{"total":171,"rows":[{"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,"area":null},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158,"area":null},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2101.00529","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","created":"2021-01-02","cited_by_count":110,"area":"mllm"},{"id":"2105.13677","title":"ResT: An Efficient Transformer for Visual Recognition","created":"2021-05-28","cited_by_count":79,"area":null},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66,"area":null},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","cited_by_count":58,"area":null},{"id":"2204.08412","title":"Temporally Efficient Vision Transformer for Video Instance Segmentation","created":"2022-04-18","cited_by_count":55,"area":null},{"id":"2304.08876","title":"Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection","created":"2023-04-18","cited_by_count":43,"area":null},{"id":"2402.13144","title":"Neural Network Diffusion","created":"2024-02-20","cited_by_count":42,"area":"diffusion"},{"id":"2311.09847","title":"Overcoming Data Scarcity in Biomedical Imaging with a Foundational Multi-Task Model","created":"2023-11-16","cited_by_count":40,"area":null},{"id":"2206.07389","title":"Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification","created":"2022-06-15","cited_by_count":39,"area":null},{"id":"2303.08594","title":"FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation","created":"2023-03-15","cited_by_count":32,"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":"2406.09410","title":"STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery","created":"2024-06-13","cited_by_count":31,"area":null},{"id":"2301.10051","title":"Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism","created":"2023-01-24","cited_by_count":30,"area":null},{"id":"2205.15445","title":"Continual Object Detection: A review of definitions, strategies, and challenges","created":"2022-05-30","cited_by_count":25,"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":"2104.13395","title":"ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception","created":"2021-04-27","cited_by_count":21,"area":null},{"id":"2201.03080","title":"The State of Aerial Surveillance: A Survey","created":"2022-01-09","cited_by_count":20,"area":null},{"id":"2205.09363","title":"Plane Geometry Diagram Parsing","created":"2022-05-19","cited_by_count":20,"area":null},{"id":"2403.16092","title":"Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap","created":"2024-03-24","cited_by_count":20,"area":"driving"},{"id":"2411.16198","title":"Interpreting Object-level Foundation Models via Visual Precision Search","created":"2024-11-25","cited_by_count":20,"area":null},{"id":"2102.03026","title":"Instance and Panoptic Segmentation Using Conditional Convolutions","created":"2021-02-05","cited_by_count":19,"area":null},{"id":"2307.11035","title":"Cascade-DETR: Delving into High-Quality Universal Object Detection","created":"2023-07-20","cited_by_count":19,"area":null},{"id":"2301.00394","title":"Deep Learning Technique for Human Parsing: A Survey and Outlook","created":"2023-01-01","cited_by_count":18,"area":null},{"id":"2312.04548","title":"Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?","created":"2023-12-07","cited_by_count":18,"area":null},{"id":"2312.02481","title":"Learning to Holistically Detect Bridges from Large-Size VHR Remote Sensing Imagery","created":"2023-12-05","cited_by_count":17,"area":null},{"id":"2103.06796","title":"Unknown Object Segmentation from Stereo Images","created":"2021-03-11","cited_by_count":16,"area":null},{"id":"2204.11402","title":"PointInst3D: Segmenting 3D Instances by Points","created":"2022-04-25","cited_by_count":16,"area":null},{"id":"2303.14960","title":"Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection","created":"2023-03-27","cited_by_count":14,"area":null},{"id":"2308.09098","title":"ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection","created":"2023-08-17","cited_by_count":14,"area":null},{"id":"2107.13155","title":"Improving Video Instance Segmentation via Temporal Pyramid Routing","created":"2021-07-28","cited_by_count":13,"area":null},{"id":"2206.13381","title":"TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask","created":"2022-06-27","cited_by_count":13,"area":null},{"id":"2303.12396","title":"Rigidity-Aware Detection for 6D Object Pose