{"total":114,"rows":[{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565,"area":null},{"id":"2103.16562","title":"Boundary IoU: Improving Object-Centric Image Segmentation Evaluation","created":"2021-03-30","cited_by_count":188,"area":null},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"area":null},{"id":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143,"area":null},{"id":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140,"area":null},{"id":"2111.11429","title":"Benchmarking Detection Transfer Learning with Vision Transformers","created":"2021-11-22","cited_by_count":131,"area":null},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"id":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114,"area":"mllm"},{"id":"2304.03752","title":"V3Det: Vast Vocabulary Visual Detection Dataset","created":"2023-04-07","cited_by_count":81,"area":null},{"id":"2102.12867","title":"FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation","created":"2021-02-25","cited_by_count":76,"area":null},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68,"area":null},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63,"area":null},{"id":"2104.07434","title":"Points as Queries: Weakly Semi-supervised Object Detection by Points","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2103.13886","title":"Robust and Accurate Object Detection via Adversarial Learning","created":"2021-03-23","cited_by_count":42,"area":null},{"id":"2110.02578","title":"Decoupled Adaptation for Cross-Domain Object Detection","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2203.13249","title":"BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training","created":"2022-03-24","cited_by_count":33,"area":null},{"id":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31,"area":null},{"id":"2307.00934","title":"Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration","created":"2023-07-03","cited_by_count":19,"area":null},{"id":"2108.10520","title":"Improving Object Detection by Label Assignment Distillation","created":"2021-08-24","cited_by_count":17,"area":null},{"id":"2303.08747","title":"Cascaded Zoom-in Detector for High Resolution Aerial Images","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2309.14976","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","created":"2023-09-26","cited_by_count":17,"area":"moe"},{"id":"2211.13508","title":"1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2203.05469","title":"Prediction-Guided Distillation for Dense Object Detection","created":"2022-03-10","cited_by_count":14,"area":"distill"},{"id":"2204.07874","title":"Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake System","created":"2022-04-16","cited_by_count":14,"area":null},{"id":"2403.16528","title":"Open-Set Recognition in the Age of Vision-Language Models","created":"2024-03-25","cited_by_count":13,"area":"mllm"},{"id":"2206.00274","title":"Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations","created":"2022-06-01","cited_by_count":11,"area":null},{"id":"2308.08529","title":"Diagnosing Human-object Interaction Detectors","created":"2023-08-16","cited_by_count":11,"area":null},{"id":"2309.00832","title":"ObjectLab: Automated Diagnosis of Mislabeled Images in Object Detection Data","created":"2023-09-02","cited_by_count":11,"area":null},{"id":"2405.20459","title":"On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines","created":"2024-05-30","cited_by_count":11,"area":null},{"id":"2103.14027","title":"USB: Universal-Scale Object Detection Benchmark","created":"2021-03-25","cited_by_count":10,"area":null},{"id":"2206.04669","title":"Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields","created":"2022-06-09","cited_by_count":10,"area":null},{"id":"2206.07690","title":"ELUDE: Generating interpretable explanations via a decomposition into labelled and unlabelled features","created":"2022-06-15","cited_by_count":10,"area":null},{"id":"2302.04832","title":"Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting","created":"2023-02-09","cited_by_count":9,"area":null},{"id":"2311.18814","title":"Is Underwater Image Enhancement All Object Detectors Need?","created":"2023-11-30","cited_by_count":9,"area":null},{"id":"2203.17020","title":"Logit Normalization for Long-tail Object Detection","created":"2022-03-31","cited_by_count":8,"area":null},{"id":"2308.05168","title":"A Unified Interactive Model Evaluation for Classification, Object Detection, and Instance Segmentation in Computer Vision","created":"2023-08-09","cited_by_count":8,"area":null},{"id":"2410.05577","title":"Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future","created":"2024-10-08","cited_by_count":8,"area":null},{"id":"2104.14805","title":"Few-Shot Video Object Detection","created":"2021-04-30","cited_by_count":7,"area":null},{"id":"2203.07662","title":"What's in the Black Box? The False Negative Mechanisms Inside Object Detectors","created":"2022-03-15","cited_by_count":7,"area":null},{"id":"2310.18788","title":"PrObeD: Proactive Object Detection Wrapper","created":"2023-10-28","cited_by_count":7,"area":null},{"id":"2203.08049","title":"On Hyperbolic Embeddings in 2D Object Detection","created":"2022-03-15","cited_by_count":6,"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":"2209.04861","title":"Inverse Image Frequency for Long-tailed Image Recognition","created":"2022-09-11","cited_by_count":6,"area":null},{"id":"2308.14286","title":"Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection","created":"2023-08-28","cited_by_count":6,"area":"distill"},{"id":"2505.24189","title":"Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2106.02288","title":"Tackling the Background Bias in Sparse Object Detection via Cropped Windows","created":"2021-06-04","cited_by_count":5,"area":null},{"id":"2106.05665","title":"Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception","created":"2021-06-10","cited_by_count":5,"area":null},{"id":"2311.10437","title":"DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection","created":"2023-11-17","cited_by_count":5,"area":null},{"id":"2410.11774","title":"Fractal Calibration for long-tailed object detection","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2110.13110","title":"Diagnosing Errors in Video Relation Detectors","created":"2021-10-25","cited_by_count":4,"area":null},{"id":"2112.05533","title":"Error Diagnosis of Deep Monocular Depth Estimation Models","created":"2021-11-15","cited_by_count":4,"area":null},{"id":"2305.07663","title":"Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces","created":"2023-04-30","cited_by_count":4,"area":null},{"id":"2106.03496","title":"Self-Supervision & Meta-Learning for One-Shot Unsupervised Cross-Domain Detection","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2107.13627","title":"United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across Tasks","created":"2021-07-28","cited_by_count":3,"area":null},{"id":"2204.00147","title":"Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes","created":"2022-04-01","cited_by_count":3,"area":null},{"id":"2303.01920","title":"Robust Detection Outcome: A Metric for Pathology Detection in Medical Images","created":"2023-03-03","cited_by_count":3,"area":null},{"id":"2305.10801","title":"Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2311.04040","title":"Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated data","created":"2023-11-07","cited_by_count":3,"area":"distill"},{"id":"2411.09749","title":"RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering","created":"2024-11-14","cited_by_count":3,"area":null},{"id":"2411.14626","title":"Beneath the Surface: The Role of Underwater Image Enhancement in Object Detection","created":"2024-11-21","cited_by_count":3,"area":null},{"id":"2507.23295","title":"LED Benchmark: Diagnosing Structural Layout Errors for Document Layout Analysis","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2508.04943","title":"TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2508.18729","title":"Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2604.18076","title":"Class-specific diffusion models improve military object detection in a low-data domain","created":"2026-04-20","cited_by_count":3,"area":"diffusion"},{"id":"2307.11828","title":"Enhancing Your Trained DETRs with Box Refinement","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2308.06686","title":"TorchQL: A Programming Framework for Integrity Constraints in Machine Learning","created":"2023-08-13","cited_by_count":2,"area":null},{"id":"2312.13822","title":"Universal Noise Annotation: Unveiling the Impact of Noisy annotation on Object Detection","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2410.18919","title":"Optimizing Edge Offloading Decisions for Object Detection","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2503.19202","title":"Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2504.18510","title":"Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models","created":"2025-04-25","cited_by_count":2,"area":null},{"id":"2506.21042","title":"Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability","created":"2025-06-26","cited_by_count":2,"area":"diffusion"},{"id":"2601.16895","title":"Evaluating Large Vision-language Models for Surgical Tool Detection","created":"2026-01-23","cited_by_count":2,"area":"mllm"},{"id":"2603.23455","title":"DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection","created":"2026-03-24","cited_by_count":2,"area":"mllm"},{"id":"2110.13064","title":"2nd Place Solution for SODA10M Challenge 2021 -- Continual Detection Track","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2201.06444","title":"Black-box Error Diagnosis in Deep Neural Networks for Computer Vision: a Survey of Tools","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2207.04693","title":"Exploring Contextual Relationships for Cervical Abnormal Cell Detection","created":"2022-07-11","cited_by_count":1,"area":null},{"id":"2210.01402","title":"Streaming Video Analytics On The Edge With Asynchronous Cloud Support","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2210.08856","title":"TIVE: A Toolbox for Identifying Video Instance Segmentation Errors","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2210.12989","title":"Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2212.01376","title":"D2DF2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation","created":"2022-12-02","cited_by_count":1,"area":null},{"id":"2307.11748","title":"BandRe: Rethinking Band-Pass Filters for Scale-Wise Object Detection Evaluation","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2310.05447","title":"Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2311.12064","title":"Security Fence Inspection at Airports Using Object Detection","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2407.07780","title":"Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher","created":"2024-07-10","cited_by_count":1,"area":null},{"id":"2409.07907","title":"From COCO to COCO-FP: A Deep Dive into Background False Positives for COCO Detectors","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2502.12415","title":"Gaseous Object Detection","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2506.00997","title":"Pseudo-Labeling Driven Refinement of Benchmark Object Detection Datasets via Analysis of Learning Patterns","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2603.17265","title":"LED: A Benchmark for Evaluating Layout Error Detection in Document Analysis","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2107.05279","title":"ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment","created":"2021-07-12","cited_by_count":0,"area":null},{"id":"2206.10107","title":"Sensitivity of Average Precision to Bounding Box Perturbations","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2206.11473","title":"Complementary datasets to COCO for object detection","created":"2022-06-23","cited_by_count":0,"area":null},{"id":"2211.09022","title":"Label-Efficient Object Detection via Region Proposal Network Pre-Training","created":"2022-11-16","cited_by_count":0,"area":null},{"id":"2308.05032","title":"Density Crop-guided Semi-supervised Object Detection in Aerial Images","created":"2023-08-09","cited_by_count":0,"area":null},{"id":"2404.11266","title":"Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2407.09372","title":"Segmentation Dataset for Reinforced Concrete Construction","created":"2024-07-12","cited_by_count":0,"area":null},{"id":"2409.04025","title":"BFA-YOLO: A balanced multiscale object detection network for building fa\\c{c}ade attachments detection","created":"2024-09-06","cited_by_count":0,"area":null},{"id":"2411.17536","title":"Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2505.08170","title":"MoKD: Multi-Task Optimization for Knowledge Distillation","created":"2025-05-13","cited_by_count":0,"area":"distill"},{"id":"2601.13975","title":"Harmonizing the Deep: A Unified Information Pipeline for Robust Marine Biodiversity Assessment Across Heterogeneous Domains","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.05250","title":"Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images","created":"2026-02-05","cited_by_count":0,"area":null}],"next_cursor":"100"}