{"list":"other","total":51,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"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":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2203.08528","title":"Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors","created":"2022-03-16","cited_by_count":146},{"id":"2007.13003","title":"Robust and Generalizable Visual Representation Learning via Random Convolutions","created":"2020-07-25","cited_by_count":142},{"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},{"id":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103},{"id":"2209.12354","title":"InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction","created":"2022-09-26","cited_by_count":93},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"1805.07925","title":"Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks","created":"2018-05-21","cited_by_count":78},{"id":"2106.15796","title":"Monocular 3D Object Detection: An Extrinsic Parameter Free Approach","created":"2021-06-30","cited_by_count":69},{"id":"2102.00690","title":"Ground-aware Monocular 3D Object Detection for Autonomous Driving","created":"2021-02-01","cited_by_count":65},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54},{"id":"2206.07372","title":"MonoGround: Detecting Monocular 3D Objects from the Ground","created":"2022-06-15","cited_by_count":37},{"id":"2304.00424","title":"Progressive Random Convolutions for Single Domain Generalization","created":"2023-04-02","cited_by_count":34},{"id":"2404.04819","title":"Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer","created":"2024-04-07","cited_by_count":29},{"id":"2309.09975","title":"GEDepth: Ground Embedding for Monocular Depth Estimation","created":"2023-09-18","cited_by_count":26},{"id":"2207.05385","title":"Controllable Shadow Generation Using Pixel Height Maps","created":"2022-07-12","cited_by_count":22},{"id":"2307.09520","title":"Adversarial Bayesian Augmentation for Single-Source Domain Generalization","created":"2023-07-18","cited_by_count":22},{"id":"2308.06554","title":"Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction","created":"2023-08-12","cited_by_count":18},{"id":"2403.17610","title":"MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors","created":"2024-03-26","cited_by_count":17},{"id":"2208.04598","title":"UnderPressure: Deep Learning for Foot Contact Detection, Ground Reaction Force Estimation and Footskate Cleanup","created":"2022-08-09","cited_by_count":16},{"id":"2303.00137","title":"PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing","created":"2023-02-28","cited_by_count":15},{"id":"2505.11152","title":"Learning Dense Hand Contact Estimation from Imbalanced Data","created":"2025-05-16","cited_by_count":14},{"id":"2312.10118","title":"From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior","created":"2023-12-15","cited_by_count":13},{"id":"2401.04143","title":"RHOBIN Challenge: Reconstruction of Human Object Interaction","created":"2024-01-07","cited_by_count":10},{"id":"2504.05046","title":"MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond","created":"2025-04-07","cited_by_count":10},{"id":"2309.01943","title":"Extract-and-Adaptation Network for 3D Interacting Hand Mesh Recovery","created":"2023-09-05","cited_by_count":7},{"id":"2409.14850","title":"GroCo: Ground Constraint for Metric Self-Supervised Monocular Depth","created":"2024-09-23","cited_by_count":6},{"id":"2406.00275","title":"StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization","created":"2024-06-01","cited_by_count":5},{"id":"2308.14596","title":"LatentDR: Improving Model Generalization Through Sample-Aware Latent Degradation and Restoration","created":"2023-08-28","cited_by_count":4},{"id":"2407.18914","title":"Floating No More: Object-Ground Reconstruction from a Single Image","created":"2024-07-26","cited_by_count":3}],"next_cursor":null}