{"total":120,"rows":[{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361,"area":null},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349,"area":null},{"id":"2105.09451","title":"Anabranch Network for Camouflaged Object Segmentation","created":"2021-05-20","cited_by_count":227,"area":null},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212,"area":null},{"id":"2103.06495","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","created":"2021-03-11","cited_by_count":194,"area":null},{"id":"2108.02350","title":"Hierarchical Aggregation for 3D Instance Segmentation","created":"2021-08-05","cited_by_count":127,"area":null},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104,"area":null},{"id":"2202.12181","title":"FreeSOLO: Learning to Segment Objects without Annotations","created":"2022-02-24","cited_by_count":102,"area":null},{"id":"2107.14228","title":"Open-World Entity Segmentation","created":"2021-07-29","cited_by_count":74,"area":null},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68,"area":null},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64,"area":null},{"id":"2105.06464","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","created":"2021-05-13","cited_by_count":59,"area":null},{"id":"2308.06202","title":"Exploring Predicate Visual Context in Detecting Human-Object Interactions","created":"2023-08-11","cited_by_count":56,"area":null},{"id":"2309.01017","title":"Contrastive Grouping with Transformer for Referring Image Segmentation","created":"2023-09-02","cited_by_count":54,"area":null},{"id":"2105.00637","title":"ISTR: End-to-End Instance Segmentation with Transformers","created":"2021-05-03","cited_by_count":52,"area":null},{"id":"2208.01166","title":"Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions","created":"2022-08-01","cited_by_count":48,"area":null},{"id":"2207.01223","title":"A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction","created":"2022-07-04","cited_by_count":46,"area":null},{"id":"2104.05606","title":"Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation","created":"2021-04-06","cited_by_count":42,"area":null},{"id":"2108.06747","title":"SOTR: Segmenting Objects with Transformers","created":"2021-08-15","cited_by_count":42,"area":null},{"id":"2102.02696","title":"Active Boundary Loss for Semantic Segmentation","created":"2021-02-04","cited_by_count":40,"area":null},{"id":"2104.06601","title":"Zero-Shot Instance Segmentation","created":"2021-04-14","cited_by_count":40,"area":null},{"id":"2211.10578","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","created":"2022-11-19","cited_by_count":40,"area":null},{"id":"2304.04395","title":"Instance Neural Radiance Field","created":"2023-04-10","cited_by_count":40,"area":null},{"id":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39,"area":null},{"id":"2111.11011","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","created":"2021-11-22","cited_by_count":36,"area":null},{"id":"2210.06323","title":"AISFormer: Amodal Instance Segmentation with Transformer","created":"2022-10-12","cited_by_count":35,"area":null},{"id":"2212.06826","title":"Look Before You Match: Instance Understanding Matters in Video Object Segmentation","created":"2022-12-13","cited_by_count":34,"area":null},{"id":"2106.15947","title":"SOLO: A Simple Framework for Instance Segmentation","created":"2021-06-30","cited_by_count":32,"area":null},{"id":"2105.07647","title":"FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection","created":"2021-05-17","cited_by_count":29,"area":null},{"id":"2112.04177","title":"VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation","created":"2021-12-08","cited_by_count":29,"area":null},{"id":"2105.02184","title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","created":"2021-05-05","cited_by_count":27,"area":null},{"id":"2107.14110","title":"Enhancing Adversarial Robustness via Test-time Transformation Ensembling","created":"2021-07-29","cited_by_count":27,"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":"2302.06378","title":"Semantic Image Segmentation: Two Decades of Research","created":"2023-02-13","cited_by_count":27,"area":null},{"id":"2109.09477","title":"Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement","created":"2021-09-20","cited_by_count":26,"area":null},{"id":"2205.10767","title":"Human Instance Matting via Mutual Guidance and Multi-Instance Refinement","created":"2022-05-22","cited_by_count":25,"area":null},{"id":"2104.05367","title":"Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition","created":"2021-04-12","cited_by_count":23,"area":null},{"id":"2106.09748","title":"DeepLab2: A TensorFlow Library for Deep Labeling","created":"2021-06-17","cited_by_count":22,"area":null},{"id":"2207.04614","title":"Instance Shadow Detection with A Single-Stage Detector","created":"2022-07-11","cited_by_count":22,"area":null},{"id":"2108.09897","title":"A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation","created":"2021-08-23","cited_by_count":21,"area":null},{"id":"2203.09775","title":"ContrastMask: Contrastive Learning to Segment Every Thing","created":"2022-03-18","cited_by_count":20,"area":null},{"id":"2211.11679","title":"Mean Shift Mask Transformer for Unseen Object Instance Segmentation","created":"2022-11-21","cited_by_count":19,"area":null},{"id":"2108.11771","title":"ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation","created":"2021-08-26","cited_by_count":18,"area":null},{"id":"2207.02062","title":"Image Amodal Completion: A Survey","created":"2022-07-05","cited_by_count":18,"area":null},{"id":"2210.00911","title":"Learning Equivariant Segmentation with Instance-Unique Querying","created":"2022-10-03","cited_by_count":17,"area":null},{"id":"2103.17123","title":"Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite","created":"2021-03-31","cited_by_count":16,"area":null},{"id":"2110.12663","title":"Industrial Scene Text Detection with Refined Feature-attentive Network","created":"2021-10-25","cited_by_count":16,"area":null},{"id":"2104.00073","title":"FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2105.03186","title":"A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation","created":"2021-05-07","cited_by_count":15,"area":null},{"id":"2106.15711","title":"RICE: Refining Instance Masks in Cluttered Environments with Graph Neural Networks","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2301.03992","title":"Vision Transformers Are Good Mask