{"list":"other","total":92,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","cited_by_count":521},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"1908.05932","title":"FSGAN: Subject Agnostic Face Swapping and Reenactment","created":"2019-08-16","cited_by_count":320},{"id":"2312.02981","title":"ReconFusion: 3D Reconstruction with Diffusion Priors","created":"2023-12-05","cited_by_count":318},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2304.02602","title":"Generative Novel View Synthesis with 3D-Aware Diffusion Models","created":"2023-04-05","cited_by_count":274},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2312.02201","title":"ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation","created":"2023-12-02","cited_by_count":257},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2004.11660","title":"Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning","created":"2020-04-24","cited_by_count":220},{"id":"1910.11006","title":"Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison","created":"2019-10-24","cited_by_count":218},{"id":"2212.00792","title":"SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction","created":"2022-12-01","cited_by_count":216},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200},{"id":"2311.16933","title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","created":"2023-11-28","cited_by_count":175},{"id":"1801.00055","title":"Deformable GANs for Pose-based Human Image Generation","created":"2017-12-29","cited_by_count":166},{"id":"2211.09869","title":"RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation","created":"2022-11-17","cited_by_count":162},{"id":"2408.06070","title":"ControlNeXt: Powerful and Efficient Control for Image and Video Generation","created":"2024-08-12","cited_by_count":159},{"id":"2411.04928","title":"DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion","created":"2024-11-07","cited_by_count":140},{"id":"2210.02697","title":"DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation","created":"2022-10-06","cited_by_count":137},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115},{"id":"2310.17994","title":"ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image","created":"2023-10-27","cited_by_count":111},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68},{"id":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64},{"id":"2312.01305","title":"ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models","created":"2023-12-03","cited_by_count":58},{"id":"2206.08219","title":"HaGRID - HAnd Gesture Recognition Image Dataset","created":"2022-06-16","cited_by_count":43},{"id":"2311.17957","title":"HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting","created":"2023-11-29","cited_by_count":42},{"id":"2403.01693","title":"HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances","created":"2024-03-04","cited_by_count":42},{"id":"2310.17768","title":"A Dataset of Relighted 3D Interacting Hands","created":"2023-10-26","cited_by_count":35},{"id":"2404.14403","title":"GeoDiffuser: Geometry-Based Image Editing with Diffusion Models","created":"2024-04-22","cited_by_count":34},{"id":"1906.01314","title":"Example-Guided Style Consistent Image Synthesis from Semantic Labeling","created":"2019-06-04","cited_by_count":29},{"id":"1808.04859","title":"GestureGAN for Hand Gesture-to-Gesture Translation in the Wild","created":"2018-08-14","cited_by_count":27},{"id":"2312.02137","title":"MANUS: Markerless Grasp Capture using Articulated 3D Gaussians","created":"2023-12-04","cited_by_count":26},{"id":"2210.07650","title":"DART: Articulated Hand Model with Diverse Accessories and Rich Textures","created":"2022-10-14","cited_by_count":25},{"id":"2304.12483","title":"Towards Realistic Generative 3D Face Models","created":"2023-04-24","cited_by_count":20},{"id":"2406.18958","title":"AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation","created":"2024-06-27","cited_by_count":20},{"id":"2408.07147","title":"Controlling the World by Sleight of Hand","created":"2024-08-13","cited_by_count":19},{"id":"2307.16897","title":"DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields","created":"2023-07-31","cited_by_count":17},{"id":"2309.09301","title":"RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimation","created":"2023-09-17","cited_by_count":16},{"id":"2309.05662","title":"ViHOPE: Visuotactile In-Hand Object 6D Pose Estimation with Shape Completion","created":"2023-09-11","cited_by_count":14},{"id":"2106.10876","title":"Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes","created":"2021-06-21","cited_by_count":12},{"id":"2408.15461","title":"Hand1000: Generating Realistic Hands from Text with Only 1,000 Images","created":"2024-08-28","cited_by_count":11},{"id":"2407.18034","title":"AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild","created":"2024-07-25","cited_by_count":10},{"id":"2409.03644","title":"RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images","created":"2024-09-05","cited_by_count":10},{"id":"1901.02284","title":"Unpaired Pose Guided Human Image Generation","created":"2019-01-08","cited_by_count":8},{"id":"2208.14263","title":"Controllable 3D Generative Adversarial Face Model via Disentangling Shape and Appearance","created":"2022-08-30","cited_by_count":8},{"id":"2410.13911","title":"GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction","created":"2024-10-17","cited_by_count":8},{"id":"2304.00761","title":"Learning Anchor Transformations for 3D Garment Animation","created":"2023-04-03","cited_by_count":7},{"id":"2406.10167","title":"4DRecons: 4D Neural Implicit Deformable Objects Reconstruction from a single RGB-D Camera with Geometrical and Topological Regularizations","created":"2024-06-14","cited_by_count":5},{"id":"2411.04332","title":"HandCraft: Anatomically Correct Restoration of Malformed Hands in Diffusion Generated Images","created":"2024-11-07","cited_by_count":5},{"id":"1802.00613","title":"Effects of Hand Representations for Typing in Virtual Reality","created":"2018-02-02","cited_by_count":4},{"id":"2404.04643","title":"Constrained 6-DoF Grasp Generation on Complex Shapes for Improved Dual-Arm Manipulation","created":"2024-04-06","cited_by_count":4},{"id":"2311.17878","title":"TSDF-Sampling: Efficient Sampling for Neural Surface Field using Truncated Signed Distance Field","created":"2023-11-29","cited_by_count":3}],"next_cursor":null}