{"list":"other","total":63,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"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":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"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":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"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":"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":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"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":"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":"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":"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":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"id":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229},{"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":"2008.08535","title":"STAR: Sparse Trained Articulated Human Body Regressor","created":"2020-08-19","cited_by_count":194},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"id":"2003.08325","title":"DeepCap: Monocular Human Performance Capture Using Weak Supervision","created":"2020-03-18","cited_by_count":162},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"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":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111},{"id":"1703.08014","title":"Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs","created":"2017-03-23","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":"1810.02648","title":"LiveCap: Real-time Human Performance Capture from Monocular Video","created":"2018-10-05","cited_by_count":93},{"id":"1707.07548","title":"Towards Accurate Markerless Human Shape and Pose Estimation over Time","created":"2017-07-24","cited_by_count":92},{"id":"1904.09882","title":"You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions","created":"2019-04-22","cited_by_count":82},{"id":"2210.10542","title":"PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting","created":"2022-10-19","cited_by_count":78},{"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":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75},{"id":"2105.14804","title":"Scene-aware Generative Network for Human Motion Synthesis","created":"2021-05-31","cited_by_count":70},{"id":"2007.06559","title":"Graph Structure of Neural Networks","created":"2020-07-13","cited_by_count":68},{"id":"1908.11505","title":"EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera","created":"2019-08-30","cited_by_count":65},{"id":"1708.02136","title":"MonoPerfCap: Human Performance Capture from Monocular Video","created":"2017-08-07","cited_by_count":63},{"id":"2008.06910","title":"Neural Descent for Visual 3D Human Pose and Shape","created":"2020-08-16","cited_by_count":60},{"id":"2103.00776","title":"Single-Shot Motion Completion with Transformer","created":"2021-03-01","cited_by_count":59},{"id":"1704.04793","title":"Harvesting Multiple Views for Marker-less 3D Human Pose Annotations","created":"2017-04-16","cited_by_count":48},{"id":"1810.04703","title":"Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time","created":"2018-10-10","cited_by_count":47},{"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":"2210.01448","title":"Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings","created":"2022-10-04","cited_by_count":38},{"id":"2211.15603","title":"Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation","created":"2022-11-28","cited_by_count":28},{"id":"2103.06747","title":"ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References","created":"2021-03-11","cited_by_count":26},{"id":"2105.04605","title":"TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors","created":"2021-05-10","cited_by_count":25},{"id":"1610.09534","title":"FlyCap: Markerless Motion Capture Using Multiple Autonomous Flying Cameras","created":"2016-10-29","cited_by_count":23},{"id":"2203.09287","title":"HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions","created":"2022-03-17","cited_by_count":19},{"id":"2210.15134","title":"Learning Variational Motion Prior for Video-based Motion Capture","created":"2022-10-27","cited_by_count":17},{"id":"1610.06740","title":"Model-based Outdoor Performance Capture","created":"2016-10-21","cited_by_count":13}],"next_cursor":null}