{"list":"other","total":59,"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":"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":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2202.09778","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","created":"2022-02-20","cited_by_count":700},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"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":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"1904.01310","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","created":"2019-04-02","cited_by_count":308},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"2109.06977","title":"Design Guidelines for Prompt Engineering Text-to-Image Generative Models","created":"2021-09-14","cited_by_count":218},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2201.02610","title":"Embodied Hands: Modeling and Capturing Hands and Bodies Together","created":"2022-01-07","cited_by_count":181},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"2008.05865","title":"DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis","created":"2020-08-13","cited_by_count":162},{"id":"2006.10214","title":"MediaPipe Hands: On-device Real-time Hand Tracking","created":"2020-06-18","cited_by_count":161},{"id":"2112.11454","title":"GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping","created":"2021-12-21","cited_by_count":144},{"id":"1511.02793","title":"Generating Images from Captions with Attention","created":"2015-11-09","cited_by_count":136},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","cited_by_count":124},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"1908.09186","title":"Efficient Learning on Point Clouds with Basis Point Sets","created":"2019-08-24","cited_by_count":103},{"id":"2205.07982","title":"TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement","created":"2022-05-16","cited_by_count":70},{"id":"2107.02423","title":"Improving Text-to-Image Synthesis Using Contrastive Learning","created":"2021-07-06","cited_by_count":62},{"id":"2205.08535","title":"AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars","created":"2022-05-17","cited_by_count":55},{"id":"2309.08942","title":"AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose","created":"2023-09-16","cited_by_count":49},{"id":"2303.05725","title":"CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment","created":"2023-03-10","cited_by_count":45},{"id":"2206.08219","title":"HaGRID - HAnd Gesture Recognition Image Dataset","created":"2022-06-16","cited_by_count":43},{"id":"2206.04382","title":"CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes","created":"2022-06-09","cited_by_count":41},{"id":"2309.08480","title":"PoseFix: Correcting 3D Human Poses with Natural Language","created":"2023-09-15","cited_by_count":40},{"id":"2010.09676","title":"Detecting Hands and Recognizing Physical Contact in the Wild","created":"2020-10-19","cited_by_count":38},{"id":"2211.15663","title":"Hand-Object Interaction Image Generation","created":"2022-11-28","cited_by_count":19},{"id":"2106.01981","title":"ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics","created":"2021-06-03","cited_by_count":17},{"id":"1904.04882","title":"Contextual Attention for Hand Detection in the Wild","created":"2019-04-09","cited_by_count":16}],"next_cursor":null}