{"list":"other","total":124,"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"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":"2203.10638","title":"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer","created":"2022-03-20","cited_by_count":320},{"id":"1902.07830","title":"Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges","created":"2019-02-21","cited_by_count":314},{"id":"1704.04394","title":"DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents","created":"2017-04-14","cited_by_count":310},{"id":"2109.07644","title":"OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication","created":"2021-09-16","cited_by_count":304},{"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":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"2204.05575","title":"DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection","created":"2022-04-12","cited_by_count":273},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"1710.07368","title":"SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud","created":"2017-10-19","cited_by_count":232},{"id":"1905.06113","title":"Human Motion Trajectory Prediction: A Survey","created":"2019-05-15","cited_by_count":232},{"id":"2108.10831","title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","created":"2021-08-24","cited_by_count":231},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"1710.04689","title":"Social Attention: Modeling Attention in Human Crowds","created":"2017-10-12","cited_by_count":186},{"id":"2003.08111","title":"Transformer Networks for Trajectory Forecasting","created":"2020-03-18","cited_by_count":181},{"id":"2202.08449","title":"V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving","created":"2022-02-17","cited_by_count":157},{"id":"2303.07601","title":"V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception","created":"2023-03-14","cited_by_count":155},{"id":"1911.07602","title":"The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections","created":"2019-11-18","cited_by_count":137},{"id":"1909.01300","title":"The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset","created":"2019-09-03","cited_by_count":134},{"id":"2310.14414","title":"Vision Language Models in Autonomous Driving: A Survey and Outlook","created":"2023-10-22","cited_by_count":126},{"id":"2002.09147","title":"SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances","created":"2020-02-21","cited_by_count":123},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"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":"1903.02793","title":"SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction","created":"2019-03-07","cited_by_count":111},{"id":"2010.09076","title":"RADIATE: A Radar Dataset for Automotive Perception in Bad Weather","created":"2020-10-18","cited_by_count":100},{"id":"2009.12664","title":"Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks","created":"2020-09-26","cited_by_count":85},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83},{"id":"1611.02644","title":"Multispectral Deep Neural Networks for Pedestrian Detection","created":"2016-11-08","cited_by_count":82},{"id":"2303.03595","title":"LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion","created":"2023-03-07","cited_by_count":80},{"id":"1904.09507","title":"Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs","created":"2019-04-20","cited_by_count":79},{"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":"1905.01631","title":"Conditional Generative Neural System for Probabilistic Trajectory Prediction","created":"2019-05-05","cited_by_count":76},{"id":"2107.05399","title":"Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation","created":"2021-07-12","cited_by_count":76},{"id":"1803.05347","title":"Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection","created":"2018-03-14","cited_by_count":74},{"id":"1912.12148","title":"DADA: Driver Attention Prediction in Driving Accident Scenarios","created":"2019-12-18","cited_by_count":70},{"id":"2104.02493","title":"RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications","created":"2021-04-06","cited_by_count":61},{"id":"1805.07193","title":"The EuroCity Persons Dataset: A Novel Benchmark for Object Detection","created":"2018-05-18","cited_by_count":57},{"id":"2403.15241","title":"IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection","created":"2024-03-22","cited_by_count":57},{"id":"1609.00866","title":"Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes","created":"2016-09-03","cited_by_count":50},{"id":"2104.10753","title":"Multi-task Learning with Attention for End-to-end Autonomous Driving","created":"2021-04-21","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":"2104.05485","title":"Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention","created":"2021-04-12","cited_by_count":48},{"id":"2304.12205","title":"Synthetic