{"list":"other","total":129,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"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":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"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":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"1705.02445","title":"On human motion prediction using recurrent neural networks","created":"2017-05-06","cited_by_count":338},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"1711.08447","title":"VITON: An Image-based Virtual Try-on Network","created":"2017-11-22","cited_by_count":286},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252},{"id":"1908.05436","title":"Learning Trajectory Dependencies for Human Motion Prediction","created":"2019-08-15","cited_by_count":246},{"id":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"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":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2009.02119","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","created":"2020-09-04","cited_by_count":202},{"id":"2008.08535","title":"STAR: Sparse Trained Articulated Human Body Regressor","created":"2020-08-19","cited_by_count":194},{"id":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178},{"id":"1711.09561","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","created":"2017-11-27","cited_by_count":176},{"id":"1905.05754","title":"Learnable Triangulation of Human Pose","created":"2019-05-14","cited_by_count":161},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"id":"2003.08802","title":"Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction","created":"2020-03-17","cited_by_count":132},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117},{"id":"2309.00796","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","created":"2023-09-02","cited_by_count":117},{"id":"2310.04582","title":"Universal Humanoid Motion Representations for Physics-Based Control","created":"2023-10-06","cited_by_count":116},{"id":"2012.00619","title":"We are More than Our Joints: Predicting how 3D Bodies Move","created":"2020-12-01","cited_by_count":115},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"1810.12541","title":"Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots","created":"2018-10-30","cited_by_count":110},{"id":"1805.06485","title":"QuaterNet: A Quaternion-based Recurrent Model for Human Motion","created":"2018-05-16","cited_by_count":109},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"2312.15004","title":"FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing","created":"2023-12-22","cited_by_count":106},{"id":"2308.08545","title":"TeCH: Text-guided Reconstruction of Lifelike Clothed Humans","created":"2023-08-16","cited_by_count":104},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90},{"id":"2404.00562","title":"Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction","created":"2024-03-31","cited_by_count":86},{"id":"1804.08264","title":"To Create What You Tell: Generating Videos from Captions","created":"2018-04-23","cited_by_count":84},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81},{"id":"2404.10685","title":"Generating Human Interaction Motions in Scenes with Text Control","created":"2024-04-16","cited_by_count":80},{"id":"2203.07706","title":"ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation","created":"2022-03-15","cited_by_count":77},{"id":"2211.16016","title":"UDE: A Unified Driving Engine for Human Motion Generation","created":"2022-11-29","cited_by_count":67},{"id":"2308.14480","title":"Priority-Centric Human Motion Generation in Discrete Latent Space","created":"2023-08-28","cited_by_count":67},{"id":"2007.12553","title":"Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach","created":"2020-07-24","cited_by_count":65},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2408.00712","title":"MotionFix: Text-Driven 3D Human Motion Editing","created":"2024-08-01","cited_by_count":64},{"id":"2311.16468","title":"AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond","created":"2023-11-28","cited_by_count":63},{"id":"2203.13694","title":"Implicit Neural Representations for Variable Length Human Motion Generation","created":"2022-03-25","cited_by_count":61},{"id":"2410.21747","title":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","created":"2024-10-29","cited_by_count":59},{"id":"2403.19435","title":"BAMM: Bidirectional Autoregressive Motion Model","created":"2024-03-28","cited_by_count":55},{"id":"2304.08483","title":"Text2Performer: Text-Driven Human Video Generation","created":"2023-04-17","cited_by_count":53},{"id":"2106.09336","title":"THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers","created":"2021-06-17","cited_by_count":50},{"id":"2405.17013","title":"Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs","created":"2024-05-27","cited_by_count":47},{"id":"2210.15929","title":"Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training","created":"2022-10-28","cited_by_count":45},{"id":"2212.05897","title":"MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels","created":"2022-12-12","cited_by_count":45},{"id":"2303.11726","title":"3D Human Mesh Estimation from Virtual Markers","created":"2023-03-21","cited_by_count":44},{"id":"2207.10955","title":"Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection","created":"2022-07-22","cited_by_count":39},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39},{"id":"2003.12590","title":"word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Data","created":"2020-03-27","cited_by_count":38},{"id":"2410.10780","title":"MaskControl: Spatio-Temporal Control for Masked Motion Synthesis","created":"2024-10-14","cited_by_count":38},{"id":"2108.11244","title":"Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction","created":"2021-08-25","cited_by_count":37},{"id":"2304.02777","title":"MoStGAN-V: Video Generation with Temporal Motion Styles","created":"2023-04-05","cited_by_count":37},{"id":"2410.00464","title":"Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation","created":"2024-10-01","cited_by_count":35},{"id":"1902.07367","title":"Human Motion Prediction via Learning Local Structure Representations and Temporal Dependencies","created":"2019-02-20","cited_by_count":34},{"id":"2312.05295","title":"Disentangled Clothed Avatar Generation from Text Descriptions","created":"2023-12-08","cited_by_count":33},{"id":"2203.01593","title":"3D Human Motion Prediction: A Survey","created":"2022-03-03","cited_by_count":30},{"id":"2305.09381","title":"AMD: Autoregressive Motion Diffusion","created":"2023-05-16","cited_by_count":30},{"id":"2404.01700","title":"MotionChain: Conversational Motion Controllers via Multimodal Prompts","created":"2024-04-02","cited_by_count":30},{"id":"2007.09268","title":"3D Human Shape Reconstruction from a Polarization Image","created":"2020-07-17","cited_by_count":28},{"id":"2208.09191","title":"Synthetic Data in Human Analysis: A Survey","created":"2022-08-19","cited_by_count":28},{"id":"2212.02837","title":"Pretrained Diffusion Models for Unified Human Motion Synthesis","created":"2022-12-06","cited_by_count":26},{"id":"2312.14828","title":"Plan, Posture and Go: Towards Open-World Text-to-Motion Generation","created":"2023-12-22","cited_by_count":26},{"id":"2407.14502","title":"M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models","created":"2024-07-19","cited_by_count":24},{"id":"2103.09755","title":"Aggregated Multi-GANs for Controlled 3D Human Motion Prediction","created":"2021-03-17","cited_by_count":23},{"id":"2407.10061","title":"InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation","created":"2024-07-14","cited_by_count":23},{"id":"2303.13472","title":"Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models","created":"2023-03-23","cited_by_count":22},{"id":"2401.02142","title":"GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation","created":"2024-01-04","cited_by_count":22},{"id":"2312.12634","title":"MotionScript: Natural Language Descriptions for Expressive 3D Human Motions","created":"2023-12-19","cited_by_count":21}],"next_cursor":"100"}