{"list":"other","total":53,"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"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":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"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},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236},{"id":"1701.02468","title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","created":"2017-01-10","cited_by_count":205},{"id":"2303.09618","title":"HIVE: Harnessing Human Feedback for Instructional Visual Editing","created":"2023-03-16","cited_by_count":173},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"id":"2307.10173","title":"DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering","created":"2023-07-19","cited_by_count":103},{"id":"2404.16752","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","created":"2024-04-25","cited_by_count":95},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"2011.11534","title":"Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation","created":"2020-11-23","cited_by_count":81},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64},{"id":"1805.10627","title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","created":"2018-05-27","cited_by_count":57},{"id":"2011.00980","title":"3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data","created":"2020-11-02","cited_by_count":50},{"id":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","cited_by_count":49},{"id":"2110.00990","title":"Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild","created":"2021-10-03","cited_by_count":48},{"id":"2403.17934","title":"AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation","created":"2024-03-26","cited_by_count":42},{"id":"2303.13796","title":"Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction","created":"2023-03-24","cited_by_count":41},{"id":"2403.09623","title":"Score-Guided Diffusion for 3D Human Recovery","created":"2024-03-14","cited_by_count":39},{"id":"2504.04753","title":"CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images","created":"2025-04-07","cited_by_count":35},{"id":"2304.06024","title":"Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views","created":"2023-04-12","cited_by_count":33},{"id":"2501.09782","title":"SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation","created":"2025-01-16","cited_by_count":32},{"id":"2303.13357","title":"POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery","created":"2023-03-23","cited_by_count":31},{"id":"2403.12959","title":"WHAC: World-grounded Humans and Cameras","created":"2024-03-19","cited_by_count":30},{"id":"2308.13369","title":"Distribution-Aligned Diffusion for Human Mesh Recovery","created":"2023-08-25","cited_by_count":27},{"id":"2305.06968","title":"HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation","created":"2023-05-11","cited_by_count":24},{"id":"2404.11291","title":"Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption","created":"2024-04-17","cited_by_count":19},{"id":"2308.02963","title":"Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models","created":"2023-08-05","cited_by_count":14},{"id":"2306.17651","title":"Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view","created":"2023-06-30","cited_by_count":8},{"id":"2312.02209","title":"AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing","created":"2023-12-03","cited_by_count":8},{"id":"2409.19580","title":"High Quality Human Image Animation using Regional Supervision and Motion Blur Condition","created":"2024-09-29","cited_by_count":7},{"id":"2312.08730","title":"Towards Robust and Expressive Whole-body Human Pose and Shape Estimation","created":"2023-12-14","cited_by_count":6},{"id":"2504.18215","title":"Unify3D: An Augmented Holistic End-to-end Monocular 3D Human Reconstruction via Anatomy Shaping and Twins Negotiating","created":"2025-04-25","cited_by_count":1}],"next_cursor":null}