{"list":"other","total":59,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"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":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"1711.02281","title":"Non-Autoregressive Neural Machine Translation","created":"2017-11-07","cited_by_count":463},{"id":"1812.07179","title":"Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving","created":"2018-12-18","cited_by_count":457},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"2208.14437","title":"MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction","created":"2022-08-30","cited_by_count":314},{"id":"1809.10732","title":"Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks","created":"2018-09-18","cited_by_count":289},{"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":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"1811.08188","title":"Orthographic Feature Transform for Monocular 3D Object Detection","created":"2018-11-20","cited_by_count":202},{"id":"1911.06667","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","created":"2019-11-15","cited_by_count":201},{"id":"1905.11006","title":"Levenshtein Transformer","created":"2019-05-27","cited_by_count":199},{"id":"1802.06901","title":"Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement","created":"2018-02-19","cited_by_count":195},{"id":"2003.13402","title":"Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks","created":"2020-03-30","cited_by_count":175},{"id":"1902.03249","title":"Insertion Transformer: Flexible Sequence Generation via Insertion Operations","created":"2019-02-08","cited_by_count":125},{"id":"1911.02727","title":"Understanding Knowledge Distillation in Non-autoregressive Machine Translation","created":"2019-11-07","cited_by_count":122},{"id":"1803.09693","title":"Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++","created":"2018-03-26","cited_by_count":120},{"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":"2110.00966","title":"Translating Images into Maps","created":"2021-10-03","cited_by_count":115},{"id":"2110.01997","title":"Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images","created":"2021-10-05","cited_by_count":98},{"id":"2105.05003","title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","created":"2021-05-11","cited_by_count":95},{"id":"2007.12147","title":"CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending","created":"2020-07-23","cited_by_count":80},{"id":"2002.06604","title":"Key Points Estimation and Point Instance Segmentation Approach for Lane Detection","created":"2020-02-16","cited_by_count":77},{"id":"2204.09269","title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","created":"2022-04-20","cited_by_count":64},{"id":"1908.07181","title":"Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior","created":"2019-08-20","cited_by_count":58},{"id":"1808.08583","title":"Semi-Autoregressive Neural Machine Translation","created":"2018-08-26","cited_by_count":48},{"id":"2206.04042","title":"Learning Ego 3D Representation as Ray Tracing","created":"2022-06-08","cited_by_count":43},{"id":"1911.02215","title":"Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information","created":"2019-11-06","cited_by_count":37},{"id":"2112.10155","title":"Topology Preserving Local Road Network Estimation from Single Onboard Camera Image","created":"2021-12-19","cited_by_count":34},{"id":"2004.10454","title":"A Study of Non-autoregressive Model for Sequence Generation","created":"2020-04-22","cited_by_count":31},{"id":"2103.11405","title":"Non-Autoregressive Translation by Learning Target Categorical Codes","created":"2021-03-21","cited_by_count":25},{"id":"1908.03274","title":"Exploiting Sparse Semantic HD Maps for Self-Driving Vehicle Localization","created":"2019-08-08","cited_by_count":24},{"id":"2204.02030","title":"$\\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation","created":"2022-04-05","cited_by_count":20},{"id":"2207.09399","title":"RCLane: Relay Chain Prediction for Lane Detection","created":"2022-07-19","cited_by_count":20},{"id":"1809.11036","title":"Real-time Dynamic Object Detection for Autonomous Driving using Prior 3D-Maps","created":"2018-09-28","cited_by_count":17},{"id":"2108.05814","title":"Decoder Fusion RNN: Context and Interaction Aware Decoders for Trajectory Prediction","created":"2021-08-12","cited_by_count":12},{"id":"2002.06832","title":"DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories","created":"2020-02-17","cited_by_count":7},{"id":"2307.01807","title":"SUIT: Learning Significance-guided Information for 3D Temporal Detection","created":"2023-07-04","cited_by_count":1}],"next_cursor":null}