{"list":"other","total":72,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"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":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"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":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"1711.08447","title":"VITON: An Image-based Virtual Try-on Network","created":"2017-11-22","cited_by_count":286},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"id":"1910.11006","title":"Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison","created":"2019-10-24","cited_by_count":218},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"1904.07223","title":"Joint Discriminative and Generative Learning for Person Re-identification","created":"2019-04-15","cited_by_count":213},{"id":"1611.05424","title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","created":"2016-11-16","cited_by_count":212},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2008.08143","title":"How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language","created":"2020-08-18","cited_by_count":173},{"id":"1803.08225","title":"PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model","created":"2018-03-22","cited_by_count":133},{"id":"1903.06593","title":"PifPaf: Composite Fields for Human Pose Estimation","created":"2019-03-15","cited_by_count":120},{"id":"2004.14874","title":"Progressive Transformers for End-to-End Sign Language Production","created":"2020-04-30","cited_by_count":120},{"id":"1511.06645","title":"DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation","created":"2015-11-20","cited_by_count":117},{"id":"2007.12131","title":"BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues","created":"2020-07-23","cited_by_count":106},{"id":"1802.00977","title":"Pose Flow: Efficient Online Pose Tracking","created":"2018-02-03","cited_by_count":80},{"id":"2004.00945","title":"PaStaNet: Toward Human Activity Knowledge Engine","created":"2020-04-02","cited_by_count":80},{"id":"2010.05468","title":"TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation","created":"2020-10-12","cited_by_count":75},{"id":"2002.03187","title":"Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition","created":"2020-02-08","cited_by_count":74},{"id":"1807.11152","title":"Pose Guided Human Video Generation","created":"2018-07-30","cited_by_count":67},{"id":"2101.12195","title":"Playable Video Generation","created":"2021-01-28","cited_by_count":64},{"id":"2203.15354","title":"Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production","created":"2022-03-29","cited_by_count":61},{"id":"2110.05382","title":"SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition","created":"2021-10-11","cited_by_count":60},{"id":"2007.12402","title":"Fully Convolutional Networks for Continuous Sign Language Recognition","created":"2020-07-24","cited_by_count":58},{"id":"2008.12405","title":"Adversarial Training for Multi-Channel Sign Language Production","created":"2020-08-27","cited_by_count":57},{"id":"1506.02897","title":"Flowing ConvNets for Human Pose Estimation in Videos","created":"2015-06-09","cited_by_count":55},{"id":"2103.02440","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","created":"2021-03-03","cited_by_count":55},{"id":"2012.03796","title":"Pose-Guided Human Animation from a Single Image in the Wild","created":"2020-12-07","cited_by_count":53},{"id":"2107.11317","title":"Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives","created":"2021-07-23","cited_by_count":50},{"id":"2001.08095","title":"UniPose: Unified Human Pose Estimation in Single Images and Videos","created":"2020-01-22","cited_by_count":49},{"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":"2008.10428","title":"Global-local Enhancement Network for NMFs-aware Sign Language Recognition","created":"2020-08-24","cited_by_count":38},{"id":"2012.00781","title":"Pose-based Sign Language Recognition using GCN and BERT","created":"2020-12-01","cited_by_count":37},{"id":"2011.09846","title":"Everybody Sign Now: Translating Spoken Language to Photo Realistic Sign Language Video","created":"2020-11-19","cited_by_count":34},{"id":"2006.04569","title":"Parameter-Efficient Person Re-identification in the 3D Space","created":"2020-06-08","cited_by_count":33},{"id":"1807.08260","title":"Macro-Micro Adversarial Network for Human Parsing","created":"2018-07-22","cited_by_count":28},{"id":"1904.00129","title":"Dance Dance Generation: Motion Transfer for Internet Videos","created":"2019-03-30","cited_by_count":28},{"id":"2109.00471","title":"Sparse to Dense Motion Transfer for Face Image Animation","created":"2021-09-01","cited_by_count":25},{"id":"1511.06676","title":"Personalizing Human Video Pose Estimation","created":"2015-11-20","cited_by_count":16},{"id":"2107.10685","title":"AnonySIGN: Novel Human Appearance Synthesis for Sign Language Video Anonymisation","created":"2021-07-22","cited_by_count":16},{"id":"2110.06161","title":"Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble","created":"2021-10-12","cited_by_count":16},{"id":"2006.09788","title":"Sketch-Guided Scenery Image Outpainting","created":"2020-06-17","cited_by_count":12},{"id":"2012.10941","title":"Can Everybody Sign Now? Exploring Sign Language Video Generation from 2D Poses","created":"2020-12-20","cited_by_count":12},{"id":"2108.01578","title":"SPG-VTON: Semantic Prediction Guidance for Multi-pose Virtual Try-on","created":"2021-08-03","cited_by_count":12},{"id":"2105.05066","title":"ChaLearn LAP Large Scale Signer Independent Isolated Sign Language Recognition Challenge: Design, Results and Future Research","created":"2021-05-11","cited_by_count":10},{"id":"2110.00988","title":"Keypoint Communities","created":"2021-10-03","cited_by_count":8},{"id":"2110.00453","title":"Phonology Recognition in American Sign Language","created":"2021-10-01","cited_by_count":5}],"next_cursor":null}