{"list":"other","total":98,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1708.07819","title":"Semantic Foggy Scene Understanding with Synthetic Data","created":"2017-08-25","cited_by_count":403},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"2108.10831","title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","created":"2021-08-24","cited_by_count":231},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"1712.06080","title":"Spatial As Deep: Spatial CNN for Traffic Scene Understanding","created":"2017-12-17","cited_by_count":187},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"id":"1407.1808","title":"Simultaneous Detection and Segmentation","created":"2014-07-07","cited_by_count":159},{"id":"2104.14812","title":"SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation","created":"2021-04-30","cited_by_count":150},{"id":"2203.11089","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","created":"2022-03-21","cited_by_count":140},{"id":"1904.07595","title":"Detecting the Unexpected via Image Resynthesis","created":"2019-04-16","cited_by_count":137},{"id":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137},{"id":"1810.02575","title":"Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime","created":"2018-10-05","cited_by_count":122},{"id":"1904.03215","title":"The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation","created":"2019-04-05","cited_by_count":122},{"id":"1609.04653","title":"Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles","created":"2016-09-15","cited_by_count":117},{"id":"1811.10203","title":"3D-LaneNet: End-to-End 3D Multiple Lane Detection","created":"2018-11-26","cited_by_count":107},{"id":"1511.04136","title":"UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking","created":"2015-11-13","cited_by_count":98},{"id":"1808.01265","title":"Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding","created":"2018-08-03","cited_by_count":98},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2008.00334","title":"Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning","created":"2020-08-01","cited_by_count":91},{"id":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"2005.14553","title":"Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation","created":"2020-05-28","cited_by_count":86},{"id":"2304.10440","title":"OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping","created":"2023-04-20","cited_by_count":83},{"id":"1901.06340","title":"Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection","created":"2019-01-18","cited_by_count":80},{"id":"1705.03854","title":"Predicting the Driver's Focus of Attention: the DR(eye)VE Project","created":"2017-05-10","cited_by_count":79},{"id":"2002.08945","title":"Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction","created":"2020-02-20","cited_by_count":71},{"id":"1903.00618","title":"Unsupervised Traffic Accident Detection in First-Person Videos","created":"2019-03-02","cited_by_count":70},{"id":"1912.12148","title":"DADA: Driver Attention Prediction in Driving Accident Scenarios","created":"2019-12-18","cited_by_count":70},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66},{"id":"1902.05093","title":"DeeperLab: Single-Shot Image Parser","created":"2019-02-13","cited_by_count":63},{"id":"2004.13316","title":"SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing","created":"2020-04-28","cited_by_count":62},{"id":"1711.06406","title":"Predicting Driver Attention in Critical Situations","created":"2017-11-17","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":"1904.12634","title":"DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark","created":"2019-04-23","cited_by_count":57},{"id":"2402.04857","title":"Advancing Video Anomaly Detection: A Concise Review and a New Dataset","created":"2024-02-07","cited_by_count":49},{"id":"2005.08630","title":"End-to-End Lane Marker Detection via Row-wise Classification","created":"2020-05-06","cited_by_count":47},{"id":"2107.10189","title":"DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation","created":"2021-07-21","cited_by_count":46},{"id":"2403.00436","title":"Abductive Ego-View Accident Video Understanding for Safe Driving Perception","created":"2024-03-01","cited_by_count":43},{"id":"1809.07408","title":"Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems","created":"2018-09-19","cited_by_count":42},{"id":"2009.14660","title":"Driver