{"total":113,"rows":[{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575,"area":null},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263,"area":null},{"id":"2206.08920","title":"VectorMapNet: End-to-end Vectorized HD Map Learning","created":"2022-06-17","cited_by_count":245,"area":null},{"id":"2308.05736","title":"MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction","created":"2023-08-10","cited_by_count":193,"area":null},{"id":"2102.06583","title":"Reviving Iterative Training with Mask Guidance for Interactive Segmentation","created":"2021-02-12","cited_by_count":163,"area":null},{"id":"2203.15224","title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","created":"2022-03-29","cited_by_count":152,"area":null},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148,"area":null},{"id":"2103.05073","title":"Offboard 3D Object Detection from Point Cloud Sequences","created":"2021-03-08","cited_by_count":145,"area":null},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140,"area":null},{"id":"2210.11006","title":"SimpleClick: Interactive Image Segmentation with Simple Vision Transformers","created":"2022-10-20","cited_by_count":111,"area":null},{"id":"2110.01997","title":"Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images","created":"2021-10-05","cited_by_count":98,"area":null},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71,"area":null},{"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,"area":null},{"id":"2305.08196","title":"A Comprehensive Survey on Segment Anything Model for Vision and Beyond","created":"2023-05-14","cited_by_count":64,"area":null},{"id":"2107.12664","title":"Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection","created":"2021-07-27","cited_by_count":47,"area":null},{"id":"2104.12166","title":"MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning","created":"2021-04-25","cited_by_count":45,"area":null},{"id":"2111.15491","title":"PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images","created":"2021-11-30","cited_by_count":43,"area":null},{"id":"2204.02251","title":"RBGNet: Ray-based Grouping for 3D Object Detection","created":"2022-04-05","cited_by_count":40,"area":null},{"id":"2105.05424","title":"Transitioning to human interaction with AI systems: New challenges and opportunities for HCI professionals to enable human-centered AI","created":"2021-05-12","cited_by_count":38,"area":null},{"id":"2112.10155","title":"Topology Preserving Local Road Network Estimation from Single Onboard Camera Image","created":"2021-12-19","cited_by_count":34,"area":null},{"id":"2406.15658","title":"TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning","created":"2024-06-21","cited_by_count":31,"area":null},{"id":"2203.04074","title":"E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation","created":"2022-03-08","cited_by_count":27,"area":null},{"id":"2106.08186","title":"A Spacecraft Dataset for Detection, Segmentation and Parts Recognition","created":"2021-06-15","cited_by_count":23,"area":null},{"id":"2207.01725","title":"How Much More Data Do I Need? Estimating Requirements for Downstream Tasks","created":"2022-07-04","cited_by_count":23,"area":null},{"id":"2209.15458","title":"Towards General-Purpose Representation Learning of Polygonal Geometries","created":"2022-09-29","cited_by_count":22,"area":null},{"id":"2210.14142","title":"From colouring-in to pointillism: revisiting semantic segmentation supervision","created":"2022-10-25","cited_by_count":22,"area":null},{"id":"2304.02942","title":"InterFormer: Real-time Interactive Image Segmentation","created":"2023-04-06","cited_by_count":20,"area":null},{"id":"2212.04708","title":"PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection","created":"2022-12-09","cited_by_count":19,"area":null},{"id":"2311.04414","title":"Learning the What and How of Annotation in Video Object Segmentation","created":"2023-11-08","cited_by_count":19,"area":null},{"id":"2408.02635","title":"Interactive 3D Medical Image Segmentation with SAM 2","created":"2024-08-05","cited_by_count":17,"area":null},{"id":"2310.13378","title":"ScalableMap: Scalable Map Learning for Online Long-Range Vectorized HD Map Construction","created":"2023-10-20","cited_by_count":16,"area":null},{"id":"2210.01234","title":"Optimizing Data Collection for Machine Learning","created":"2022-10-03","cited_by_count":15,"area":null},{"id":"2203.15266","title":"Interactive Multi-Class Tiny-Object Detection","created":"2022-03-29","cited_by_count":14,"area":null},{"id":"2302.14578","title":"Interactive Segmentation as Gaussian Process Classification","created":"2023-02-28","cited_by_count":14,"area":null},{"id":"2310.13398","title":"OpenAnnotate3D: Open-Vocabulary Auto-Labeling System for Multi-modal 3D