{"list":"other","total":88,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1709.05584","title":"Representation Learning on Graphs: Methods and Applications","created":"2017-09-17","cited_by_count":457},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"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":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"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":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"1909.04656","title":"Video Representation Learning by Dense Predictive Coding","created":"2019-09-10","cited_by_count":175},{"id":"1804.01523","title":"Stochastic Adversarial Video Prediction","created":"2018-04-04","cited_by_count":173},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"1706.08033","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","created":"2017-06-25","cited_by_count":169},{"id":"1806.04166","title":"Learning to Decompose and Disentangle Representations for Video Prediction","created":"2018-06-11","cited_by_count":121},{"id":"1902.03748","title":"Peeking into the Future: Predicting Future Person Activities and Locations in Videos","created":"2019-02-11","cited_by_count":114},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"1703.07475","title":"PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding","created":"2017-03-22","cited_by_count":101},{"id":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"1412.6604","title":"Video (language) modeling: a baseline for generative models of natural videos","created":"2014-12-20","cited_by_count":92},{"id":"1911.12409","title":"PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition","created":"2019-11-27","cited_by_count":91},{"id":"1704.05831","title":"Learning to Generate Long-term Future via Hierarchical Prediction","created":"2017-04-19","cited_by_count":88},{"id":"1911.01655","title":"High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks","created":"2019-11-05","cited_by_count":88},{"id":"1911.11206","title":"Oops! Predicting Unintentional Action in Video","created":"2019-11-25","cited_by_count":82},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"id":"1301.6725","title":"Loopy Belief Propagation for Approximate Inference: An Empirical Study","created":"2013-01-23","cited_by_count":76},{"id":"1509.01947","title":"An end-to-end generative framework for video segmentation and recognition","created":"2015-09-07","cited_by_count":61},{"id":"1711.11217","title":"Future Person Localization in First-Person Videos","created":"2017-11-30","cited_by_count":58},{"id":"2001.03093","title":"Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data","created":"2020-01-09","cited_by_count":58},{"id":"1611.08563","title":"Online Real-time Multiple Spatiotemporal Action Localisation and Prediction","created":"2016-11-25","cited_by_count":57},{"id":"2004.00542","title":"Future Video Synthesis with Object Motion Prediction","created":"2020-04-01","cited_by_count":57},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"1703.07684","title":"Predicting Deeper into the Future of Semantic Segmentation","created":"2017-03-22","cited_by_count":51},{"id":"1804.02675","title":"Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB","created":"2018-04-08","cited_by_count":51},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49},{"id":"2005.06582","title":"Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs","created":"2020-05-13","cited_by_count":48},{"id":"1712.00311","title":"Folded Recurrent Neural Networks for Future Video Prediction","created":"2017-12-01","cited_by_count":44},{"id":"1909.03449","title":"Imitation Learning for Human Pose Prediction","created":"2019-09-08","cited_by_count":44},{"id":"1908.08522","title":"Compositional Video Prediction","created":"2019-08-22","cited_by_count":43},{"id":"1509.05016","title":"Recurrent Neural Networks for Driver Activity Anticipation via Sensory-Fusion Architecture","created":"2015-09-16","cited_by_count":42},{"id":"1805.02513","title":"Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic","created":"2018-05-07","cited_by_count":41},{"id":"1612.07796","title":"First-Person Activity Forecasting with Online Inverse Reinforcement Learning","created":"2016-12-22","cited_by_count":40},{"id":"2009.01142","title":"Long-Term Anticipation of Activities with Cycle Consistency","created":"2020-09-02","cited_by_count":40},{"id":"1908.09540","title":"Uncertainty-Aware Anticipation of Activities","created":"2019-08-26","cited_by_count":39},{"id":"1703.07023","title":"Encouraging LSTMs to Anticipate Actions Very Early","created":"2017-03-21","cited_by_count":37},{"id":"1803.11496","title":"Predicting Future Instance Segmentation by Forecasting Convolutional Features","created":"2018-03-30","cited_by_count":37},{"id":"1609.04741","title":"Joint Attention in Autonomous Driving (JAAD)","created":"2016-09-15","cited_by_count":36},{"id":"2105.12414","title":"Anticipating human actions by correlating past with the future with Jaccard similarity measures","created":"2021-05-26","cited_by_count":36},{"id":"1705.06560","title":"Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization","created":"2017-05-18","cited_by_count":33},{"id":"1904.03273","title":"A Variational Auto-Encoder Model for Stochastic Point Processes","created":"2019-04-05","cited_by_count":30},{"id":"1604.05633","title":"Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks","created":"2016-04-19","cited_by_count":28},{"id":"1904.04231","title":"Relational Action Forecasting","created":"2019-04-08","cited_by_count":27},{"id":"1806.09655","title":"Learning what you can do before doing anything","created":"2018-06-25","cited_by_count":26},{"id":"1507.02159","title":"Towards Good Practices for Very Deep Two-Stream ConvNets","created":"2015-07-08","cited_by_count":25},{"id":"1711.03270","title":"Predicting Scene Parsing and Motion Dynamics in the Future","created":"2017-11-09","cited_by_count":20},{"id":"1911.07806","title":"Action Anticipation with RBF Kernelized Feature Mapping RNN","created":"2019-11-18","cited_by_count":20},{"id":"1910.03568","title":"Object-centric Forward Modeling for Model Predictive Control","created":"2019-10-08","cited_by_count":19},{"id":"1912.04608","title":"Forecasting future action sequences with attention: a new approach to weakly supervised action forecasting","created":"2019-12-10","cited_by_count":19},{"id":"2008.04888","title":"Adversarial Generative Grammars for Human Activity Prediction","created":"2020-08-11","cited_by_count":19},{"id":"1909.09278","title":"Forecasting Future Action Sequences with Neural Memory Networks","created":"2019-09-20","cited_by_count":18},{"id":"1708.05827","title":"Visual Forecasting by Imitating Dynamics in Natural Sequences","created":"2017-08-19","cited_by_count":14},{"id":"1911.10967","title":"Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video","created":"2019-11-25","cited_by_count":14},{"id":"1610.06906","title":"Review of Action Recognition and Detection Methods","created":"2016-10-21","cited_by_count":13},{"id":"1708.00065","title":"Time-Dependent Representation for Neural Event Sequence Prediction","created":"2017-07-31","cited_by_count":11},{"id":"1807.11176","title":"Human Motion Analysis with Deep Metric Learning","created":"2018-07-30","cited_by_count":11},{"id":"1808.07712","title":"Predicting Action Tubes","created":"2018-08-23","cited_by_count":6},{"id":"2008.02441","title":"Group Activity Prediction with Sequential Relational Anticipation Model","created":"2020-08-06","cited_by_count":6},{"id":"1708.06690","title":"A Spatiotemporal Oriented Energy Network for Dynamic Texture Recognition","created":"2017-08-22","cited_by_count":4},{"id":"1904.13085","title":"Early Action Prediction with Generative Adversarial Networks","created":"2019-04-30","cited_by_count":4},{"id":"1709.01630","title":"Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention","created":"2017-09-05","cited_by_count":2},{"id":"2009.14661","title":"Encode the Unseen: Predictive Video Hashing for Scalable Mid-Stream Retrieval","created":"2020-09-30","cited_by_count":2},{"id":"1803.09760","title":"Predicting the Future with Transformational States","created":"2018-03-26","cited_by_count":1}],"next_cursor":null}