{"list":"other","total":53,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"1812.03079","title":"ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst","created":"2018-12-07","cited_by_count":397},{"id":"2007.13732","title":"Learning Lane Graph Representations for Motion Forecasting","created":"2020-07-27","cited_by_count":382},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"1809.10732","title":"Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks","created":"2018-09-18","cited_by_count":289},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"1911.10298","title":"CoverNet: Multimodal Behavior Prediction using Trajectory Sets","created":"2019-11-23","cited_by_count":259},{"id":"2104.10490","title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","created":"2021-04-21","cited_by_count":239},{"id":"2012.12395","title":"Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net","created":"2020-12-22","cited_by_count":228},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"2003.01460","title":"Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction","created":"2020-03-03","cited_by_count":195},{"id":"2305.10430","title":"Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes","created":"2023-05-17","cited_by_count":191},{"id":"1603.07285","title":"A guide to convolution arithmetic for deep learning","created":"2016-03-23","cited_by_count":185},{"id":"2206.05099","title":"SimVP: Simpler yet Better Video Prediction","created":"2022-06-09","cited_by_count":184},{"id":"1706.03458","title":"Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model","created":"2017-06-12","cited_by_count":182},{"id":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","cited_by_count":182},{"id":"2003.08111","title":"Transformer Networks for Trajectory Forecasting","created":"2020-03-18","cited_by_count":181},{"id":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158},{"id":"1804.06300","title":"PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning","created":"2018-04-17","cited_by_count":122},{"id":"1906.08945","title":"Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions","created":"2019-06-21","cited_by_count":117},{"id":"1811.02146","title":"TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents","created":"2018-11-06","cited_by_count":111},{"id":"1910.08233","title":"Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data","created":"2019-10-18","cited_by_count":104},{"id":"2207.01567","title":"Back to MLP: A Simple Baseline for Human Motion Prediction","created":"2022-07-04","cited_by_count":100},{"id":"2103.03067","title":"TPCN: Temporal Point Cloud Networks for Motion Forecasting","created":"2021-03-04","cited_by_count":94},{"id":"1811.07490","title":"Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics","created":"2018-11-19","cited_by_count":92},{"id":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86},{"id":"1801.07962","title":"An LSTM Network for Highway Trajectory Prediction","created":"2018-01-24","cited_by_count":81},{"id":"2103.04027","title":"Learning to Predict Vehicle Trajectories with Model-based Planning","created":"2021-03-06","cited_by_count":63},{"id":"2004.00542","title":"Future Video Synthesis with Object Motion Prediction","created":"2020-04-01","cited_by_count":57},{"id":"2306.11249","title":"OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning","created":"2023-06-20","cited_by_count":54},{"id":"1712.00311","title":"Folded Recurrent Neural Networks for Future Video Prediction","created":"2017-12-01","cited_by_count":44},{"id":"1911.12736","title":"DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling","created":"2019-11-28","cited_by_count":40},{"id":"1810.01325","title":"FutureGAN: Anticipating the Future Frames of Video Sequences using Spatio-Temporal 3d Convolutions in Progressively Growing GANs","created":"2018-10-02","cited_by_count":24},{"id":"2306.10761","title":"PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View","created":"2023-06-19","cited_by_count":24},{"id":"2208.06671","title":"Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes","created":"2022-08-13","cited_by_count":23},{"id":"2210.07571","title":"Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization","created":"2022-10-14","cited_by_count":20},{"id":"2308.16154","title":"MMVP: Motion-Matrix-based Video Prediction","created":"2023-08-30","cited_by_count":18},{"id":"2301.04581","title":"Elevation Estimation-Driven Building 3D Reconstruction from Single-View Remote Sensing Imagery","created":"2023-01-11","cited_by_count":17},{"id":"2207.10278","title":"Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification","created":"2022-07-21","cited_by_count":16},{"id":"2310.12452","title":"Not Just Learning from Others but Relying on Yourself: A New Perspective on Few-Shot Segmentation in Remote Sensing","created":"2023-10-19","cited_by_count":11},{"id":"1909.13377","title":"Lane Attention: Predicting Vehicles' Moving Trajectories by Learning Their Attention over Lanes","created":"2019-09-29","cited_by_count":9},{"id":"2310.04724","title":"Activate and Reject: Towards Safe Domain Generalization under Category Shift","created":"2023-10-07","cited_by_count":9}],"next_cursor":null}