Data","created":"2023-10-20","cited_by_count":14,"area":null},{"id":"2303.10692","title":"Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning","created":"2023-03-19","cited_by_count":13,"area":null},{"id":"2106.15338","title":"Probabilistic Attention for Interactive Segmentation","created":"2021-06-23","cited_by_count":12,"area":null},{"id":"2203.13312","title":"SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation","created":"2022-03-24","cited_by_count":12,"area":null},{"id":"2303.11630","title":"BoxSnake: Polygonal Instance Segmentation with Box Supervision","created":"2023-03-21","cited_by_count":12,"area":null},{"id":"2309.10815","title":"PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes","created":"2023-09-19","cited_by_count":10,"area":null},{"id":"2107.11920","title":"CP-loss: Connectivity-preserving Loss for Road Curb Detection in Autonomous Driving with Aerial Images","created":"2021-07-26","cited_by_count":9,"area":null},{"id":"2110.02277","title":"Scaling up instance annotation via label propagation","created":"2021-10-05","cited_by_count":9,"area":null},{"id":"2203.15700","title":"MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator","created":"2022-03-29","cited_by_count":9,"area":null},{"id":"2301.08898","title":"Recurrent Generic Contour-based Instance Segmentation with Progressive Learning","created":"2023-01-21","cited_by_count":9,"area":null},{"id":"2306.08958","title":"Temporally-Extended Prompts Optimization for SAM in Interactive Medical Image Segmentation","created":"2023-06-15","cited_by_count":9,"area":null},{"id":"2101.06545","title":"VideoClick: Video Object Segmentation with a Single Click","created":"2021-01-16","cited_by_count":8,"area":null},{"id":"2312.13116","title":"VSR-Net: Vessel-like Structure Rehabilitation Network with Graph Clustering","created":"2023-12-20","cited_by_count":8,"area":null},{"id":"2102.12759","title":"Binary segmentation of medical images using implicit spline representations and deep learning","created":"2021-02-25","cited_by_count":7,"area":null},{"id":"2104.04606","title":"RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes","created":"2021-04-09","cited_by_count":7,"area":null},{"id":"2307.10947","title":"Improving Online Lane Graph Extraction by Object-Lane Clustering","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2404.11426","title":"SPAMming Labels: Efficient Annotations for the Trackers of Tomorrow","created":"2024-04-17","cited_by_count":7,"area":null},{"id":"2108.07990","title":"Structured Outdoor Architecture Reconstruction by Exploration and Classification","created":"2021-08-18","cited_by_count":6,"area":null},{"id":"2108.08923","title":"CenterPoly: real-time instance segmentation using bounding polygons","created":"2021-08-19","cited_by_count":6,"area":null},{"id":"2108.11950","title":"LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision","created":"2021-08-26","cited_by_count":6,"area":null},{"id":"2309.09643","title":"HiT: Building Mapping with Hierarchical Transformers","created":"2023-09-18","cited_by_count":6,"area":null},{"id":"2407.14912","title":"PolyR-CNN: R-CNN for end-to-end polygonal building outline extraction","created":"2024-07-20","cited_by_count":6,"area":null},{"id":"2407.14920","title":"RoIPoly: Vectorized Building Outline Extraction Using Vertex and Logit Embeddings","created":"2024-07-20","cited_by_count":6,"area":null},{"id":"2103.03821","title":"Fast Interactive Video Object Segmentation with Graph Neural Networks","created":"2021-03-05","cited_by_count":4,"area":null},{"id":"2103.14420","title":"YOLinO: Generic Single Shot Polyline Detection in Real Time","created":"2021-03-26","cited_by_count":4,"area":null},{"id":"2111.07716","title":"Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration","created":"2021-11-15","cited_by_count":4,"area":null},{"id":"2212.10207","title":"Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2304.11609","title":"PiClick: Picking the desired mask from multiple candidates in click-based interactive segmentation","created":"2023-04-23","cited_by_count":4,"area":null},{"id":"2405.18706","title":"FocSAM: Delving Deeply into Focused Objects in Segmenting Anything","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2106.03987","title":"Weakly Supervised Volumetric Image Segmentation with Deformed Templates","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2108.02996","title":"Efficient and Generic Interactive Segmentation Framework to Correct Mispredictions during Clinical Evaluation of Medical Images","created":"2021-08-06","cited_by_count":3,"area":null},{"id":"2204.02898","title":"End-to-End Instance Edge Detection","created":"2022-04-06","cited_by_count":3,"area":null},{"id":"2211.01589","title":"PolyBuilding: Polygon Transformer for End-to-End Building Extraction","created":"2022-11-03","cited_by_count":3,"area":null},{"id":"2302.06353","title":"Contour-based Interactive Segmentation","created":"2023-02-13","cited_by_count":3,"area":null},{"id":"2304.04048","title":"Polygonizer: An auto-regressive building delineator","created":"2023-04-08","cited_by_count":3,"area":null},{"id":"2307.02280","title":"Interactive Image Segmentation with Cross-Modality Vision Transformers","created":"2023-07-05","cited_by_count":3,"area":null},{"id":"2307.10518","title":"Interactive Segmentation for Diverse Gesture Types Without Context","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2402.08207","title":"Translating Images to Road Network: A Sequence-to-Sequence Perspective","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2503.07209","title":"Synthetic Lung X-ray Generation through Cross-Attention and Affinity Transformation","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2101.04378","title":"Rethinking Interactive Image Segmentation: Feature Space Annotation","created":"2021-01-12","cited_by_count":2,"area":null},{"id":"2111.06162","title":"Clicking Matters:Towards Interactive Human Parsing","created":"2021-11-11","cited_by_count":2,"area":null},{"id":"2112.06454","title":"Split GCN: Effective Interactive Annotation for Segmentation of Disconnected Instance","created":"2021-12-13","cited_by_count":2,"area":null},{"id":"2302.09765","title":"ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2105.14584","title":"Polygonal Point Set Tracking","created":"2021-05-30","cited_by_count":1,"area":null},{"id":"2106.03382","title":"ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass","created":"2021-06-07","cited_by_count":1,"area":null},{"id":"2203.15856","title":"OdontoAI: A human-in-the-loop labeled data set and an online platform to boost research on dental panoramic radiographs","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2205.11563","title":"Accelerating the creation of instance segmentation training sets through bounding box annotation","created":"2022-05-23","cited_by_count":1,"area":null},{"id":"2303.00300","title":"BiSVP: Building Footprint Extraction via Bidirectional Serialized Vertex Prediction","created":"2023-03-01","cited_by_count":1,"area":null},{"id":"2305.05490","title":"Real-time instance segmentation with polygons using an Intersection-over-Union loss","created":"2023-05-09","cited_by_count":1,"area":null},{"id":"2406.18809","title":"Divide, Ensemble and Conquer: The Last Mile on Unsupervised Domain Adaptation for Semantic Segmentation","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2411.16132","title":"TreeFormer: Single-view Plant Skeleton Estimation via Tree-constrained Graph Generation","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2411.16616","title":"GeoFormer: A Multi-Polygon Segmentation Transformer","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2602.09016","title":"Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2108.09433","title":"BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation","created":"2021-08-21","cited_by_count":0,"area":null},{"id":"2111.00063","title":"Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2112.02535","title":"End-to-End Segmentation via Patch-wise Polygons Prediction","created":"2021-12-05","cited_by_count":0,"area":null},{"id":"2203.05145","title":"Cascaded Sparse Feature Propagation Network for Interactive Segmentation","created":"2022-03-10","cited_by_count":0,"area":null},{"id":"2206.13963","title":"Primitive Graph Learning for Unified Vector Mapping","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2209.11159","title":"Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures","created":"2022-09-22","cited_by_count":0,"area":null},{"id":"2212.06756","title":"Connectivity-constrained Interactive Panoptic Segmentation","created":"2022-12-13","cited_by_count":0,"area":null},{"id":"2304.00930","title":"Online Lane Graph Extraction from Onboard Video","created":"2023-04-03","cited_by_count":0,"area":null},{"id":"2304.07072","title":"CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2305.03105","title":"HAISTA-NET: Human Assisted Instance Segmentation Through Attention","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2305.16968","title":"Linear Object Detection in Document Images using Multiple Object Tracking","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2310.07638","title":"Context-Enhanced Detector For Building Detection From Remote Sensing Images","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2403.03296","title":"CenterDisks: Real-time instance segmentation with disk covering","created":"2024-03-05","cited_by_count":0,"area":null}],"next_cursor":"100"}