{"list":"other","total":63,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"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":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"1906.05113","title":"A Survey of Autonomous Driving: Common Practices and Emerging Technologies","created":"2019-06-12","cited_by_count":379},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2101.06679","title":"End-to-end Interpretable Neural Motion Planner","created":"2021-01-17","cited_by_count":242},{"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":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","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":"1807.11546","title":"Textual Explanations for Self-Driving Vehicles","created":"2018-07-30","cited_by_count":226},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"1704.05519","title":"Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art","created":"2017-04-18","cited_by_count":182},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158},{"id":"2008.05930","title":"Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","created":"2020-08-13","cited_by_count":153},{"id":"1911.10868","title":"End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances","created":"2019-11-25","cited_by_count":149},{"id":"2006.14911","title":"Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?","created":"2020-06-26","cited_by_count":139},{"id":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"id":"2003.06404","title":"A Survey of End-to-End Driving: Architectures and Training Methods","created":"2020-03-13","cited_by_count":123},{"id":"2110.00966","title":"Translating Images into Maps","created":"2021-10-03","cited_by_count":115},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114},{"id":"1906.03199","title":"Multimodal End-to-End Autonomous Driving","created":"2019-06-07","cited_by_count":110},{"id":"2003.13942","title":"Spatio-Temporal Graph for Video Captioning with Knowledge Distillation","created":"2020-03-31","cited_by_count":109},{"id":"1703.10631","title":"Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention","created":"2017-03-30","cited_by_count":107},{"id":"2002.11566","title":"Object Relational Graph with Teacher-Recommended Learning for Video Captioning","created":"2020-02-26","cited_by_count":107},{"id":"2101.06547","title":"LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving","created":"2021-01-16","cited_by_count":96},{"id":"1412.4729","title":"Translating Videos to Natural Language Using Deep Recurrent Neural Networks","created":"2014-12-15","cited_by_count":95},{"id":"1804.09364","title":"Driving Policy Transfer via Modularity and Abstraction","created":"2018-04-25","cited_by_count":92},{"id":"2205.00613","title":"MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries","created":"2022-05-02","cited_by_count":91},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"1806.06498","title":"Conditional Affordance Learning for Driving in Urban Environments","created":"2018-06-18","cited_by_count":70},{"id":"2008.06041","title":"DSDNet: Deep Structured self-Driving Network","created":"2020-08-13","cited_by_count":62},{"id":"1510.07712","title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks","created":"2015-10-26","cited_by_count":54},{"id":"1505.01861","title":"Jointly Modeling Embedding and Translation to Bridge Video and Language","created":"2015-05-07","cited_by_count":53},{"id":"1611.07675","title":"Video Captioning with Transferred Semantic Attributes","created":"2016-11-23","cited_by_count":46},{"id":"2005.09202","title":"Multi-modal Sensor Fusion-Based Deep Neural Network for End-to-end Autonomous Driving with Scene Understanding","created":"2020-05-19","cited_by_count":42},{"id":"2005.10091","title":"Label Efficient Visual Abstractions for Autonomous Driving","created":"2020-05-20","cited_by_count":33},{"id":"1707.00383","title":"Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation","created":"2017-07-03","cited_by_count":29},{"id":"2109.05566","title":"PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds","created":"2021-09-12","cited_by_count":26},{"id":"2104.12861","title":"Learning Interpretable End-to-End Vision-Based Motion Planning for Autonomous Driving with Optical Flow Distillation","created":"2021-04-18","cited_by_count":25},{"id":"2210.10775","title":"TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation","created":"2022-10-19","cited_by_count":25},{"id":"2011.01153","title":"Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving","created":"2020-11-02","cited_by_count":24},{"id":"2111.12608","title":"Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing","created":"2021-11-24","cited_by_count":22},{"id":"1704.07489","title":"Multi-Task Video Captioning with Video and Entailment Generation","created":"2017-04-24","cited_by_count":17},{"id":"1708.09667","title":"Video Captioning with Guidance of Multimodal Latent Topics","created":"2017-08-31","cited_by_count":16},{"id":"2005.03863","title":"Learning hierarchical behavior and motion planning for autonomous driving","created":"2020-05-08","cited_by_count":15},{"id":"2007.11888","title":"SBAT: Video Captioning with Sparse Boundary-Aware Transformer","created":"2020-07-23","cited_by_count":12},{"id":"2008.09417","title":"Action-Based Representation Learning for Autonomous Driving","created":"2020-08-21","cited_by_count":11},{"id":"2008.12969","title":"Driving Through Ghosts: Behavioral Cloning with False Positives","created":"2020-08-29","cited_by_count":8},{"id":"2208.07870","title":"Language-guided Semantic Style Transfer of 3D Indoor Scenes","created":"2022-08-16","cited_by_count":7},{"id":"2208.11122","title":"Distance-Aware Occlusion Detection with Focused Attention","created":"2022-08-23","cited_by_count":6},{"id":"1905.01333","title":"DeepSignals: Predicting Intent of Drivers Through Visual Signals","created":"2019-05-03","cited_by_count":3}],"next_cursor":null}