{"list":"other","total":51,"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"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":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2209.02646","title":"A Survey on Generative Diffusion Model","created":"2022-09-06","cited_by_count":240},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2209.14491","title":"Re-Imagen: Retrieval-Augmented Text-to-Image Generator","created":"2022-09-29","cited_by_count":210},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"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":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","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":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138},{"id":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111},{"id":"2312.15004","title":"FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing","created":"2023-12-22","cited_by_count":106},{"id":"2207.01567","title":"Back to MLP: A Simple Baseline for Human Motion Prediction","created":"2022-07-04","cited_by_count":100},{"id":"2309.07918","title":"Unified Human-Scene Interaction via Prompted Chain-of-Contacts","created":"2023-09-14","cited_by_count":94},{"id":"2209.07556","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","created":"2022-09-15","cited_by_count":84},{"id":"2006.06119","title":"Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning","created":"2020-06-11","cited_by_count":81},{"id":"2302.03665","title":"HumanMAC: Masked Motion Completion for Human Motion Prediction","created":"2023-02-07","cited_by_count":81},{"id":"2203.16051","title":"Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction","created":"2022-03-30","cited_by_count":66},{"id":"2203.13694","title":"Implicit Neural Representations for Variable Length Human Motion Generation","created":"2022-03-25","cited_by_count":61},{"id":"1903.03369","title":"Analyzing Input and Output Representations for Speech-Driven Gesture Generation","created":"2019-03-08","cited_by_count":52},{"id":"2312.04547","title":"Digital Life Project: Autonomous 3D Characters with Social Intelligence","created":"2023-12-07","cited_by_count":43},{"id":"2403.12835","title":"AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents","created":"2024-03-19","cited_by_count":32},{"id":"2007.01971","title":"Structure-Aware Human-Action Generation","created":"2020-07-04","cited_by_count":28},{"id":"2312.02700","title":"Revisit Human-Scene Interaction via Space Occupancy","created":"2023-12-05","cited_by_count":25},{"id":"2110.11191","title":"Generative Adversarial Graph Convolutional Networks for Human Action Synthesis","created":"2021-10-21","cited_by_count":23},{"id":"2207.08164","title":"Action-conditioned On-demand Motion Generation","created":"2022-07-17","cited_by_count":18},{"id":"2312.04867","title":"HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models","created":"2023-12-08","cited_by_count":13},{"id":"2312.11850","title":"GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction","created":"2023-12-19","cited_by_count":12},{"id":"2301.10134","title":"Bipartite Graph Diffusion Model for Human Interaction Generation","created":"2023-01-24","cited_by_count":11},{"id":"2401.10242","title":"DanceMeld: Unraveling Dance Phrases with Hierarchical Latent Codes for Music-to-Dance Synthesis","created":"2023-11-30","cited_by_count":4}],"next_cursor":null}