{"total":418,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653,"area":null},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350,"area":null},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306,"area":null},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272,"area":null},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265,"area":null},{"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,"area":null},{"id":"2203.12575","title":"NeuMan: Neural Human Radiance Field from a Single Video","created":"2022-03-23","cited_by_count":244,"area":null},{"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,"area":null},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236,"area":null},{"id":"2112.05329","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","created":"2021-12-10","cited_by_count":209,"area":null},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193,"area":null},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180,"area":null},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169,"area":null},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"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,"area":null},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","cited_by_count":153,"area":null},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153,"area":null},{"id":"2111.12707","title":"MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation","created":"2021-11-24","cited_by_count":151,"area":null},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142,"area":null},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141,"area":null},{"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,"area":null},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137,"area":null},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136,"area":null},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124,"area":null},{"id":"2104.14639","title":"Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation","created":"2021-04-29","cited_by_count":123,"area":null},{"id":"2207.13298","title":"Is Attention All That NeRF Needs?","created":"2022-07-27","cited_by_count":113,"area":null},{"id":"2207.13784","title":"AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing","created":"2022-07-27","cited_by_count":110,"area":null},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107,"area":null},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106,"area":null},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103,"area":null},{"id":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103,"area":null},{"id":"2204.08680","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","created":"2022-04-19","cited_by_count":101,"area":null},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"id":"2203.14564","title":"HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network","created":"2022-03-28","cited_by_count":96,"area":null},{"id":"2103.14304","title":"Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation","created":"2021-03-26","cited_by_count":94,"area":null},{"id":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91,"area":null},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2203.09364","title":"Interacting Attention Graph for Single Image Two-Hand Reconstruction","created":"2022-03-17","cited_by_count":87,"area":null},{"id":"2401.01970","title":"FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding","created":"2024-01-03","cited_by_count":86,"area":null},{"id":"2403.19417","title":"OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion","created":"2024-03-28","cited_by_count":82,"area":null},{"id":"2207.13820","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","created":"2022-07-27","cited_by_count":81,"area":null},{"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,"area":null},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78,"area":null},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74,"area":null},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70,"area":null},{"id":"2602.15989","title":"SAM 3D Body: Robust Full-Body Human Mesh Recovery","created":"2026-02-17","cited_by_count":69,"area":null},{"id":"2304.07221","title":"Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models","created":"2023-04-14","cited_by_count":68,"area":null},{"id":"2203.04845","title":"Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction","created":"2022-03-09","cited_by_count":67,"area":null},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66,"area":null},{"id":"2503.21860","title":"ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning","created":"2025-03-27","cited_by_count":66,"area":null},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64,"area":null},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60,"area":null},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59,"area":null},{"id":"2203.13349","title":"Occluded Human Mesh Recovery","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54,"area":null},{"id":"2106.09336","title":"THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers","created":"2021-06-17","cited_by_count":50,"area":null},{"id":"2212.14474","title":"Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats","created":"2022-12-29","cited_by_count":50,"area":null},{"id":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","cited_by_count":49,"area":null},{"id":"2107.09142","title":"Sequence-to-Sequence Piano Transcription with Transformers","created":"2021-07-19","cited_by_count":48,"area":null},{"id":"2401.08570","title":"RoHM: Robust Human Motion Reconstruction via Diffusion","created":"2024-01-16","cited_by_count":48,"area":null},{"id":"2303.14747","title":"Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation","created":"2023-03-26","cited_by_count":47,"area":null},{"id":"2308.11184","title":"ReFit: Recurrent Fitting Network for 3D Human Recovery","created":"2023-08-22","cited_by_count":47,"area":null},{"id":"2305.08590","title":"NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation","created":"2023-05-15","cited_by_count":45,"area":null},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45,"area":"ssm"},{"id":"2303.11726","title":"3D Human Mesh Estimation from Virtual Markers","created":"2023-03-21","cited_by_count":44,"area":null},{"id":"2308.08855","title":"Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling","created":"2023-08-17","cited_by_count":43,"area":null},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42,"area":null},{"id":"2312.10726","title":"Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders","created":"2023-12-17","cited_by_count":42,"area":null},{"id":"2211.10705","title":"TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer","created":"2022-11-19","cited_by_count":41,"area":null},{"id":"2403.09623","title":"Score-Guided Diffusion for 3D Human Recovery","created":"2024-03-14","cited_by_count":39,"area":"diffusion"},{"id":"2205.06254","title":"Learned Vertex Descent: A New Direction for 3D Human Model Fitting","created":"2022-05-12","cited_by_count":37,"area":null},{"id":"2303.05938","title":"ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction","created":"2023-03-10","cited_by_count":37,"area":null},{"id":"2207.11061","title":"3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal","created":"2022-07-22","cited_by_count":36,"area":null},{"id":"2209.09484","title":"Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos","created":"2022-09-20","cited_by_count":35,"area":null},{"id":"2211.16835","title":"Reconstructing Hand-Held Objects from Monocular Video","created":"2022-11-30","cited_by_count":35,"area":null},{"id":"2310.13768","title":"PACE: Human and Camera Motion Estimation from in-the-wild Videos","created":"2023-10-20","cited_by_count":34,"area":null},{"id":"2210.06110","title":"Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers","created":"2022-10-12","cited_by_count":33,"area":null},{"id":"2304.06024","title":"Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views","created":"2023-04-12","cited_by_count":33,"area":null},{"id":"2110.09554","title":"TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation","created":"2021-10-18","cited_by_count":32,"area":null},{"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,"area":null},{"id":"2304.14299","title":"A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image","created":"2023-04-27","cited_by_count":32,"area":null},{"id":"2207.10228","title":"MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis","created":"2022-07-20","cited_by_count":31,"area":null},{"id":"2303.13357","title":"POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery","created":"2023-03-23","cited_by_count":31,"area":null},{"id":"2410.20294","title":"Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions","created":"2024-10-27","cited_by_count":31,"area":null},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30,"area":null},{"id":"2212.02796","title":"DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model","created":"2022-12-06","cited_by_count":29,"area":"diffusion"},{"id":"2201.09548","title":"Consistent 3D Hand Reconstruction in Video via self-supervised Learning","created":"2022-01-24","cited_by_count":28,"area":null},{"id":"2209.10529","title":"Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms","created":"2022-09-21","cited_by_count":28,"area":null},{"id":"2212.09530","title":"HARP: Personalized Hand Reconstruction from a Monocular RGB Video","created":"2022-12-19","cited_by_count":28,"area":null},{"id":"2404.04430","title":"PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos","created":"2024-04-05","cited_by_count":28,"area":null},{"id":"2111.00763","title":"Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements","created":"2021-11-01","cited_by_count":27,"area":null},{"id":"2201.06618","title":"VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer","created":"2022-01-17","cited_by_count":27,"area":null},{"id":"2209.08194","title":"PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation","created":"2022-09-16","cited_by_count":27,"area":null},{"id":"2308.13369","title":"Distribution-Aligned Diffusion for Human Mesh Recovery","created":"2023-08-25","cited_by_count":27,"area":null},{"id":"2111.14672","title":"Human Performance Capture from Monocular Video in the Wild","created":"2021-11-29","cited_by_count":26,"area":null},{"id":"2208.04307","title":"PlaneFormers: From Sparse View Planes to 3D Reconstruction","created":"2022-08-08","cited_by_count":26,"area":null}],"next_cursor":"100"}