{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"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":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"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":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"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":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"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":"2111.13606","title":"Conditional Image Generation with Score-Based Diffusion Models","created":"2021-11-26","cited_by_count":197},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"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":"1805.04095","title":"Ordinal Depth Supervision for 3D Human Pose Estimation","created":"2018-05-10","cited_by_count":107},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100},{"id":"2103.16385","title":"Graph Stacked Hourglass Networks for 3D Human Pose Estimation","created":"2021-03-30","cited_by_count":95},{"id":"2303.17472","title":"PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation","created":"2023-03-30","cited_by_count":92},{"id":"1711.08585","title":"Exploiting temporal information for 3D pose estimation","created":"2017-11-23","cited_by_count":89},{"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":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75},{"id":"2211.16487","title":"DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models","created":"2022-11-29","cited_by_count":65},{"id":"2310.16288","title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","created":"2023-10-25","cited_by_count":64},{"id":"2212.08641","title":"GFPose: Learning 3D Human Pose Prior with Gradient Fields","created":"2022-12-16","cited_by_count":57},{"id":"2307.05853","title":"GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video","created":"2023-07-12","cited_by_count":47},{"id":"1609.05317","title":"Deep Kinematic Pose Regression","created":"2016-09-17","cited_by_count":40},{"id":"2404.00658","title":"KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation","created":"2024-03-31","cited_by_count":34},{"id":"2212.02796","title":"DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model","created":"2022-12-06","cited_by_count":29},{"id":"1511.06692","title":"Direct Prediction of 3D Body Poses from Motion Compensated Sequences","created":"2015-11-20","cited_by_count":26},{"id":"2405.05216","title":"FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models","created":"2024-05-08","cited_by_count":23},{"id":"2206.06420","title":"GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation","created":"2022-06-13","cited_by_count":21},{"id":"2302.07408","title":"Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation","created":"2023-02-15","cited_by_count":19},{"id":"2311.12028","title":"Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation","created":"2023-11-20","cited_by_count":15},{"id":"2403.11310","title":"A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation","created":"2024-03-17","cited_by_count":15},{"id":"2501.01770","title":"TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation","created":"2025-01-03","cited_by_count":14},{"id":"2403.04444","title":"Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser","created":"2024-03-07","cited_by_count":13},{"id":"2408.02922","title":"Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network","created":"2024-08-06","cited_by_count":12},{"id":"2506.04228","title":"LayerFlow: A Unified Model for Layer-aware Video Generation","created":"2025-06-04","cited_by_count":10},{"id":"2503.23331","title":"HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation","created":"2025-03-30","cited_by_count":8},{"id":"2106.14706","title":"Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos","created":"2021-06-28","cited_by_count":5},{"id":"2509.06956","title":"H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers","created":"2025-09-08","cited_by_count":5},{"id":"2402.02339","title":"Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation","created":"2024-02-04","cited_by_count":2},{"id":"2501.15763","title":"NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation","created":"2025-01-27","cited_by_count":2}],"next_cursor":null}