Body Poses from Motion Compensated Sequences","created":"2015-11-20","cited_by_count":26},{"id":"2010.13668","title":"GraphMDN: Leveraging graph structure and deep learning to solve inverse problems","created":"2020-10-26","cited_by_count":26},{"id":"2202.11091","title":"Efficient and Differentiable Conformal Prediction with General Function Classes","created":"2022-02-22","cited_by_count":26},{"id":"2008.05770","title":"Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses","created":"2020-08-13","cited_by_count":25},{"id":"2203.11471","title":"Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization","created":"2022-03-22","cited_by_count":25},{"id":"2011.04840","title":"Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables","created":"2020-11-10","cited_by_count":21},{"id":"2308.12965","title":"POCO: 3D Pose and Shape Estimation with Confidence","created":"2023-08-24","cited_by_count":21},{"id":"2206.02246","title":"Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models","created":"2022-06-05","cited_by_count":20},{"id":"2107.13994","title":"Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation","created":"2021-07-29","cited_by_count":18},{"id":"2105.14246","title":"Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms","created":"2021-05-29","cited_by_count":17},{"id":"2009.08618","title":"6-DoF Grasp Planning using Fast 3D Reconstruction and Grasp Quality CNN","created":"2020-09-18","cited_by_count":13},{"id":"2211.04886","title":"ART/ATK: A research platform for assessing and mitigating the sim-to-real gap in robotics and autonomous vehicle engineering","created":"2022-11-09","cited_by_count":10},{"id":"2308.12605","title":"APLA: Additional Perturbation for Latent Noise with Adversarial Training Enables Consistency","created":"2023-08-24","cited_by_count":9},{"id":"2308.00799","title":"Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction","created":"2023-08-01","cited_by_count":8},{"id":"2402.10865","title":"Multi-Model 3D Registration: Finding Multiple Moving Objects in Cluttered Point Clouds","created":"2024-02-16","cited_by_count":7},{"id":"2301.02979","title":"CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations","created":"2023-01-08","cited_by_count":6},{"id":"2311.01457","title":"Conformal Policy Learning for Sensorimotor Control Under Distribution Shifts","created":"2023-11-02","cited_by_count":6}],"next_cursor":null}