Anomaly Detection: A Dataset and Contrastive Learning Approach","created":"2020-09-30","cited_by_count":41},{"id":"1809.05782","title":"CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis","created":"2018-09-16","cited_by_count":39},{"id":"1908.00894","title":"Pothole Detection Based on Disparity Transformation and Road Surface Modeling","created":"2019-08-02","cited_by_count":38},{"id":"2003.06883","title":"Night-time Scene Parsing with a Large Real Dataset","created":"2020-03-15","cited_by_count":37},{"id":"1607.03476","title":"End-to-end training of object class detectors for mean average precision","created":"2016-07-12","cited_by_count":35},{"id":"1904.00649","title":"Deep Learning for Large-Scale Traffic-Sign Detection and Recognition","created":"2019-04-01","cited_by_count":34},{"id":"2009.06435","title":"Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions","created":"2020-08-31","cited_by_count":34},{"id":"2209.08538","title":"RDD2022: A multi-national image dataset for automatic Road Damage Detection","created":"2022-09-18","cited_by_count":32},{"id":"2308.15985","title":"Vision-Based Traffic Accident Detection and Anticipation: A Survey","created":"2023-08-30","cited_by_count":31},{"id":"1901.08292","title":"Anomaly Detection in Road Traffic Using Visual Surveillance: A Survey","created":"2019-01-24","cited_by_count":30},{"id":"2010.00456","title":"From Handcrafted to Deep Features for Pedestrian Detection: A Survey","created":"2020-10-01","cited_by_count":30},{"id":"2012.13633","title":"Detecting Road Obstacles by Erasing Them","created":"2020-12-25","cited_by_count":29},{"id":"2111.06123","title":"Spatio-Temporal Scene-Graph Embedding for Autonomous Vehicle Collision Prediction","created":"2021-11-11","cited_by_count":29},{"id":"1809.03605","title":"PedX: Benchmark Dataset for Metric 3D Pose Estimation of Pedestrians in Complex Urban Intersections","created":"2018-09-10","cited_by_count":27},{"id":"2004.03044","title":"When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos","created":"2020-04-06","cited_by_count":27},{"id":"2108.08482","title":"VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection","created":"2021-08-19","cited_by_count":21},{"id":"2308.02046","title":"UGainS: Uncertainty Guided Anomaly Instance Segmentation","created":"2023-08-03","cited_by_count":15},{"id":"2312.01659","title":"RiskBench: A Scenario-based Benchmark for Risk Identification","created":"2023-12-04","cited_by_count":12},{"id":"2505.02148","title":"Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving","created":"2025-05-04","cited_by_count":10},{"id":"2209.08716","title":"GLARE: A Dataset for Traffic Sign Detection in Sun Glare","created":"2022-09-19","cited_by_count":9},{"id":"2211.11362","title":"Crowdsensing-based Road Damage Detection Challenge (CRDDC-2022)","created":"2022-11-21","cited_by_count":9},{"id":"2308.11106","title":"Recursive Video Lane Detection","created":"2023-08-22","cited_by_count":9},{"id":"2205.01198","title":"NHA12D: A New Pavement Crack Dataset and a Comparison Study Of Crack Detection Algorithms","created":"2022-05-02","cited_by_count":8},{"id":"2005.13298","title":"An Iteratively Optimized Patch Label Inference Network for Automatic Pavement Distress Detection","created":"2020-05-27","cited_by_count":7},{"id":"1906.02859","title":"Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer","created":"2019-06-07","cited_by_count":6},{"id":"2003.10142","title":"EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion","created":"2020-03-23","cited_by_count":6},{"id":"2205.13326","title":"SHREC 2022: pothole and crack detection in the road pavement using images and RGB-D data","created":"2022-05-26","cited_by_count":6},{"id":"1611.05369","title":"Fast On-Line Kernel Density Estimation for Active Object Localization","created":"2016-11-16","cited_by_count":4},{"id":"2402.04297","title":"Road Surface Defect Detection -- From Image-based to Non-image-based: A Survey","created":"2024-02-06","cited_by_count":4},{"id":"2301.02726","title":"Augmenting Ego-Vehicle for Traffic Near-Miss and Accident Classification Dataset using Manipulating Conditional Style Translation","created":"2023-01-06","cited_by_count":2},{"id":"2504.10123","title":"M2S-RoAD: Multi-Modal Semantic Segmentation for Road Damage Using Camera and LiDAR Data","created":"2025-04-14","cited_by_count":1}],"next_cursor":null}