Datasets for Autonomous Driving: A Survey","created":"2023-04-24","cited_by_count":48},{"id":"1702.05552","title":"Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detection","created":"2017-02-18","cited_by_count":42},{"id":"1911.04074","title":"SUMMIT: A Simulator for Urban Driving in Massive Mixed Traffic","created":"2019-11-11","cited_by_count":40},{"id":"1607.07032","title":"Is Faster R-CNN Doing Well for Pedestrian Detection?","created":"2016-07-24","cited_by_count":37},{"id":"1801.05944","title":"PTB-TIR: A Thermal Infrared Pedestrian Tracking Benchmark","created":"2018-01-18","cited_by_count":34},{"id":"1705.02503","title":"Context-Aware Trajectory Prediction","created":"2017-05-06","cited_by_count":31},{"id":"2403.18447","title":"Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction","created":"2024-03-27","cited_by_count":31},{"id":"2010.00456","title":"From Handcrafted to Deep Features for Pedestrian Detection: A Survey","created":"2020-10-01","cited_by_count":30},{"id":"2111.06740","title":"Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches","created":"2021-11-11","cited_by_count":30},{"id":"2211.00385","title":"Behavioral Intention Prediction in Driving Scenes: A Survey","created":"2022-11-01","cited_by_count":30},{"id":"1904.09862","title":"Real-time Intent Prediction of Pedestrians for Autonomous Ground Vehicles via Spatio-Temporal DenseNet","created":"2019-04-22","cited_by_count":28},{"id":"1704.05776","title":"Accurate Single Stage Detector Using Recurrent Rolling Convolution","created":"2017-04-19","cited_by_count":27},{"id":"2109.07078","title":"DSOR: A Scalable Statistical Filter for Removing Falling Snow from LiDAR Point Clouds in Severe Winter Weather","created":"2021-09-15","cited_by_count":27},{"id":"2106.02781","title":"IPS300+: a Challenging Multimodal Dataset for Intersection Perception System","created":"2021-06-05","cited_by_count":26},{"id":"1808.04018","title":"Scene-LSTM: A Model for Human Trajectory Prediction","created":"2018-08-12","cited_by_count":25},{"id":"2403.07284","title":"SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection","created":"2024-03-12","cited_by_count":25},{"id":"1709.08528","title":"A Data-driven Model for Interaction-aware Pedestrian Motion Prediction in Object Cluttered Environments","created":"2017-09-25","cited_by_count":24},{"id":"1902.04997","title":"Gated2Depth: Real-time Dense Lidar from Gated Images","created":"2019-02-13","cited_by_count":23},{"id":"2112.09922","title":"Fast and Robust Registration of Partially Overlapping Point Clouds","created":"2021-12-18","cited_by_count":22},{"id":"2107.08031","title":"Is attention to bounding boxes all you need for pedestrian action prediction?","created":"2021-07-16","cited_by_count":21},{"id":"2207.07609","title":"DOLPHINS: Dataset for Collaborative Perception enabled Harmonious and Interconnected Self-driving","created":"2022-07-15","cited_by_count":21},{"id":"2004.14747","title":"Pedestrian Path, Pose and Intention Prediction through Gaussian Process Dynamical Models and Pedestrian Activity Recognition","created":"2020-04-30","cited_by_count":20},{"id":"1910.03858","title":"Intention Recognition of Pedestrians and Cyclists by 2D Pose Estimation","created":"2019-10-09","cited_by_count":19},{"id":"2105.14370","title":"BAAI-VANJEE Roadside Dataset: Towards the Connected Automated Vehicle Highway technologies in Challenging Environments of China","created":"2021-05-29","cited_by_count":19},{"id":"2006.04700","title":"Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior","created":"2020-06-08","cited_by_count":18},{"id":"2308.06419","title":"Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review","created":"2023-08-11","cited_by_count":18},{"id":"2102.02802","title":"Federated mmWave Beam Selection Utilizing LIDAR Data","created":"2021-02-04","cited_by_count":12},{"id":"1501.05759","title":"Filtered Channel Features for Pedestrian Detection","created":"2015-01-23","cited_by_count":11},{"id":"1807.02323","title":"Optimal Sensor Data Fusion Architecture for Object Detection in Adverse Weather Conditions","created":"2018-07-06","cited_by_count":11},{"id":"2201.12626","title":"Assessing Cross-dataset Generalization of Pedestrian Crossing Predictors","created":"2022-01-29","cited_by_count":11},{"id":"2311.14786","title":"GPT-4V Takes the Wheel: Promises and Challenges for Pedestrian Behavior Prediction","created":"2023-11-24","cited_by_count":11},{"id":"1810.09805","title":"Action and intention recognition of pedestrians in urban traffic","created":"2018-10-23","cited_by_count":10},{"id":"2310.17659","title":"RTNH+: Enhanced 4D Radar Object Detection Network using Combined CFAR-based Two-level Preprocessing and Vertical Encoding","created":"2023-10-19","cited_by_count":9}],"next_cursor":"100"}