{"list":"other","total":91,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"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":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"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":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2012.15838","title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans","created":"2020-12-31","cited_by_count":634},{"id":"2311.12775","title":"SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering","created":"2023-11-21","cited_by_count":616},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"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":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"2105.02872","title":"Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies","created":"2021-05-06","cited_by_count":361},{"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":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2203.12575","title":"NeuMan: Neural Human Radiance Field from a Single Video","created":"2022-03-23","cited_by_count":244},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2312.02973","title":"GauHuman: Articulated Gaussian Splatting from Monocular Human Videos","created":"2023-12-05","cited_by_count":168},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2311.17910","title":"HUGS: Human Gaussian Splats","created":"2023-11-29","cited_by_count":154},{"id":"2112.11454","title":"GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping","created":"2021-12-21","cited_by_count":144},{"id":"2210.10036","title":"ARAH: Animatable Volume Rendering of Articulated Human SDFs","created":"2022-10-18","cited_by_count":139},{"id":"2212.10550","title":"InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds","created":"2022-12-20","cited_by_count":138},{"id":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2012.05522","title":"Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes","created":"2020-12-10","cited_by_count":135},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","cited_by_count":124},{"id":"2311.16099","title":"GART: Gaussian Articulated Template Models","created":"2023-11-27","cited_by_count":121},{"id":"2311.08581","title":"Drivable 3D Gaussian Avatars","created":"2023-11-14","cited_by_count":120},{"id":"2112.03028","title":"D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions","created":"2021-12-01","cited_by_count":113},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109},{"id":"2106.02019","title":"Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control","created":"2021-06-03","cited_by_count":106},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"2309.07918","title":"Unified Human-Scene Interaction via Prompted Chain-of-Contacts","created":"2023-09-14","cited_by_count":94},{"id":"2312.06553","title":"HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models","created":"2023-12-11","cited_by_count":93},{"id":"2112.10103","title":"SAGA: Stochastic Whole-Body Grasping with Contact","created":"2021-12-19","cited_by_count":91},{"id":"2205.13001","title":"Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis","created":"2022-05-25","cited_by_count":91},{"id":"2304.02001","title":"MonoHuman: Animatable Human Neural Field from Monocular Video","created":"2023-04-04","cited_by_count":85},{"id":"2211.14304","title":"BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction","created":"2022-11-25","cited_by_count":82},{"id":"2204.09443","title":"GIMO: Gaze-Informed Human Motion Prediction in Context","created":"2022-04-20","cited_by_count":81},{"id":"2303.17912","title":"CIRCLE: Capture In Rich Contextual Environments","created":"2023-03-31","cited_by_count":79},{"id":"2307.07511","title":"NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis","created":"2023-07-14","cited_by_count":78},{"id":"2302.12237","title":"Learning Neural Volumetric Representations of Dynamic Humans in Minutes","created":"2023-02-23","cited_by_count":70},{"id":"2206.03287","title":"NeMF: Neural Motion Fields for Kinematic Animation","created":"2022-06-04","cited_by_count":68},{"id":"2302.05905","title":"Single Motion Diffusion","created":"2023-02-12","cited_by_count":65},{"id":"2403.19652","title":"InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction","created":"2024-03-28","cited_by_count":64},{"id":"2303.15469","title":"CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis","created":"2023-03-25","cited_by_count":56},{"id":"2410.03187","title":"Autonomous Character-Scene Interaction Synthesis from Text Instruction","created":"2024-10-04","cited_by_count":56},{"id":"2309.07907","title":"Physically Plausible Full-Body Hand-Object Interaction Synthesis","created":"2023-09-14","cited_by_count":52},{"id":"2301.02667","title":"Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments","created":"2023-01-09","cited_by_count":51},{"id":"2307.15042","title":"TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis","created":"2023-07-27","cited_by_count":49},{"id":"2306.09532","title":"Hierarchical Planning and Control for Box Loco-Manipulation","created":"2023-06-15","cited_by_count":44},{"id":"2203.14402","title":"UV Volumes for Real-time Rendering of Editable Free-view Human Performance","created":"2022-03-27","cited_by_count":43},{"id":"2303.13129","title":"Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations","created":"2023-03-23","cited_by_count":42},{"id":"2311.17737","title":"GenZI: Zero-Shot 3D Human-Scene Interaction Generation","created":"2023-11-29","cited_by_count":40},{"id":"2310.11449","title":"DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis","created":"2023-10-17","cited_by_count":36},{"id":"2401.12978","title":"Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models","created":"2024-01-23","cited_by_count":32},{"id":"2311.16482","title":"Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars","created":"2023-11-27","cited_by_count":30},{"id":"2403.12959","title":"WHAC: World-grounded Humans and Cameras","created":"2024-03-19","cited_by_count":30},{"id":"2206.12612","title":"Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions","created":"2022-06-25","cited_by_count":21}],"next_cursor":null}