{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"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":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"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":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"1902.11020","title":"DPOD: 6D Pose Object Detector and Refiner","created":"2019-02-28","cited_by_count":189},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"2008.04451","title":"Grasping Field: Learning Implicit Representations for Human Grasps","created":"2020-08-10","cited_by_count":179},{"id":"2007.15649","title":"Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild","created":"2020-07-30","cited_by_count":152},{"id":"2012.09856","title":"Reconstructing Hand-Object Interactions in the Wild","created":"2020-12-17","cited_by_count":144},{"id":"1904.05349","title":"H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions","created":"2019-04-10","cited_by_count":141},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141},{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141},{"id":"2004.13449","title":"Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction","created":"2020-04-28","cited_by_count":139},{"id":"2104.07267","title":"ContactOpt: Optimizing Contact to Improve Grasps","created":"2021-04-15","cited_by_count":139},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129},{"id":"1506.02178","title":"Capturing Hands in Action using Discriminative Salient Points and Physics Simulation","created":"2015-06-06","cited_by_count":115},{"id":"2003.09282","title":"Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints","created":"2020-03-20","cited_by_count":97},{"id":"2204.07153","title":"What's in your hands? 3D Reconstruction of Generic Objects in Hands","created":"2022-04-14","cited_by_count":90},{"id":"2203.09364","title":"Interacting Attention Graph for Single Image Two-Hand Reconstruction","created":"2022-03-17","cited_by_count":87},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74},{"id":"2307.11307","title":"EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos","created":"2023-07-21","cited_by_count":69},{"id":"2401.06013","title":"Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery","created":"2024-01-11","cited_by_count":52},{"id":"2412.12861","title":"Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera","created":"2024-12-17","cited_by_count":51},{"id":"2106.01035","title":"Towards Unified Surgical Skill Assessment","created":"2021-06-02","cited_by_count":49},{"id":"1902.07766","title":"Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning Methods","created":"2019-02-20","cited_by_count":47},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45},{"id":"2006.15561","title":"Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion","created":"2020-06-28","cited_by_count":39},{"id":"2303.05938","title":"ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction","created":"2023-03-10","cited_by_count":37},{"id":"2303.13652","title":"Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild","created":"2023-03-23","cited_by_count":36},{"id":"2211.16835","title":"Reconstructing Hand-Held Objects from Monocular Video","created":"2022-11-30","cited_by_count":35},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32},{"id":"2411.15421","title":"OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining","created":"2024-11-23","cited_by_count":29},{"id":"2503.02579","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","created":"2025-03-04","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":"2404.06507","title":"Reconstructing Hand-Held Objects in 3D from Images and Videos","created":"2024-04-09","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":"2310.13347","title":"NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding","created":"2023-10-20","cited_by_count":20},{"id":"2307.10387","title":"POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical Activities","created":"2023-07-19","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":"2305.03036","title":"3D Reconstruction of Objects in Hands without Real World 3D Supervision","created":"2023-05-04","cited_by_count":12},{"id":"2409.05442","title":"EndoOmni: Zero-Shot Cross-Dataset Depth Estimation in Endoscopy by Robust Self-Learning from Noisy Labels","created":"2024-09-09","cited_by_count":12},{"id":"2304.04038","title":"POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo","created":"2023-04-08","cited_by_count":10},{"id":"2409.06037","title":"Online 3D reconstruction and dense tracking in endoscopic videos","created":"2024-09-09","cited_by_count":10},{"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":"2101.01659","title":"Spatial Attention Improves Iterative 6D Object Pose Estimation","created":"2021-01-05","cited_by_count":4},{"id":"2405.01353","title":"Sparse multi-view hand-object reconstruction for unseen environments","created":"2024-05-02","cited_by_count":4},{"id":"2408.03078","title":"BodySLAM: A Generalized Monocular Visual SLAM Framework for Surgical Applications","created":"2024-08-06","cited_by_count":4},{"id":"2406.16137","title":"MLPHand: Real Time Multi-View 3D Hand Mesh Reconstruction via MLP Modeling","created":"2024-06-23","cited_by_count":3},{"id":"2407.09215","title":"HUP-3D: A 3D multi-view synthetic dataset for assisted-egocentric hand-ultrasound pose estimation","created":"2024-07-12","cited_by_count":2}],"next_cursor":null}