{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"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":"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":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"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":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"1907.10786","title":"Interpreting the Latent Space of GANs for Semantic Face Editing","created":"2019-07-25","cited_by_count":695},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"1903.08527","title":"Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set","created":"2019-03-20","cited_by_count":482},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2104.14951","title":"SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models","created":"2021-04-30","cited_by_count":415},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2208.04202","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","created":"2022-08-08","cited_by_count":373},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"1807.10267","title":"Generating 3D faces using Convolutional Mesh Autoencoders","created":"2018-07-26","cited_by_count":268},{"id":"1805.11714","title":"Deep Video Portraits","created":"2018-05-29","cited_by_count":267},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2211.12446","title":"EDICT: Exact Diffusion Inversion via Coupled Transformations","created":"2022-11-22","cited_by_count":258},{"id":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238},{"id":"2206.09012","title":"Diffusion models as plug-and-play priors","created":"2022-06-17","cited_by_count":231},{"id":"2009.09960","title":"Towards Fast, Accurate and Stable 3D Dense Face Alignment","created":"2020-09-21","cited_by_count":219},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2206.02262","title":"Diffusion-GAN: Training GANs with Diffusion","created":"2022-06-05","cited_by_count":205},{"id":"1803.07835","title":"Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network","created":"2018-03-21","cited_by_count":195},{"id":"2004.14367","title":"Editing in Style: Uncovering the Local Semantics of GANs","created":"2020-04-29","cited_by_count":183},{"id":"1807.09251","title":"GANimation: Anatomically-aware Facial Animation from a Single Image","created":"2018-07-24","cited_by_count":161},{"id":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111},{"id":"2201.00308","title":"DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents","created":"2022-01-02","cited_by_count":104},{"id":"2112.03530","title":"A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion","created":"2021-12-07","cited_by_count":100},{"id":"1905.02876","title":"Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation","created":"2019-05-08","cited_by_count":90},{"id":"1902.09887","title":"Disentangled Representation Learning for 3D Face Shape","created":"2019-02-26","cited_by_count":48},{"id":"1703.10155","title":"CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training","created":"2017-03-29","cited_by_count":42},{"id":"1802.01873","title":"Every Smile is Unique: Landmark-Guided Diverse Smile Generation","created":"2018-02-06","cited_by_count":23},{"id":"1907.10087","title":"Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets","created":"2019-07-23","cited_by_count":19},{"id":"2105.07463","title":"Sparse to Dense Dynamic 3D Facial Expression Generation","created":"2021-05-16","cited_by_count":19},{"id":"2008.05110","title":"Facial Expression Retargeting from Human to Avatar Made Easy","created":"2020-08-12","cited_by_count":13},{"id":"2007.09805","title":"Learning to Generate Customized Dynamic 3D Facial Expressions","created":"2020-07-19","cited_by_count":11},{"id":"2002.02194","title":"Joint Deep Learning of Facial Expression Synthesis and Recognition","created":"2020-02-06","cited_by_count":6},{"id":"2210.11182","title":"Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN","created":"2022-10-20","cited_by_count":4}],"next_cursor":null}