{"list":"other","total":61,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"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":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"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":"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":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"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":"2302.07685","title":"Video Probabilistic Diffusion Models in Projected Latent Space","created":"2023-02-15","cited_by_count":171},{"id":"2207.06389","title":"ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech","created":"2022-07-13","cited_by_count":149},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139},{"id":"1712.09763","title":"PixelSNAIL: An Improved Autoregressive Generative Model","created":"2017-12-28","cited_by_count":137},{"id":"2207.13784","title":"AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing","created":"2022-07-27","cited_by_count":110},{"id":"2304.08577","title":"Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model","created":"2023-04-17","cited_by_count":107},{"id":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91},{"id":"2204.09443","title":"GIMO: Gaze-Informed Human Motion Prediction in Context","created":"2022-04-20","cited_by_count":81},{"id":"2412.15205","title":"FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching","created":"2024-12-19","cited_by_count":80},{"id":"2210.10542","title":"PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting","created":"2022-10-19","cited_by_count":78},{"id":"1703.03664","title":"Parallel Multiscale Autoregressive Density Estimation","created":"2017-03-10","cited_by_count":71},{"id":"2406.09750","title":"ControlVAR: Exploring Controllable Visual Autoregressive Modeling","created":"2024-06-14","cited_by_count":58},{"id":"2212.08641","title":"GFPose: Learning 3D Human Pose Prior with Gradient Fields","created":"2022-12-16","cited_by_count":57},{"id":"2203.05789","title":"FLAG: Flow-based 3D Avatar Generation from Sparse Observations","created":"2022-03-11","cited_by_count":55},{"id":"2303.09095","title":"SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments","created":"2023-03-16","cited_by_count":47},{"id":"2103.01500","title":"LoBSTr: Real-time Lower-body Pose Prediction from Sparse Upper-body Tracking Signals","created":"2021-03-02","cited_by_count":45},{"id":"2304.11118","title":"BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis","created":"2023-04-21","cited_by_count":45},{"id":"2308.08855","title":"Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling","created":"2023-08-17","cited_by_count":43},{"id":"2211.10705","title":"TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer","created":"2022-11-19","cited_by_count":41},{"id":"2104.11452","title":"SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos","created":"2021-04-23","cited_by_count":40},{"id":"2308.06493","title":"EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere","created":"2023-08-12","cited_by_count":34},{"id":"2503.23367","title":"FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning","created":"2025-03-30","cited_by_count":34},{"id":"2203.14698","title":"LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds","created":"2022-03-28","cited_by_count":33},{"id":"2410.04671","title":"CAR: Controllable Autoregressive Modeling for Visual Generation","created":"2024-10-07","cited_by_count":30},{"id":"2406.10797","title":"STAR: Scale-wise Text-conditioned AutoRegressive image generation","created":"2024-06-16","cited_by_count":28},{"id":"2411.10433","title":"M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation","created":"2024-11-15","cited_by_count":28},{"id":"2303.17948","title":"CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions","created":"2023-03-31","cited_by_count":27},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27},{"id":"2403.03561","title":"HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations","created":"2024-03-06","cited_by_count":25},{"id":"2405.20786","title":"Stratified Avatar Generation from Sparse Observations","created":"2024-05-30","cited_by_count":21},{"id":"2403.19501","title":"RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method","created":"2024-03-28","cited_by_count":16},{"id":"2111.11927","title":"Hierarchical Graph Networks for 3D Human Pose Estimation","created":"2021-11-23","cited_by_count":12},{"id":"2504.05265","title":"From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models","created":"2025-04-07","cited_by_count":11},{"id":"2503.23331","title":"HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation","created":"2025-03-30","cited_by_count":8},{"id":"2409.04398","title":"HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR","created":"2024-09-06","cited_by_count":5},{"id":"2603.06181","title":"Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robots","created":"2026-03-06","cited_by_count":4},{"id":"2503.21268","title":"ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate","created":"2025-03-27","cited_by_count":3},{"id":"2603.19770","title":"FlashCap: Millisecond-Accurate Human Motion Capture via Flashing LEDs and Event-Based Vision","created":"2026-03-20","cited_by_count":1}],"next_cursor":null}