{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"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":"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":"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":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"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":"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":"1705.02445","title":"On human motion prediction using recurrent neural networks","created":"2017-05-06","cited_by_count":338},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"1905.03244","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","created":"2019-05-08","cited_by_count":270},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"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":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238},{"id":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"1711.09561","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","created":"2017-11-27","cited_by_count":176},{"id":"2007.11755","title":"History Repeats Itself: Human Motion Prediction via Motion Attention","created":"2020-07-23","cited_by_count":165},{"id":"2011.08627","title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","created":"2020-11-17","cited_by_count":163},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","cited_by_count":153},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126},{"id":"2105.01905","title":"4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface","created":"2021-05-05","cited_by_count":124},{"id":"1812.05478","title":"Human Motion Prediction via Spatio-Temporal Inpainting","created":"2018-12-13","cited_by_count":114},{"id":"2104.00683","title":"SimPoE: Simulated Character Control for 3D Human Pose Estimation","created":"2021-04-01","cited_by_count":114},{"id":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91},{"id":"1908.07172","title":"Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation","created":"2019-08-20","cited_by_count":87},{"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":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"id":"1907.02499","title":"Sim2real transfer learning for 3D human pose estimation: motion to the rescue","created":"2019-07-04","cited_by_count":76},{"id":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75},{"id":"2104.07300","title":"Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes","created":"2021-04-15","cited_by_count":65},{"id":"2111.12073","title":"Multi-Person 3D Motion Prediction with Multi-Range Transformers","created":"2021-11-23","cited_by_count":63},{"id":"2312.11461","title":"GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning","created":"2023-12-18","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":"2203.08534","title":"Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video","created":"2022-03-16","cited_by_count":60},{"id":"2103.00776","title":"Single-Shot Motion Completion with Transformer","created":"2021-03-01","cited_by_count":59},{"id":"2203.13349","title":"Occluded Human Mesh Recovery","created":"2022-03-24","cited_by_count":54},{"id":"1810.02363","title":"Recurrent Transition Networks for Character Locomotion","created":"2018-10-04","cited_by_count":52},{"id":"2002.12625","title":"4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras","created":"2020-02-28","cited_by_count":49},{"id":"1906.04158","title":"Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interaction","created":"2019-06-10","cited_by_count":48},{"id":"2303.12337","title":"Music-Driven Group Choreography","created":"2023-03-22","cited_by_count":37},{"id":"2303.09187","title":"PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers","created":"2023-03-16","cited_by_count":32},{"id":"2212.02837","title":"Pretrained Diffusion Models for Unified Human Motion Synthesis","created":"2022-12-06","cited_by_count":26},{"id":"2111.07868","title":"Tracking People with 3D Representations","created":"2021-11-15","cited_by_count":22},{"id":"1903.10153","title":"DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image","created":"2019-03-25","cited_by_count":20},{"id":"2311.18303","title":"OmniMotionGPT: Animal Motion Generation with Limited Data","created":"2023-11-30","cited_by_count":20},{"id":"2308.09611","title":"Language-guided Human Motion Synthesis with Atomic Actions","created":"2023-08-18","cited_by_count":17},{"id":"2110.11460","title":"MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion","created":"2021-10-21","cited_by_count":14},{"id":"2110.11680","title":"Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation","created":"2021-10-22","cited_by_count":7},{"id":"2306.10065","title":"Taming Diffusion Models for Music-driven Conducting Motion Generation","created":"2023-06-15","cited_by_count":7}],"next_cursor":null}