{"list":"other","total":72,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"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":"1909.04349","title":"FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images","created":"2019-09-10","cited_by_count":271},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","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":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"id":"1904.03345","title":"Semantic Graph Convolutional Networks for 3D Human Pose Regression","created":"2019-04-06","cited_by_count":204},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"id":"1902.03451","title":"3D Hand Shape and Pose from Images in the Wild","created":"2019-02-09","cited_by_count":190},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"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},{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167},{"id":"1812.01598","title":"Monocular Total Capture: Posing Face, Body, and Hands in the Wild","created":"2018-12-04","cited_by_count":162},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162},{"id":"2004.01946","title":"Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild","created":"2020-04-04","cited_by_count":146},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"1902.09305","title":"End-to-end Hand Mesh Recovery from a Monocular RGB Image","created":"2019-02-25","cited_by_count":124},{"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},{"id":"1506.02178","title":"Capturing Hands in Action using Discriminative Salient Points and Physics Simulation","created":"2015-06-06","cited_by_count":115},{"id":"2203.14564","title":"HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network","created":"2022-03-28","cited_by_count":96},{"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":"2109.05488","title":"ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis","created":"2021-09-12","cited_by_count":76},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74},{"id":"2103.11703","title":"Model-based 3D Hand Reconstruction via Self-Supervised Learning","created":"2021-03-22","cited_by_count":65},{"id":"2103.02845","title":"Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration","created":"2021-03-04","cited_by_count":59},{"id":"2403.18795","title":"Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction","created":"2024-03-27","cited_by_count":56},{"id":"2204.13062","title":"Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution","created":"2022-04-27","cited_by_count":54},{"id":"2102.03725","title":"I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling","created":"2021-02-07","cited_by_count":52},{"id":"2109.01723","title":"Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction","created":"2021-09-03","cited_by_count":44},{"id":"2211.12782","title":"Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Video","created":"2022-11-23","cited_by_count":37},{"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},{"id":"2107.11646","title":"Hand Image Understanding via Deep Multi-Task Learning","created":"2021-07-24","cited_by_count":31},{"id":"2108.05126","title":"M3D-VTON: A Monocular-to-3D Virtual Try-On Network","created":"2021-08-11","cited_by_count":31},{"id":"2403.01813","title":"A Simple Baseline for Efficient Hand Mesh Reconstruction","created":"2024-03-04","cited_by_count":27},{"id":"2107.00887","title":"HO-3D_v3: Improving the Accuracy of Hand-Object Annotations of the HO-3D Dataset","created":"2021-07-02","cited_by_count":26},{"id":"2304.09502","title":"Sampling is Matter: Point-guided 3D Human Mesh Reconstruction","created":"2023-04-19","cited_by_count":24},{"id":"2312.16737","title":"HMP: Hand Motion Priors for Pose and Shape Estimation from Video","created":"2023-12-27","cited_by_count":23},{"id":"1609.09698","title":"Training a Feedback Loop for Hand Pose Estimation","created":"2016-09-30","cited_by_count":21},{"id":"2302.11306","title":"Human MotionFormer: Transferring Human Motions with Vision Transformers","created":"2023-02-22","cited_by_count":14},{"id":"2402.17062","title":"HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields","created":"2024-02-26","cited_by_count":14},{"id":"2406.01334","title":"HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models","created":"2024-06-03","cited_by_count":14},{"id":"2403.18575","title":"HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions","created":"2024-03-27","cited_by_count":13},{"id":"1705.07640","title":"Dynamics Based 3D Skeletal Hand Tracking","created":"2017-05-22","cited_by_count":10},{"id":"1809.07697","title":"Higher-order Graph Convolutional Networks","created":"2018-09-12","cited_by_count":8},{"id":"2211.13429","title":"UV-Based 3D Hand-Object Reconstruction with Grasp Optimization","created":"2022-11-24","cited_by_count":8},{"id":"2302.02410","title":"Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image","created":"2023-02-05","cited_by_count":8},{"id":"2308.10334","title":"Coordinate Transformer: Achieving Single-stage Multi-person Mesh Recovery from Videos","created":"2023-08-20","cited_by_count":5},{"id":"2403.07912","title":"HandGCAT: Occlusion-Robust 3D Hand Mesh Reconstruction from Monocular Images","created":"2024-02-27","cited_by_count":4},{"id":"2305.11101","title":"XFormer: Fast and Accurate Monocular 3D Body Capture","created":"2023-05-18","cited_by_count":1}],"next_cursor":null}