{"total":116,"rows":[{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071,"area":null},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724,"area":null},{"id":"2207.13085","title":"Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment","created":"2022-07-26","cited_by_count":98,"area":null},{"id":"2203.02431","title":"Rethinking Efficient Lane Detection via Curve Modeling","created":"2022-03-04","cited_by_count":88,"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":"2212.03241","title":"P{\\O}DA: Prompt-driven Zero-shot Domain Adaptation","created":"2022-12-06","cited_by_count":60,"area":null},{"id":"2305.04925","title":"PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds","created":"2023-05-08","cited_by_count":54,"area":null},{"id":"2105.04322","title":"RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation","created":"2021-05-10","cited_by_count":52,"area":null},{"id":"2208.08738","title":"RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection","created":"2022-08-18","cited_by_count":51,"area":null},{"id":"2309.11331","title":"Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism","created":"2023-09-20","cited_by_count":51,"area":null},{"id":"2212.06137","title":"NMS Strikes Back","created":"2022-12-12","cited_by_count":33,"area":null},{"id":"2108.12102","title":"FOVEA: Foveated Image Magnification for Autonomous Navigation","created":"2021-08-27","cited_by_count":32,"area":null},{"id":"2109.07107","title":"Anchor DETR: Query Design for Transformer-Based Object Detection","created":"2021-09-15","cited_by_count":30,"area":null},{"id":"2311.14758","title":"Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision","created":"2023-11-23","cited_by_count":21,"area":null},{"id":"2212.05680","title":"REAP: A Large-Scale Realistic Adversarial Patch Benchmark","created":"2022-12-12","cited_by_count":18,"area":null},{"id":"2212.07778","title":"Efficient Visual Computing with Camera RAW Snapshots","created":"2022-12-15","cited_by_count":18,"area":null},{"id":"2108.10520","title":"Improving Object Detection by Label Assignment Distillation","created":"2021-08-24","cited_by_count":17,"area":null},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2307.02733","title":"MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection","created":"2023-07-06","cited_by_count":15,"area":null},{"id":"2207.12926","title":"A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2210.02093","title":"Centralized Feature Pyramid for Object Detection","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2207.05345","title":"HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors","created":"2022-07-12","cited_by_count":12,"area":"distill"},{"id":"2207.07889","title":"You Should Look at All Objects","created":"2022-07-16","cited_by_count":12,"area":null},{"id":"2203.14438","title":"Optimal Correction Cost for Object Detection Evaluation","created":"2022-03-28","cited_by_count":11,"area":null},{"id":"2201.11620","title":"Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center study","created":"2022-01-27","cited_by_count":10,"area":null},{"id":"2306.08370","title":"Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation","created":"2023-06-14","cited_by_count":10,"area":null},{"id":"2307.07662","title":"MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression","created":"2023-07-14","cited_by_count":10,"area":null},{"id":"2506.19472","title":"USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation","created":"2025-06-24","cited_by_count":10,"area":null},{"id":"2407.20078","title":"Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection","created":"2024-07-29","cited_by_count":9,"area":null},{"id":"2210.04399","title":"Deep Learning for Logo Detection: A Survey","created":"2022-10-10","cited_by_count":8,"area":null},{"id":"2310.17294","title":"Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution","created":"2023-10-26","cited_by_count":8,"area":null},{"id":"2403.01123","title":"ELA: Efficient Local Attention for Deep Convolutional Neural Networks","created":"2024-03-02","cited_by_count":8,"area":null},{"id":"2406.02833","title":"DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2502.01785","title":"AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis","created":"2025-02-03","cited_by_count":7,"area":"mllm"},{"id":"2603.26735","title":"Distilled Large Language Model-Driven Dynamic Sparse Expert Activation Mechanism","created":"2026-03-21","cited_by_count":7,"area":"moe"},{"id":"2210.06008","title":"BoxMask: Revisiting Bounding Box Supervision for Video Object Detection","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2211.08055","title":"PAI3D: Painting Adaptive Instance-Prior for 3D Object Detection","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2307.00592","title":"X-MLP: A Patch Embedding-Free MLP Architecture for Vision","created":"2023-07-02","cited_by_count":6,"area":null},{"id":"2410.17144","title":"YOLO-TS: Real-Time Traffic Sign Detection with Enhanced Accuracy Using Optimized Receptive Fields and Anchor-Free Fusion","created":"2024-10-22","cited_by_count":6,"area":null},{"id":"2502.09471","title":"Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection","created":"2025-02-13","cited_by_count":6,"area":null},{"id":"2108.12313","title":"TE-YOLOF: Tiny and efficient YOLOF for blood cell detection","created":"2021-08-27","cited_by_count":5,"area":null},{"id":"2109.08963","title":"SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2206.06829","title":"Efficient Decoder-free Object Detection with Transformers","created":"2022-06-14","cited_by_count":5,"area":null},{"id":"2212.04111","title":"Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Framework","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2305.04170","title":"YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification","created":"2023-05-07","cited_by_count":4,"area":null},{"id":"2312.01789","title":"Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical world","created":"2023-12-04","cited_by_count":4,"area":null},{"id":"2409.17963","title":"CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2505.08808","title":"SparseMeXT Unlocking the Potential of Sparse Representations