{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"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":"2006.06676","title":"Training Generative Adversarial Networks with Limited Data","created":"2020-06-11","cited_by_count":1186},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1709.04875","title":"Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting","created":"2017-09-14","cited_by_count":1136},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"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":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"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":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142},{"id":"2012.05522","title":"Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes","created":"2020-12-10","cited_by_count":135},{"id":"1912.02923","title":"Generating 3D People in Scenes without People","created":"2019-12-05","cited_by_count":127},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83},{"id":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79},{"id":"2105.14804","title":"Scene-aware Generative Network for Human Motion Synthesis","created":"2021-05-31","cited_by_count":70},{"id":"2003.01888","title":"MoVi: A Large Multipurpose Motion and Video Dataset","created":"2020-03-04","cited_by_count":58},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53},{"id":"2305.04835","title":"How Do In-Context Examples Affect Compositional Generalization?","created":"2023-05-08","cited_by_count":51},{"id":"2205.15410","title":"LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors","created":"2022-05-30","cited_by_count":44},{"id":"2403.13307","title":"LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment","created":"2024-03-20","cited_by_count":33},{"id":"2303.17948","title":"CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions","created":"2023-03-31","cited_by_count":27},{"id":"2112.06909","title":"Hallucinating Pose-Compatible Scenes","created":"2021-12-13","cited_by_count":14},{"id":"2401.10822","title":"ActAnywhere: Subject-Aware Video Background Generation","created":"2024-01-19","cited_by_count":8}],"next_cursor":null}