{"list":"other","total":183,"rows":[{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"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":"2011.10033","title":"Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation","created":"2020-11-19","cited_by_count":389},{"id":"2008.08294","title":"TNT: Target-driveN Trajectory Prediction","created":"2020-08-19","cited_by_count":347},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"1604.07446","title":"A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles","created":"2016-04-25","cited_by_count":254},{"id":"2208.00571","title":"CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation","created":"2022-08-01","cited_by_count":238},{"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":"2303.11301","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","created":"2023-03-20","cited_by_count":222},{"id":"2103.09213","title":"Back to the Feature: Learning Robust Camera Localization from Pixels to Pose","created":"2021-03-16","cited_by_count":199},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"2003.08111","title":"Transformer Networks for Trajectory Forecasting","created":"2020-03-18","cited_by_count":181},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"1905.01296","title":"PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings","created":"2019-05-03","cited_by_count":179},{"id":"1911.00997","title":"Multiple Futures Prediction","created":"2019-11-04","cited_by_count":178},{"id":"2103.12978","title":"RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation","created":"2021-03-24","cited_by_count":173},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"2102.04530","title":"(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network","created":"2021-02-08","cited_by_count":164},{"id":"2302.03594","title":"NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM","created":"2023-02-07","cited_by_count":164},{"id":"2008.05930","title":"Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","created":"2020-08-13","cited_by_count":153},{"id":"2005.14711","title":"PnPNet: End-to-End Perception and Prediction with Tracking in the Loop","created":"2020-05-29","cited_by_count":144},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141},{"id":"2101.06549","title":"AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles","created":"2021-01-16","cited_by_count":137},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132},{"id":"1904.04776","title":"Multi-Agent Tensor Fusion for Contextual Trajectory Prediction","created":"2019-04-09","cited_by_count":131},{"id":"2104.00563","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","created":"2021-02-19","cited_by_count":131},{"id":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","cited_by_count":122},{"id":"2206.02099","title":"Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation","created":"2022-06-05","cited_by_count":119},{"id":"2005.09830","title":"Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review","created":"2020-05-20","cited_by_count":116},{"id":"2007.12036","title":"Implicit Latent Variable Model for Scene-Consistent Motion Forecasting","created":"2020-07-23","cited_by_count":116},{"id":"2211.15766","title":"Superpoint Transformer for 3D Scene Instance Segmentation","created":"2022-11-28","cited_by_count":116},{"id":"2106.13365","title":"RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection","created":"2021-06-25","cited_by_count":115},{"id":"1811.02146","title":"TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents","created":"2018-11-06","cited_by_count":111},{"id":"2004.05224","title":"Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review","created":"2020-04-10","cited_by_count":108},{"id":"2202.02215","title":"A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective","created":"2022-02-04","cited_by_count":105},{"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":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103},{"id":"2110.06607","title":"THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling","created":"2021-10-13","cited_by_count":101},{"id":"2007.11678","title":"Contact and Human Dynamics from Monocular Video","created":"2020-07-22","cited_by_count":95},{"id":"2003.10350","title":"Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows","created":"2020-03-23","cited_by_count":94},{"id":"1808.05819","title":"Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving","created":"2018-08-17","cited_by_count":90},{"id":"2105.02465","title":"PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation","created":"2021-05-06","cited_by_count":89},{"id":"2303.11579","title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","created":"2023-03-21","cited_by_count":82},{"id":"1903.07933","title":"What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction","created":"2019-03-19","cited_by_count":80},{"id":"2004.12255","title":"TPNet: Trajectory Proposal Network for Motion Prediction","created":"2020-04-26","cited_by_count":80},{"id":"2203.07628","title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","created":"2022-03-15","cited_by_count":80},{"id":"1612.08871","title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","created":"2016-12-28","cited_by_count":76},{"id":"1805.11773","title":"Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice","created":"2018-05-30","cited_by_count":76},{"id":"2003.01197","title":"Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method","created":"2020-03-02","cited_by_count":75},{"id":"2001.00735","title":"Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans","created":"2020-01-03","cited_by_count":72},{"id":"1912.09697","title":"DeepSFM: Structure From Motion Via Deep Bundle Adjustment","created":"2019-12-20","cited_by_count":70},{"id":"2003.03212","title":"Diverse and Admissible Trajectory Forecasting through Multimodal Context Understanding","created":"2020-03-06","cited_by_count":68},{"id":"2003.06620","title":"Monocular Depth Estimation Based On Deep Learning: An Overview","created":"2020-03-14","cited_by_count":68},{"id":"2303.08600","title":"MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving","created":"2023-03-15","cited_by_count":68},{"id":"1909.07541","title":"A*3D Dataset: Towards Autonomous Driving in Challenging Environments","created":"2019-09-17","cited_by_count":65},{"id":"2008.06041","title":"DSDNet: Deep Structured self-Driving Network","created":"2020-08-13","cited_by_count":62},{"id":"2101.01993","title":"A Survey of Deep RL and IL for Autonomous Driving Policy Learning","created":"2021-01-06","cited_by_count":61},{"id":"2008.06910","title":"Neural Descent for Visual 3D Human Pose and Shape","created":"2020-08-16","cited_by_count":60},{"id":"2101.06571","title":"S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling","created":"2021-01-17","cited_by_count":59},{"id":"2009.08311","title":"Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation","created":"2020-09-16","cited_by_count":55},{"id":"2004.11822","title":"3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training","created":"2020-04-07","cited_by_count":54},{"id":"2008.05927","title":"End-to-end Contextual Perception and Prediction with Interaction Transformer","created":"2020-08-13","cited_by_count":54},{"id":"2303.00246","title":"ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution","created":"2023-03-01","cited_by_count":53},{"id":"2304.08408","title":"OVTrack: Open-Vocabulary Multiple Object Tracking","created":"2023-04-17","cited_by_count":53},{"id":"1910.04586","title":"Jointly Learnable Behavior and Trajectory Planning for Self-Driving Vehicles","created":"2019-10-10","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":"2205.05509","title":"READ: Large-Scale Neural Scene Rendering for Autonomous Driving","created":"2022-05-11","cited_by_count":51},{"id":"1910.12032","title":"HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation","created":"2019-10-26","cited_by_count":50},{"id":"2106.09336","title":"THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers","created":"2021-06-17","cited_by_count":50},{"id":"2007.14558","title":"BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation","created":"2020-07-29","cited_by_count":47},{"id":"2008.03880","title":"Multimodal Deep Generative Models for Trajectory Prediction: A Conditional Variational Autoencoder Approach","created":"2020-08-10","cited_by_count":47},{"id":"2004.04400","title":"Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis","created":"2020-04-09","cited_by_count":44},{"id":"2008.11901","title":"Multi-View Fusion of Sensor Data for Improved Perception and Prediction in Autonomous Driving","created":"2020-08-27","cited_by_count":41},{"id":"1911.12736","title":"DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling","created":"2019-11-28","cited_by_count":40},{"id":"1909.12118","title":"WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild","created":"2019-09-25","cited_by_count":39},{"id":"2205.12256","title":"Differentiable Dynamics for Articulated 3d Human Motion Reconstruction","created":"2022-05-24","cited_by_count":39},{"id":"2203.11191","title":"Robust Visual Tracking by Segmentation","created":"2022-03-21","cited_by_count":38}],"next_cursor":"100"}