{"list":"other","total":51,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"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":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"1705.02445","title":"On human motion prediction using recurrent neural networks","created":"2017-05-06","cited_by_count":338},{"id":"2002.11927","title":"Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction","created":"2020-02-27","cited_by_count":325},{"id":"1704.04394","title":"DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents","created":"2017-04-14","cited_by_count":310},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1806.01482","title":"SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints","created":"2018-06-05","cited_by_count":298},{"id":"1908.05436","title":"Learning Trajectory Dependencies for Human Motion Prediction","created":"2019-08-15","cited_by_count":246},{"id":"2004.02025","title":"It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction","created":"2020-04-04","cited_by_count":236},{"id":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"id":"1907.03395","title":"Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks","created":"2019-07-04","cited_by_count":229},{"id":"2005.08514","title":"Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction","created":"2020-05-18","cited_by_count":218},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"2007.11755","title":"History Repeats Itself: Human Motion Prediction via Motion Attention","created":"2020-07-23","cited_by_count":165},{"id":"2012.05522","title":"Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes","created":"2020-12-10","cited_by_count":135},{"id":"1912.02923","title":"Generating 3D People in Scenes without People","created":"2019-12-05","cited_by_count":127},{"id":"1805.00655","title":"Convolutional Sequence to Sequence Model for Human Dynamics","created":"2018-05-02","cited_by_count":115},{"id":"2012.00619","title":"We are More than Our Joints: Predicting how 3D Bodies Move","created":"2020-12-01","cited_by_count":115},{"id":"1812.05478","title":"Human Motion Prediction via Spatio-Temporal Inpainting","created":"2018-12-13","cited_by_count":114},{"id":"2104.00683","title":"SimPoE: Simulated Character Control for 3D Human Pose Estimation","created":"2021-04-01","cited_by_count":114},{"id":"1805.06485","title":"QuaterNet: A Quaternion-based Recurrent Model for Human Motion","created":"2018-05-16","cited_by_count":109},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"1702.07486","title":"Deep representation learning for human motion prediction and classification","created":"2017-02-24","cited_by_count":98},{"id":"1809.03036","title":"A Neural Temporal Model for Human Motion Prediction","created":"2018-09-09","cited_by_count":87},{"id":"2008.08171","title":"Learning to Generate Diverse Dance Motions with Transformer","created":"2020-08-18","cited_by_count":85},{"id":"1907.04967","title":"Diverse Trajectory Forecasting with Determinantal Point Processes","created":"2019-07-11","cited_by_count":80},{"id":"1904.09507","title":"Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs","created":"2019-04-20","cited_by_count":79},{"id":"1704.02827","title":"Learning Human Motion Models for Long-term Predictions","created":"2017-04-10","cited_by_count":67},{"id":"2004.10402","title":"Recursive Social Behavior Graph for Trajectory Prediction","created":"2020-04-22","cited_by_count":66},{"id":"2104.04029","title":"TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild","created":"2021-04-08","cited_by_count":52},{"id":"1908.04781","title":"Predicting 3D Human Dynamics from Video","created":"2019-08-13","cited_by_count":51},{"id":"2007.06843","title":"Socially and Contextually Aware Human Motion and Pose Forecasting","created":"2020-07-14","cited_by_count":51},{"id":"2103.07854","title":"Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis","created":"2021-03-14","cited_by_count":46},{"id":"1702.05552","title":"Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detection","created":"2017-02-18","cited_by_count":42},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30},{"id":"1604.03692","title":"Learning Social Affordance for Human-Robot Interaction","created":"2016-04-13","cited_by_count":20},{"id":"1703.00503","title":"Learning Social Affordance Grammar from Videos: Transferring Human Interactions to Human-Robot Interactions","created":"2017-03-01","cited_by_count":5}],"next_cursor":null}