{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"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":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"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":"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":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"2208.04202","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","created":"2022-08-08","cited_by_count":373},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"2112.00390","title":"SegDiff: Image Segmentation with Diffusion Probabilistic Models","created":"2021-12-01","cited_by_count":280},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2207.06389","title":"ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech","created":"2022-07-13","cited_by_count":149},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131},{"id":"2012.14214","title":"TransPose: Keypoint Localization via Transformer","created":"2020-12-28","cited_by_count":126},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99},{"id":"1802.00977","title":"Pose Flow: Efficient Online Pose Tracking","created":"2018-02-03","cited_by_count":80},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75},{"id":"1506.02897","title":"Flowing ConvNets for Human Pose Estimation in Videos","created":"2015-06-09","cited_by_count":55},{"id":"2204.13062","title":"Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution","created":"2022-04-27","cited_by_count":54},{"id":"1712.09184","title":"Detect-and-Track: Efficient Pose Estimation in Videos","created":"2017-12-26","cited_by_count":51},{"id":"2103.07254","title":"Deep Dual Consecutive Network for Human Pose Estimation","created":"2021-03-12","cited_by_count":51},{"id":"2003.13743","title":"Combining detection and tracking for human pose estimation in videos","created":"2020-03-30","cited_by_count":49},{"id":"2212.02773","title":"DiffusionInst: Diffusion Model for Instance Segmentation","created":"2022-12-06","cited_by_count":49},{"id":"1611.07727","title":"PoseTrack: Joint Multi-Person Pose Estimation and Tracking","created":"2016-11-23","cited_by_count":44},{"id":"1703.10898","title":"Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos","created":"2017-03-31","cited_by_count":40},{"id":"1906.04016","title":"Learning Temporal Pose Estimation from Sparsely-Labeled Videos","created":"2019-06-06","cited_by_count":39},{"id":"1903.09214","title":"Multi-person Articulated Tracking with Spatial and Temporal Embeddings","created":"2019-03-21","cited_by_count":38},{"id":"2106.03772","title":"Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking","created":"2021-06-07","cited_by_count":37},{"id":"1811.11975","title":"Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields","created":"2018-11-29","cited_by_count":32},{"id":"1712.06316","title":"LSTM Pose Machines","created":"2017-12-18","cited_by_count":28},{"id":"2105.04154","title":"Unsupervised Human Pose Estimation through Transforming Shape Templates","created":"2021-05-10","cited_by_count":26},{"id":"2203.15227","title":"Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation","created":"2022-03-29","cited_by_count":24},{"id":"2004.12652","title":"Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos","created":"2020-04-27","cited_by_count":22},{"id":"1810.08338","title":"Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking","created":"2018-10-19","cited_by_count":21},{"id":"2212.02024","title":"Fine-grained Image Editing by Pixel-wise Guidance Using Diffusion Models","created":"2022-12-05","cited_by_count":18},{"id":"2303.08475","title":"Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video","created":"2023-03-15","cited_by_count":17},{"id":"1908.05593","title":"FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks","created":"2019-08-15","cited_by_count":15},{"id":"1305.2269","title":"Beyond Physical Connections: Tree Models in Human Pose Estimation","created":"2013-05-10","cited_by_count":14},{"id":"1905.09500","title":"Pose estimator and tracker using temporal flow maps for limbs","created":"2019-05-23","cited_by_count":13},{"id":"2208.00874","title":"S$^2$Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning","created":"2022-08-01","cited_by_count":8}],"next_cursor":null}