Auto-Labelers","created":"2023-01-10","cited_by_count":14,"area":null},{"id":"2311.05770","title":"PolyMaX: General Dense Prediction with Mask Transformer","created":"2023-11-09","cited_by_count":14,"area":null},{"id":"2203.10939","title":"Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2110.10599","title":"Video Instance Segmentation by Instance Flow Assembly","created":"2021-10-20","cited_by_count":12,"area":null},{"id":"2112.09902","title":"3D Instance Segmentation of MVS Buildings","created":"2021-12-18","cited_by_count":12,"area":null},{"id":"2207.10320","title":"OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search","created":"2022-07-21","cited_by_count":12,"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":"2305.05322","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2311.00987","title":"CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2507.02798","title":"No time to train! Training-Free Reference-Based Instance Segmentation","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2101.02196","title":"Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videos","created":"2021-01-06","cited_by_count":8,"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":"2105.01998","title":"Instance segmentation of fallen trees in aerial color infrared imagery using active multi-contour evolution with fully convolutional network-based intensity priors","created":"2021-05-05","cited_by_count":8,"area":null},{"id":"2109.01123","title":"Benchmarking the Robustness of Instance Segmentation Models","created":"2021-09-02","cited_by_count":8,"area":null},{"id":"2111.13997","title":"Learning Continuous Environment Fields via Implicit Functions","created":"2021-11-27","cited_by_count":8,"area":null},{"id":"2210.06989","title":"Multi-Task Meta Learning: learn how to adapt to unseen tasks","created":"2022-10-13","cited_by_count":8,"area":null},{"id":"2302.02693","title":"PatchDCT: Patch Refinement for High Quality Instance Segmentation","created":"2023-02-06","cited_by_count":8,"area":null},{"id":"2101.04757","title":"Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization","created":"2021-01-12","cited_by_count":7,"area":null},{"id":"2103.15428","title":"PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN","created":"2021-03-29","cited_by_count":7,"area":null},{"id":"2105.11168","title":"Human-centric Relation Segmentation: Dataset and Solution","created":"2021-05-24","cited_by_count":7,"area":null},{"id":"2109.01594","title":"Super Neurons","created":"2021-08-03","cited_by_count":7,"area":null},{"id":"2303.01503","title":"FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation","created":"2023-03-02","cited_by_count":7,"area":null},{"id":"2503.00828","title":"Training-Free Dataset Pruning for Instance Segmentation","created":"2025-03-02","cited_by_count":7,"area":null},{"id":"2207.01614","title":"Beyond mAP: Towards better evaluation of instance segmentation","created":"2022-07-04","cited_by_count":6,"area":null},{"id":"2210.11318","title":"A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2212.07671","title":"Multi-task Fusion for Efficient Panoptic-Part Segmentation","created":"2022-12-15","cited_by_count":6,"area":null},{"id":"2510.01186","title":"ASTRA: Let Arbitrary Subjects Transform in Video Editing","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2102.12808","title":"SCD: A Stacked Carton Dataset for Detection and Segmentation","created":"2021-02-25","cited_by_count":5,"area":null},{"id":"2107.11758","title":"Semantic Attention and Scale Complementary Network for Instance Segmentation in Remote Sensing Images","created":"2021-07-25","cited_by_count":5,"area":null},{"id":"2202.12251","title":"ISDA: Position-Aware Instance Segmentation with Deformable Attention","created":"2022-02-23","cited_by_count":5,"area":null},{"id":"2207.05580","title":"Online Video Instance Segmentation via Robust Context Fusion","created":"2022-07-12","cited_by_count":5,"area":null},{"id":"2208.04438","title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","created":"2022-08-08","cited_by_count":5,"area":null},{"id":"2404.01990","title":"What is Point Supervision Worth in Video Instance Segmentation?","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2307.08238","title":"Unified Open-Vocabulary Dense Visual Prediction","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2308.07590","title":"ADD: An Automatic Desensitization Fisheye Dataset for Autonomous Driving","created":"2023-08-15","cited_by_count":4,"area":null},{"id":"2102.03393","title":"MudrockNet: Semantic Segmentation of Mudrock SEM Images through Deep Learning","created":"2021-02-05","cited_by_count":3,"area":null},{"id":"2107.07464","title":"Amodal segmentation just like doing a jigsaw","created":"2021-07-15","cited_by_count":3,"area":null},{"id":"2212.03517","title":"AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2505.13584","title":"Self-Supervised Learning for Image Segmentation: A Comprehensive Survey","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2103.14872","title":"Deep Learning Techniques for In-Crop Weed Identification: A Review","created":"2021-03-27","cited_by_count":2,"area":null},{"id":"2111.12892","title":"Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2112.08743","title":"Radio-Assisted Human Detection","created":"2021-12-16","cited_by_count":2,"area":null},{"id":"2301.09416","title":"Towards Robust Video Instance Segmentation with Temporal-Aware Transformer","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2311.18618","title":"JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentation","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2508.10432","title":"CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2102.10854","title":"Contour Loss for Instance Segmentation via k-step Distance Transformation Image","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2103.05430","title":"Automatic Borescope Damage Assessments for Gas Turbine Blades via Deep Learning","created":"2021-02-23","cited_by_count":1,"area":null},{"id":"2109.05353","title":"Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network","created":"2021-09-11","cited_by_count":1,"area":null},{"id":"2202.07402","title":"SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations","created":"2022-02-15","cited_by_count":1,"area":null},{"id":"2203.06421","title":"One-stage Video Instance Segmentation: From Frame-in Frame-out to Clip-in Clip-out","created":"2022-03-12","cited_by_count":1,"area":null}],"next_cursor":"100"}