{"list":"other","total":57,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"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":"2104.07267","title":"ContactOpt: Optimizing Contact to Improve Grasps","created":"2021-04-15","cited_by_count":139},{"id":"2404.12385","title":"MeshLRM: Large Reconstruction Model for High-Quality Meshes","created":"2024-04-18","cited_by_count":139},{"id":"1912.02923","title":"Generating 3D People in Scenes without People","created":"2019-12-05","cited_by_count":127},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","cited_by_count":124},{"id":"2204.10776","title":"Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images","created":"2022-04-22","cited_by_count":121},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106},{"id":"2309.07918","title":"Unified Human-Scene Interaction via Prompted Chain-of-Contacts","created":"2023-09-14","cited_by_count":94},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74},{"id":"2205.07982","title":"TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement","created":"2022-05-16","cited_by_count":70},{"id":"2302.05905","title":"Single Motion Diffusion","created":"2023-02-12","cited_by_count":65},{"id":"2303.16479","title":"Visibility Aware Human-Object Interaction Tracking from Single RGB Camera","created":"2023-03-29","cited_by_count":58},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56},{"id":"2307.15042","title":"TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis","created":"2023-07-27","cited_by_count":49},{"id":"1904.02683","title":"Estimating 3D Motion and Forces of Person-Object Interactions from Monocular Video","created":"2019-04-04","cited_by_count":48},{"id":"2306.09337","title":"Generative Proxemics: A Prior for 3D Social Interaction from Images","created":"2023-06-15","cited_by_count":43},{"id":"2003.12045","title":"Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects","created":"2020-03-26","cited_by_count":40},{"id":"2305.20041","title":"Simulation and Retargeting of Complex Multi-Character Interactions","created":"2023-05-31","cited_by_count":34},{"id":"2401.12978","title":"Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models","created":"2024-01-23","cited_by_count":32},{"id":"2205.14313","title":"Learning to Use Chopsticks in Diverse Gripping Styles","created":"2022-05-28","cited_by_count":29},{"id":"2206.12612","title":"Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions","created":"2022-06-25","cited_by_count":21},{"id":"2206.09286","title":"From Universal Humanoid Control to Automatic Physically Valid Character Creation","created":"2022-06-18","cited_by_count":12}],"next_cursor":null}