{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"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":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"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":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"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":"1807.05118","title":"Tune: A Research Platform for Distributed Model Selection and Training","created":"2018-07-13","cited_by_count":395},{"id":"1912.03458","title":"Dynamic Convolution: Attention over Convolution Kernels","created":"2019-12-07","cited_by_count":356},{"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":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"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":"1905.05754","title":"Learnable Triangulation of Human Pose","created":"2019-05-14","cited_by_count":161},{"id":"2111.12707","title":"MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation","created":"2021-11-24","cited_by_count":151},{"id":"1907.11346","title":"Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image","created":"2019-07-26","cited_by_count":132},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"1805.04095","title":"Ordinal Depth Supervision for 3D Human Pose Estimation","created":"2018-05-10","cited_by_count":107},{"id":"1903.02330","title":"Self-Supervised Learning of 3D Human Pose using Multi-view Geometry","created":"2019-03-06","cited_by_count":98},{"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":"1909.01203","title":"Cross View Fusion for 3D Human Pose Estimation","created":"2019-09-03","cited_by_count":90},{"id":"1711.08585","title":"Exploiting temporal information for 3D pose estimation","created":"2017-11-23","cited_by_count":89},{"id":"2105.02465","title":"PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation","created":"2021-05-06","cited_by_count":89},{"id":"2008.02496","title":"ConvBERT: Improving BERT with Span-based Dynamic Convolution","created":"2020-08-06","cited_by_count":88},{"id":"2103.13915","title":"An Image is Worth 16x16 Words, What is a Video Worth?","created":"2021-03-25","cited_by_count":87},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86},{"id":"2004.13985","title":"Motion Guided 3D Pose Estimation from Videos","created":"2020-04-29","cited_by_count":85},{"id":"2006.07778","title":"Cascaded deep monocular 3D human pose estimation with evolutionary training data","created":"2020-06-14","cited_by_count":80},{"id":"1910.12032","title":"HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation","created":"2019-10-26","cited_by_count":50},{"id":"2106.09336","title":"THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers","created":"2021-06-17","cited_by_count":50},{"id":"2011.10185","title":"ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis","created":"2020-11-20","cited_by_count":34},{"id":"1911.00029","title":"Chirality Nets for Human Pose Regression","created":"2019-10-31","cited_by_count":31},{"id":"1908.08289","title":"Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation","created":"2019-08-22","cited_by_count":30},{"id":"1912.04071","title":"DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image","created":"2019-12-09","cited_by_count":14},{"id":"2003.04894","title":"HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation","created":"2020-03-10","cited_by_count":12},{"id":"2105.10379","title":"3D Human Pose Regression using Graph Convolutional Network","created":"2021-05-21","cited_by_count":8},{"id":"2111.10866","title":"CpT: Convolutional Point Transformer for 3D Point Cloud Processing","created":"2021-11-21","cited_by_count":8},{"id":"2112.04981","title":"PE-former: Pose Estimation Transformer","created":"2021-12-09","cited_by_count":7},{"id":"2103.02521","title":"On the role of depth predictions for 3D human pose estimation","created":"2021-03-03","cited_by_count":1}],"next_cursor":null}