{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"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":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2209.14734","title":"DiGress: Discrete Denoising diffusion for graph generation","created":"2022-09-29","cited_by_count":520},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","created":"2017-05-08","cited_by_count":401},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"2202.02514","title":"Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations","created":"2022-02-05","cited_by_count":283},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"2003.00638","title":"Permutation Invariant Graph Generation via Score-Based Generative Modeling","created":"2020-03-02","cited_by_count":270},{"id":"2111.13606","title":"Conditional Image Generation with Score-Based Diffusion Models","created":"2021-11-26","cited_by_count":197},{"id":"2203.00859","title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","created":"2022-03-02","cited_by_count":159},{"id":"2111.12707","title":"MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation","created":"2021-11-24","cited_by_count":151},{"id":"2207.06389","title":"ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech","created":"2022-07-13","cited_by_count":149},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100},{"id":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99},{"id":"1904.04812","title":"Unsupervised 3D Pose Estimation with Geometric Self-Supervision","created":"2019-04-09","cited_by_count":95},{"id":"2007.09389","title":"SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach","created":"2020-07-18","cited_by_count":94},{"id":"2103.14304","title":"Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation","created":"2021-03-26","cited_by_count":94},{"id":"1904.05547","title":"Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network","created":"2019-04-11","cited_by_count":92},{"id":"1902.09868","title":"RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation","created":"2019-02-26","cited_by_count":85},{"id":"2004.13985","title":"Motion Guided 3D Pose Estimation from Videos","created":"2020-04-29","cited_by_count":85},{"id":"2107.13788","title":"Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows","created":"2021-07-29","cited_by_count":85},{"id":"2203.07628","title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","created":"2022-03-15","cited_by_count":80},{"id":"1904.01324","title":"Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking","created":"2019-04-02","cited_by_count":76},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75},{"id":"2211.16487","title":"DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models","created":"2022-11-29","cited_by_count":65},{"id":"2107.07797","title":"Conditional Directed Graph Convolution for 3D Human Pose Estimation","created":"2021-07-16","cited_by_count":52},{"id":"2205.15370","title":"Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data","created":"2022-05-30","cited_by_count":35},{"id":"1702.02258","title":"Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detections","created":"2017-02-08","cited_by_count":30},{"id":"2212.02796","title":"DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model","created":"2022-12-06","cited_by_count":29},{"id":"2006.14107","title":"Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation","created":"2020-06-24","cited_by_count":26},{"id":"2010.13668","title":"GraphMDN: Leveraging graph structure and deep learning to solve inverse problems","created":"2020-10-26","cited_by_count":26},{"id":"2008.05770","title":"Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses","created":"2020-08-13","cited_by_count":25},{"id":"2203.11471","title":"Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization","created":"2022-03-22","cited_by_count":25},{"id":"2206.02246","title":"Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models","created":"2022-06-05","cited_by_count":20},{"id":"2107.13994","title":"Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation","created":"2021-07-29","cited_by_count":18},{"id":"2111.15056","title":"Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning","created":"2021-11-30","cited_by_count":17}],"next_cursor":null}