Estimation","created":"2023-03-22","cited_by_count":13,"area":null},{"id":"2403.11127","title":"GRA: Detecting Oriented Objects through Group-wise Rotating and Attention","created":"2024-03-17","cited_by_count":13,"area":null},{"id":"2504.20670","title":"FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection","created":"2025-04-29","cited_by_count":13,"area":null},{"id":"2211.03850","title":"Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding","created":"2022-11-07","cited_by_count":12,"area":null},{"id":"2304.05071","title":"Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm","created":"2023-04-11","cited_by_count":12,"area":null},{"id":"2104.12041","title":"Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy","created":"2021-04-25","cited_by_count":11,"area":null},{"id":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2111.10780","title":"FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection","created":"2021-11-21","cited_by_count":10,"area":null},{"id":"2406.16384","title":"High-resolution open-vocabulary object 6D pose estimation","created":"2024-06-24","cited_by_count":10,"area":null},{"id":"2204.08394","title":"CenterNet++ for Object Detection","created":"2022-04-18","cited_by_count":9,"area":null},{"id":"2501.09720","title":"A Simple Aerial Detection Baseline of Multimodal Language Models","created":"2025-01-16","cited_by_count":9,"area":"mllm"},{"id":"2501.13898","title":"PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection","created":"2025-01-23","cited_by_count":9,"area":null},{"id":"2503.08043","title":"Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation","created":"2025-03-11","cited_by_count":9,"area":"distill"},{"id":"2503.10152","title":"A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection","created":"2025-03-13","cited_by_count":9,"area":"mllm"},{"id":"2104.04899","title":"Location-Sensitive Visual Recognition with Cross-IOU Loss","created":"2021-04-11","cited_by_count":8,"area":null},{"id":"2208.08621","title":"Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes","created":"2022-08-18","cited_by_count":8,"area":null},{"id":"2304.11805","title":"OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2112.04481","title":"What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstruction","created":"2021-12-08","cited_by_count":7,"area":null},{"id":"2405.00494","title":"GOLD: Geometry Problem Solver with Natural Language Description","created":"2024-05-01","cited_by_count":7,"area":null},{"id":"2407.18487","title":"SMPISD-MTPNet: Scene Semantic Prior-Assisted Infrared Ship Detection Using Multi-Task Perception Networks","created":"2024-07-26","cited_by_count":7,"area":null},{"id":"2408.01934","title":"A Survey and Evaluation of Adversarial Attacks for Object Detection","created":"2024-08-04","cited_by_count":7,"area":null},{"id":"2408.09332","title":"YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems","created":"2024-08-18","cited_by_count":7,"area":null},{"id":"2503.14012","title":"LEGNet: A Lightweight Edge-Gaussian Network for Low-Quality Remote Sensing Image Object Detection","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2508.20063","title":"OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations","created":"2025-08-27","cited_by_count":7,"area":null},{"id":"2101.11782","title":"Object Detection Made Simpler by Eliminating Heuristic NMS","created":"2021-01-28","cited_by_count":6,"area":null},{"id":"2207.05252","title":"Dynamic Proposals for Efficient Object Detection","created":"2022-07-12","cited_by_count":6,"area":null},{"id":"2303.17594","title":"MobileInst: Video Instance Segmentation on the Mobile","created":"2023-03-30","cited_by_count":6,"area":null},{"id":"2406.05810","title":"ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Driving","created":"2024-06-09","cited_by_count":6,"area":null},{"id":"2409.05650","title":"Replay Consolidation with Label Propagation for Continual Object Detection","created":"2024-09-09","cited_by_count":6,"area":null},{"id":"2503.02101","title":"Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection","created":"2025-03-03","cited_by_count":6,"area":"diffusion"},{"id":"2509.26037","title":"CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search","created":"2025-09-30","cited_by_count":6,"area":null},{"id":"2112.13608","title":"An Empirical Study of Adder Neural Networks for Object