{"list":"other","total":92,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"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":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"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":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"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":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"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":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2103.16507","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","created":"2021-03-30","cited_by_count":250},{"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":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2011.08627","title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","created":"2020-11-17","cited_by_count":163},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152},{"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":"2409.06662","title":"World-Grounded Human Motion Recovery via Gravity-View Coordinates","created":"2024-09-10","cited_by_count":137},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103},{"id":"2402.14654","title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","created":"2024-02-22","cited_by_count":101},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91},{"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":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72},{"id":"2107.03332","title":"SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation","created":"2021-07-07","cited_by_count":68},{"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":"2411.08128","title":"CameraHMR: Aligning People with Perspective","created":"2024-11-12","cited_by_count":65},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64},{"id":"2203.08534","title":"Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video","created":"2022-03-16","cited_by_count":60},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59},{"id":"2012.09843","title":"Human Mesh Recovery from Multiple Shots","created":"2020-12-17","cited_by_count":52},{"id":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","cited_by_count":49},{"id":"2303.11726","title":"3D Human Mesh Estimation from Virtual Markers","created":"2023-03-21","cited_by_count":44},{"id":"2403.17934","title":"AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation","created":"2024-03-26","cited_by_count":42},{"id":"2211.10705","title":"TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer","created":"2022-11-19","cited_by_count":41},{"id":"2403.09623","title":"Score-Guided Diffusion for 3D Human Recovery","created":"2024-03-14","cited_by_count":39},{"id":"2212.00776","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","created":"2022-12-01","cited_by_count":34},{"id":"2304.06024","title":"Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views","created":"2023-04-12","cited_by_count":33},{"id":"2303.09187","title":"PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers","created":"2023-03-16","cited_by_count":32},{"id":"2303.13357","title":"POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery","created":"2023-03-23","cited_by_count":31},{"id":"2209.10529","title":"Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms","created":"2022-09-21","cited_by_count":28},{"id":"2304.09502","title":"Sampling is Matter: Point-guided 3D Human Mesh Reconstruction","created":"2023-04-19","cited_by_count":24},{"id":"2206.10552","title":"Vicinity Vision Transformer","created":"2022-06-21","cited_by_count":22},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16},{"id":"2411.19824","title":"SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens","created":"2024-11-29","cited_by_count":16},{"id":"2405.18839","title":"MEGA: Masked Generative Autoencoder for Human Mesh Recovery","created":"2024-05-29","cited_by_count":14},{"id":"2205.05277","title":"AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation","created":"2022-05-11","cited_by_count":13},{"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":"2212.06795","title":"GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation","created":"2022-12-13","cited_by_count":11},{"id":"2311.15157","title":"Advancing Vision Transformers with Group-Mix Attention","created":"2023-11-26","cited_by_count":11},{"id":"2402.18844","title":"Deep learning for 3D human pose estimation and mesh recovery: A survey","created":"2024-02-29","cited_by_count":11},{"id":"2405.04533","title":"ChatHuman: Chatting about 3D Humans with Tools","created":"2024-05-07","cited_by_count":11},{"id":"2409.04196","title":"GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformers","created":"2024-09-06","cited_by_count":11},{"id":"2301.06020","title":"Delving Deep into Pixel Alignment Feature for Accurate Multi-view Human Mesh Recovery","created":"2023-01-15","cited_by_count":10},{"id":"2303.00298","title":"Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens","created":"2023-03-01","cited_by_count":8},{"id":"2406.10180","title":"MeshPose: Unifying DensePose and 3D Body Mesh reconstruction","created":"2024-06-14","cited_by_count":8},{"id":"2505.10250","title":"ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization","created":"2025-05-15","cited_by_count":7},{"id":"2503.07597","title":"HumanMM: Global Human Motion Recovery from Multi-shot Videos","created":"2025-03-10","cited_by_count":6},{"id":"2403.05055","title":"MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction","created":"2024-03-08","cited_by_count":5},{"id":"2412.13058","title":"CondiMen: Conditional Multi-Person Mesh Recovery","created":"2024-12-17","cited_by_count":5},{"id":"2012.07033","title":"Efficient Human Pose Estimation by Learning Deeply Aggregated Representations","created":"2020-12-13","cited_by_count":4},{"id":"2404.01941","title":"LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging","created":"2024-04-02","cited_by_count":3},{"id":"2503.00068","title":"PI-HMR: Towards Robust In-bed Temporal Human Shape Reconstruction with Contact Pressure Sensing","created":"2025-02-27","cited_by_count":3}],"next_cursor":null}