{"list":"other","total":67,"rows":[{"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":"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2102.05379","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","created":"2021-02-10","cited_by_count":574},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"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":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"1711.08229","title":"Integral Human Pose Regression","created":"2017-11-22","cited_by_count":256},{"id":"1611.07828","title":"Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose","created":"2016-11-23","cited_by_count":221},{"id":"1904.03345","title":"Semantic Graph Convolutional Networks for 3D Human Pose Regression","created":"2019-04-06","cited_by_count":204},{"id":"2207.06389","title":"ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech","created":"2022-07-13","cited_by_count":149},{"id":"2303.08137","title":"LayoutDM: Discrete Diffusion Model for Controllable Layout Generation","created":"2023-03-14","cited_by_count":143},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131},{"id":"2004.03686","title":"Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation","created":"2020-04-07","cited_by_count":113},{"id":"2103.10022","title":"Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE","created":"2021-03-18","cited_by_count":106},{"id":"2108.10842","title":"imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose","created":"2021-08-24","cited_by_count":103},{"id":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103},{"id":"2211.16940","title":"DiffPose: Toward More Reliable 3D Pose Estimation","created":"2022-11-30","cited_by_count":100},{"id":"2103.16385","title":"Graph Stacked Hourglass Networks for 3D Human Pose Estimation","created":"2021-03-30","cited_by_count":95},{"id":"2303.17472","title":"PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation","created":"2023-03-30","cited_by_count":92},{"id":"1711.08585","title":"Exploiting temporal information for 3D pose estimation","created":"2017-11-23","cited_by_count":89},{"id":"2004.13985","title":"Motion Guided 3D Pose Estimation from Videos","created":"2020-04-29","cited_by_count":85},{"id":"2304.06648","title":"DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning","created":"2023-04-13","cited_by_count":84},{"id":"2303.11579","title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","created":"2023-03-21","cited_by_count":82},{"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":"2308.14480","title":"Priority-Centric Human Motion Generation in Discrete Latent Space","created":"2023-08-28","cited_by_count":67},{"id":"2305.09662","title":"Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation","created":"2023-05-16","cited_by_count":56},{"id":"2307.15139","title":"Online Clustered Codebook","created":"2023-07-27","cited_by_count":55},{"id":"2107.07797","title":"Conditional Directed Graph Convolution for 3D Human Pose Estimation","created":"2021-07-16","cited_by_count":52},{"id":"2011.00980","title":"3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data","created":"2020-11-02","cited_by_count":50},{"id":"2303.11638","title":"Human Pose as Compositional Tokens","created":"2023-03-21","cited_by_count":45},{"id":"2201.07412","title":"Poseur: Direct Human Pose Regression with Transformers","created":"2022-01-19","cited_by_count":43},{"id":"2112.01799","title":"Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation","created":"2021-12-03","cited_by_count":40},{"id":"1607.02046","title":"MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild","created":"2016-07-07","cited_by_count":37},{"id":"2306.00777","title":"Object pop-up: Can we infer 3D objects and their poses from human interactions alone?","created":"2023-06-01","cited_by_count":37},{"id":"2310.05793","title":"DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models","created":"2023-10-09","cited_by_count":36},{"id":"2008.06046","title":"Full-Body Awareness from Partial Observations","created":"2020-08-13","cited_by_count":29},{"id":"1608.03075","title":"3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information","created":"2016-08-10","cited_by_count":28},{"id":"2308.10123","title":"3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation","created":"2023-08-19","cited_by_count":28},{"id":"2006.14107","title":"Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation","created":"2020-06-24","cited_by_count":26},{"id":"2307.03833","title":"Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation","created":"2023-07-07","cited_by_count":24},{"id":"2405.14201","title":"FreeTuner: Any Subject in Any Style with Training-free Diffusion","created":"2024-05-23","cited_by_count":24},{"id":"1808.09316","title":"How Robust is 3D Human Pose Estimation to Occlusion?","created":"2018-08-28","cited_by_count":23},{"id":"2012.11806","title":"Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos","created":"2020-12-22","cited_by_count":23},{"id":"2212.07729","title":"HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving","created":"2022-12-15","cited_by_count":22},{"id":"2208.07755","title":"PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation","created":"2022-08-16","cited_by_count":14},{"id":"2311.03312","title":"A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation","created":"2023-11-06","cited_by_count":11},{"id":"2303.15742","title":"System-status-aware Adaptive Network for Online Streaming Video Understanding","created":"2023-03-28","cited_by_count":9},{"id":"2111.11969","title":"Lifting 2D Human Pose to 3D with Domain Adapted 3D Body Concept","created":"2021-11-23","cited_by_count":4}],"next_cursor":null}