Detection","created":"2021-12-27","cited_by_count":5,"area":null},{"id":"2207.01842","title":"ORF-Net: Deep Omni-supervised Rib Fracture Detection from Chest CT Scans","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2208.00817","title":"DSLA: Dynamic smooth label assignment for efficient anchor-free object detection","created":"2022-08-01","cited_by_count":5,"area":null},{"id":"2308.02213","title":"Balanced Classification: A Unified Framework for Long-Tailed Object Detection","created":"2023-08-04","cited_by_count":5,"area":null},{"id":"2410.04546","title":"Learning De-Biased Representations for Remote-Sensing Imagery","created":"2024-10-06","cited_by_count":5,"area":null},{"id":"2412.12830","title":"Differential Alignment for Domain Adaptive Object Detection","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2505.16740","title":"Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2203.15687","title":"Texture based Prototypical Network for Few-Shot Semantic Segmentation of Forest Cover: Generalizing for Different Geographical Regions","created":"2022-03-29","cited_by_count":4,"area":null},{"id":"2210.01370","title":"Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2308.04025","title":"MSAC: Multiple Speech Attribute Control Method for Reliable Speech Emotion Recognition","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2404.02634","title":"3DStyleGLIP: Part-Tailored Text-Guided 3D Neural Stylization","created":"2024-04-03","cited_by_count":4,"area":null},{"id":"2405.19854","title":"RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection","created":"2024-05-30","cited_by_count":4,"area":null},{"id":"2407.04711","title":"MetaFruit Meets Foundation Models: Leveraging a Comprehensive Multi-Fruit Dataset for Advancing Agricultural Foundation Models","created":"2024-05-14","cited_by_count":4,"area":null},{"id":"2409.01872","title":"Latent Distillation for Continual Object Detection at the Edge","created":"2024-09-03","cited_by_count":4,"area":null},{"id":"2411.12301","title":"Physics-Guided Detector for SAR Airplanes","created":"2024-11-19","cited_by_count":4,"area":null},{"id":"2502.17673","title":"Semi-Supervised Weed Detection in Vegetable Fields: In-domain and Cross-domain Experiments","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2506.04211","title":"Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector","created":"2025-06-04","cited_by_count":4,"area":"diffusion"},{"id":"2103.09488","title":"Revisiting the Loss Weight Adjustment in Object Detection","created":"2021-03-17","cited_by_count":3,"area":null},{"id":"2107.08392","title":"Dynamic Convolution for 3D Point Cloud Instance Segmentation","created":"2021-07-18","cited_by_count":3,"area":null},{"id":"2112.09442","title":"Adaptively Customizing Activation Functions for Various Layers","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2205.00376","title":"Traffic Context Aware Data Augmentation for Rare Object Detection in Autonomous Driving","created":"2022-05-01","cited_by_count":3,"area":null},{"id":"2304.10226","title":"Domain Generalization for Mammographic Image Analysis with Contrastive Learning","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2307.09264","title":"Knowledge Distillation for Object Detection: from generic to remote sensing datasets","created":"2023-07-18","cited_by_count":3,"area":"distill"},{"id":"2406.06028","title":"ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagery","created":"2024-06-10","cited_by_count":3,"area":null},{"id":"2406.18443","title":"Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundary","created":"2024-06-26","cited_by_count":3,"area":null},{"id":"2412.11582","title":"Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2506.09541","title":"3DGeoDet: General-purpose Geometry-aware Image-based 3D Object Detection","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2508.15272","title":"RATopo: Improving Lane Topology Reasoning via Redundancy Assignment","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2511.17674","title":"Person Recognition in Aerial Surveillance: A Decade Survey","created":"2025-11-21","cited_by_count":3,"area":null},{"id":"2107.05093","title":"SE-PSNet: Silhouette-based Enhancement Feature for Panoptic Segmentation Network","created":"2021-07-11","cited_by_count":2,"area":null},{"id":"2112.08743","title":"Radio-Assisted Human Detection","created":"2021-12-16","cited_by_count":2,"area":null}],"next_cursor":"100"}