{"list":"other","total":62,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"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":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1712.06087","title":"\"Zero-Shot\" Super-Resolution using Deep Internal Learning","created":"2017-12-17","cited_by_count":286},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"2005.07727","title":"Semantic Photo Manipulation with a Generative Image Prior","created":"2020-05-15","cited_by_count":178},{"id":"2104.03304","title":"Hand-Object Contact Consistency Reasoning for Human Grasps Generation","created":"2021-04-07","cited_by_count":160},{"id":"1701.01779","title":"Towards Accurate Multi-person Pose Estimation in the Wild","created":"2017-01-06","cited_by_count":131},{"id":"2007.04309","title":"Self-Supervised Policy Adaptation during Deployment","created":"2020-07-08","cited_by_count":123},{"id":"1507.06550","title":"Human Pose Estimation with Iterative Error Feedback","created":"2015-07-23","cited_by_count":121},{"id":"1704.02447","title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","created":"2017-04-08","cited_by_count":115},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"2104.07645","title":"A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation","created":"2021-04-15","cited_by_count":114},{"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":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"1908.09220","title":"Single-Stage Multi-Person Pose Machines","created":"2019-08-24","cited_by_count":95},{"id":"2007.00631","title":"Causal Discovery in Physical Systems from Videos","created":"2020-07-01","cited_by_count":77},{"id":"1804.04412","title":"Unsupervised Discovery of Object Landmarks as Structural Representations","created":"2018-04-12","cited_by_count":73},{"id":"2009.05085","title":"Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning","created":"2020-09-10","cited_by_count":70},{"id":"2006.10726","title":"Tent: Fully Test-time Adaptation by Entropy Minimization","created":"2020-06-18","cited_by_count":69},{"id":"1903.06946","title":"Unsupervised Part-Based Disentangling of Object Shape and Appearance","created":"2019-03-16","cited_by_count":67},{"id":"1708.01101","title":"Learning Feature Pyramids for Human Pose Estimation","created":"2017-08-03","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":"1712.09184","title":"Detect-and-Track: Efficient Pose Estimation in Videos","created":"2017-12-26","cited_by_count":51},{"id":"2012.03196","title":"Online Adaptation for Consistent Mesh Reconstruction in the Wild","created":"2020-12-06","cited_by_count":51},{"id":"2001.08095","title":"UniPose: Unified Human Pose Estimation in Single Images and Videos","created":"2020-01-22","cited_by_count":49},{"id":"2003.13743","title":"Combining detection and tracking for human pose estimation in videos","created":"2020-03-30","cited_by_count":49},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"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":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30},{"id":"1712.06316","title":"LSTM Pose Machines","created":"2017-12-18","cited_by_count":28},{"id":"2003.12957","title":"Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose","created":"2020-03-29","cited_by_count":26},{"id":"1407.3399","title":"Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations","created":"2014-07-12","cited_by_count":24},{"id":"1603.09065","title":"Structured Feature Learning for Pose Estimation","created":"2016-03-30","cited_by_count":17},{"id":"1511.06676","title":"Personalizing Human Video Pose Estimation","created":"2015-11-20","cited_by_count":16},{"id":"1603.04037","title":"Pose for Action - Action for Pose","created":"2016-03-13","cited_by_count":16},{"id":"1708.02179","title":"Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos","created":"2017-08-07","cited_by_count":3}],"next_cursor":null}