{"list":"other","total":80,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"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":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"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":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"1902.03451","title":"3D Hand Shape and Pose from Images in the Wild","created":"2019-02-09","cited_by_count":190},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"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":"1902.09305","title":"End-to-end Hand Mesh Recovery from a Monocular RGB Image","created":"2019-02-25","cited_by_count":124},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"id":"1904.04196","title":"Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering","created":"2019-04-08","cited_by_count":115},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"2203.14564","title":"HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network","created":"2022-03-28","cited_by_count":96},{"id":"2206.11896","title":"EventNeRF: Neural Radiance Fields from a Single Colour Event Camera","created":"2022-06-23","cited_by_count":92},{"id":"1704.02201","title":"Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor","created":"2017-04-07","cited_by_count":84},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66},{"id":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64},{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57},{"id":"2405.20224","title":"EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images","created":"2024-05-29","cited_by_count":56},{"id":"2412.12861","title":"Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera","created":"2024-12-17","cited_by_count":51},{"id":"2012.06475","title":"EventHands: Real-Time Neural 3D Hand Pose Estimation from an Event Stream","created":"2020-12-11","cited_by_count":48},{"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},{"id":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34},{"id":"2312.06583","title":"3D Hand Pose Estimation in Everyday Egocentric Images","created":"2023-12-11","cited_by_count":34},{"id":"1905.01326","title":"Single Image 3D Hand Reconstruction with Mesh Convolutions","created":"2019-05-04","cited_by_count":32},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31},{"id":"1606.07253","title":"Robust 3D Hand Pose Estimation in Single Depth Images: from Single-View CNN to Multi-View CNNs","created":"2016-06-23","cited_by_count":29},{"id":"2404.08640","title":"EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams","created":"2024-04-12","cited_by_count":29},{"id":"2406.14978","title":"E2GS: Event Enhanced Gaussian Splatting","created":"2024-06-21","cited_by_count":26},{"id":"1912.10867","title":"Analysis of the hands in egocentric vision: A survey","created":"2019-12-23","cited_by_count":25},{"id":"2405.04370","title":"Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos","created":"2024-05-07","cited_by_count":21},{"id":"2403.04381","title":"Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation","created":"2024-03-07","cited_by_count":19},{"id":"2409.17680","title":"Event-based Stereo Depth Estimation: A Survey","created":"2024-09-26","cited_by_count":19},{"id":"2409.02638","title":"MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos","created":"2024-09-04","cited_by_count":18},{"id":"2210.06270","title":"Event-based Non-Rigid Reconstruction from Contours","created":"2022-10-12","cited_by_count":17},{"id":"2303.02862","title":"EvHandPose: Event-based 3D Hand Pose Estimation with Sparse Supervision","created":"2023-03-06","cited_by_count":17},{"id":"2312.14157","title":"3D Pose Estimation of Two Interacting Hands from a Monocular Event Camera","created":"2023-12-21","cited_by_count":17},{"id":"2210.13853","title":"THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervision","created":"2022-10-25","cited_by_count":16},{"id":"2504.08654","title":"The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation","created":"2025-04-11","cited_by_count":16},{"id":"2403.07346","title":"Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction","created":"2024-03-12","cited_by_count":14},{"id":"2405.19917","title":"Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition","created":"2024-05-30","cited_by_count":14},{"id":"2404.09308","title":"In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition","created":"2024-04-14","cited_by_count":12},{"id":"2412.07293","title":"EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering","created":"2024-12-10","cited_by_count":12},{"id":"2405.20030","title":"EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos","created":"2024-05-30","cited_by_count":8},{"id":"2411.09145","title":"Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos","created":"2024-11-14","cited_by_count":6},{"id":"2502.07869","title":"EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Camera","created":"2025-02-11","cited_by_count":6},{"id":"2505.19169","title":"EventEgoHands: Event-based Egocentric 3D Hand Mesh Reconstruction","created":"2025-05-25","cited_by_count":5},{"id":"2206.04927","title":"Ego2HandsPose: A Dataset for Egocentric Two-hand 3D Global Pose Estimation","created":"2022-06-10","cited_by_count":4},{"id":"2411.17313","title":"Event Ellipsometer: Event-based Mueller-Matrix Video Imaging","created":"2024-11-26","cited_by_count":4},{"id":"2509.06741","title":"Event Spectroscopy: Event-based Multispectral and Depth Sensing using Structured Light","created":"2025-09-08","cited_by_count":3},{"id":"2509.09971","title":"Event Camera Guided Visual Media Restoration & 3D Reconstruction: A Survey","created":"2025-09-12","cited_by_count":3},{"id":"2509.16949","title":"Leveraging RGB Images for Pre-Training of Event-Based Hand Pose Estimation","created":"2025-09-21","cited_by_count":3},{"id":"2510.11717","title":"Ev4DGS: Novel-view Rendering of Non-Rigid Objects from Monocular Event Streams","created":"2025-10-13","cited_by_count":3},{"id":"2512.07394","title":"Reconstructing Objects along Hand Interaction Timelines in Egocentric Video","created":"2025-12-08","cited_by_count":3},{"id":"2601.06537","title":"Towards Egocentric 3D Hand Pose Estimation in Unseen Domains","created":"2026-01-10","cited_by_count":3},{"id":"2608.11574","title":"Hand Visibility Detector: Per-Keypoint Visibility Estimation for Hands","created":"2026-08-12","cited_by_count":2},{"id":"2412.08120","title":"Dense Depth from Event Focal Stack","created":"2024-12-11","cited_by_count":1},{"id":"2505.22007","title":"Event-based Egocentric Human Pose Estimation in Dynamic Environment","created":"2025-05-28","cited_by_count":1},{"id":"2509.13883","title":"EvHand-FPV: Efficient Event-Based 3D Hand Tracking from First-Person View","created":"2025-09-17","cited_by_count":1}],"next_cursor":null}