{"list":"other","total":90,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"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":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"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":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"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":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"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":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"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":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"2008.03713","title":"I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image","created":"2020-08-09","cited_by_count":274},{"id":"1905.03244","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","created":"2019-05-08","cited_by_count":270},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2302.03660","title":"Flow Matching on General Geometries","created":"2023-02-07","cited_by_count":265},{"id":"2008.09047","title":"Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose","created":"2020-08-20","cited_by_count":248},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238},{"id":"1805.04092","title":"Learning to Estimate 3D Human Pose and Shape from a Single Color Image","created":"2018-05-10","cited_by_count":226},{"id":"2302.02277","title":"SE(3) diffusion model with application to protein backbone generation","created":"2023-02-05","cited_by_count":219},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153},{"id":"2209.03855","title":"SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion","created":"2022-09-08","cited_by_count":127},{"id":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103},{"id":"2308.16894","title":"EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild","created":"2023-08-31","cited_by_count":97},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95},{"id":"2006.14616","title":"An Analysis of SVD for Deep Rotation Estimation","created":"2020-06-25","cited_by_count":86},{"id":"2207.13807","title":"Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields","created":"2022-07-27","cited_by_count":85},{"id":"2207.13820","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","created":"2022-07-27","cited_by_count":81},{"id":"1904.01324","title":"Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking","created":"2019-04-02","cited_by_count":76},{"id":"2003.04232","title":"Hierarchical Kinematic Human Mesh Recovery","created":"2020-03-09","cited_by_count":71},{"id":"2211.16016","title":"UDE: A Unified Driving Engine for Human Motion Generation","created":"2022-11-29","cited_by_count":67},{"id":"2104.07300","title":"Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes","created":"2021-04-15","cited_by_count":65},{"id":"2212.08641","title":"GFPose: Learning 3D Human Pose Prior with Gradient Fields","created":"2022-12-16","cited_by_count":57},{"id":"2110.00990","title":"Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild","created":"2021-10-03","cited_by_count":48},{"id":"2303.11726","title":"3D Human Mesh Estimation from Virtual Markers","created":"2023-03-21","cited_by_count":44},{"id":"2306.09337","title":"Generative Proxemics: A Prior for 3D Social Interaction from Images","created":"2023-06-15","cited_by_count":43},{"id":"2103.10978","title":"Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild","created":"2021-03-19","cited_by_count":40},{"id":"2305.11094","title":"QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation","created":"2023-05-18","cited_by_count":40},{"id":"2403.09623","title":"Score-Guided Diffusion for 3D Human Recovery","created":"2024-03-14","cited_by_count":39},{"id":"2112.04203","title":"Adversarial Parametric Pose Prior","created":"2021-12-08","cited_by_count":38},{"id":"2205.06254","title":"Learned Vertex Descent: A New Direction for 3D Human Model Fitting","created":"2022-05-12","cited_by_count":37},{"id":"2304.06024","title":"Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views","created":"2023-04-12","cited_by_count":33},{"id":"2310.17359","title":"SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation","created":"2023-10-26","cited_by_count":33},{"id":"2403.17422","title":"InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion","created":"2024-03-26","cited_by_count":28},{"id":"2104.13502","title":"KAMA: 3D Keypoint Aware Body Mesh Articulation","created":"2021-04-27","cited_by_count":27},{"id":"2403.03122","title":"NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors","created":"2024-03-05","cited_by_count":27},{"id":"2302.14348","title":"Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes","created":"2023-02-28","cited_by_count":26},{"id":"2003.13764","title":"Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction","created":"2020-03-30","cited_by_count":24},{"id":"2305.06968","title":"HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation","created":"2023-05-11","cited_by_count":24},{"id":"2308.12965","title":"POCO: 3D Pose and Shape Estimation with Confidence","created":"2023-08-24","cited_by_count":21},{"id":"2410.04534","title":"UniMuMo: Unified Text, Music and Motion Generation","created":"2024-10-06","cited_by_count":19},{"id":"2305.15873","title":"Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)","created":"2023-05-25","cited_by_count":17},{"id":"2312.05541","title":"DPoser: Diffusion Model as Robust 3D Human Pose Prior","created":"2023-12-09","cited_by_count":17},{"id":"2208.10652","title":"Learning Visibility for Robust Dense Human Body Estimation","created":"2022-08-23","cited_by_count":15},{"id":"2409.04033","title":"Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics","created":"2024-09-06","cited_by_count":15},{"id":"2308.02963","title":"Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models","created":"2023-08-05","cited_by_count":14},{"id":"2405.18839","title":"MEGA: Masked Generative Autoencoder for Human Mesh Recovery","created":"2024-05-29","cited_by_count":14},{"id":"2504.04956","title":"REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning","created":"2025-04-07","cited_by_count":14},{"id":"2312.08291","title":"VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space","created":"2023-12-13","cited_by_count":13},{"id":"2307.08100","title":"FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow","created":"2023-07-16","cited_by_count":10},{"id":"2403.08262","title":"BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image","created":"2024-03-13","cited_by_count":8},{"id":"2404.05675","title":"Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling","created":"2024-04-08","cited_by_count":7},{"id":"1812.10766","title":"SMPLR: Deep SMPL reverse for 3D human pose and shape recovery","created":"2018-12-27","cited_by_count":5},{"id":"2312.11707","title":"Unified framework for diffusion generative models in SO(3): applications in computer vision and astrophysics","created":"2023-12-18","cited_by_count":5},{"id":"2409.18364","title":"Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images","created":"2024-09-27","cited_by_count":5},{"id":"2509.21859","title":"SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit 3D Meshes","created":"2025-09-26","cited_by_count":3},{"id":"2409.01591","title":"Dynamic Motion Synthesis: Masked Audio-Text Conditioned Spatio-Temporal Transformers","created":"2024-09-03","cited_by_count":1}],"next_cursor":null}