for HD Map Construction","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2509.17968","title":"Visual Detector Compression via Location-Aware Discriminant Analysis","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2110.00523","title":"Mask or Non-Mask? Robust Face Mask Detector via Triplet-Consistency Representation Learning","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2303.01047","title":"Task-Specific Context Decoupling for Object Detection","created":"2023-03-02","cited_by_count":3,"area":null},{"id":"2401.06374","title":"SamLP: A Customized Segment Anything Model for License Plate Detection","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2503.06313","title":"Advancing Autonomous Vehicle Intelligence: Deep Learning and Multimodal LLM for Traffic Sign Recognition and Robust Lane Detection","created":"2025-03-08","cited_by_count":3,"area":"driving"},{"id":"2601.18597","title":"EFSI-DETR: Efficient Frequency-Semantic Integration for Real-Time Small Object Detection in UAV Imagery","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2112.02891","title":"Seeing Objects in dark with Continual Contrastive Learning","created":"2021-12-06","cited_by_count":2,"area":null},{"id":"2203.04799","title":"Evaluation of YOLO Models with Sliced Inference for Small Object Detection","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2209.03157","title":"FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications","created":"2022-09-07","cited_by_count":2,"area":null},{"id":"2302.09365","title":"Hyneter: Hybrid Network Transformer for Object Detection","created":"2023-02-18","cited_by_count":2,"area":null},{"id":"2303.02512","title":"Visual Saliency-Guided Channel Pruning for Deep Visual Detectors in Autonomous Driving","created":"2023-03-04","cited_by_count":2,"area":null},{"id":"2305.01183","title":"Faster OreFSDet : A Lightweight and Effective Few-shot Object Detector for Ore Images","created":"2023-05-02","cited_by_count":2,"area":null},{"id":"2310.07212","title":"Multi-Task Learning-Enabled Automatic Vessel Draft Reading for Intelligent Maritime Surveillance","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2408.05729","title":"A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot","created":"2024-08-11","cited_by_count":2,"area":null},{"id":"2505.15184","title":"AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2508.09392","title":"DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection","created":"2025-08-12","cited_by_count":2,"area":null},{"id":"2601.09247","title":"Integrating Diverse Assignment Strategies into DETRs","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2110.03368","title":"A Baseline Framework for Part-level Action Parsing and Action Recognition","created":"2021-10-07","cited_by_count":1,"area":null},{"id":"2203.04476","title":"Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework","created":"2022-03-09","cited_by_count":1,"area":null},{"id":"2208.03779","title":"Sample hardness based gradient loss for long-tailed cervical cell detection","created":"2022-08-07","cited_by_count":1,"area":null},{"id":"2208.06114","title":"MAIScope: A low-cost portable microscope with built-in vision AI to automate microscopic diagnosis of diseases in remote rural settings","created":"2022-08-12","cited_by_count":1,"area":null},{"id":"2212.09039","title":"Automated Optical Inspection of FAST's Reflector Surface using Drones and Computer Vision","created":"2022-12-18","cited_by_count":1,"area":null},{"id":"2305.15114","title":"Thinking Twice: Clinical-Inspired Thyroid Ultrasound Lesion Detection Based on Feature Feedback","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2312.05832","title":"Spatial-wise Dynamic Distillation for MLP-like Efficient Visual Fault Detection of Freight Trains","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2403.05754","title":"Hybrid Quantum-inspired Resnet and Densenet for Pattern Recognition","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2405.17004","title":"Efficient Visual Fault Detection for Freight Train via Neural Architecture Search with Data Volume Robustness","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2406.14239","title":"LeYOLO, New Embedded Architecture for Object Detection","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2407.16129","title":"FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2410.08713","title":"Impact of Surface Reflections in Maritime Obstacle Detection","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2410.17734","title":"YOLO-Vehicle-Pro: A Cloud-Edge Collaborative Framework for Object Detection in Autonomous Driving under Adverse Weather Conditions","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2410.17822","title":"DREB-Net: Dual-stream Restoration Embedding Blur-feature Fusion Network for High-mobility UAV Object Detection","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2410.21361","title":"Domain Adaptation with a Single Vision-Language Embedding","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2511.01435","title":"Contrast-Guided Cross-Modal Distillation for Thermal Object Detection","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2512.18245","title":"Spectral Discrepancy and Cross-modal Semantic Consistency Learning for Object Detection in Hyperspectral Image","created":"2025-12-20","cited_by_count":1,"area":null},{"id":"2604.23718","title":"Caries DETR: Tooth Structure-aware Prior and Lesion-aware Dynamic Loss Refinement for DETR Based Caries Detection","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2608.07571","title":"A Review of Vision-Based Vehicle Detection for UAV-Based Traffic Monitoring: Experimental Insights and Future Directions","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2109.07217","title":"Progressive Hard-case Mining across Pyramid Levels for Object Detection","created":"2021-09-15","cited_by_count":0,"area":null},{"id":"2112.00342","title":"Confidence Propagation Cluster: Unleash Full Potential of Object Detectors","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2201.02314","title":"RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images","created":"2022-01-07","cited_by_count":0,"area":null},{"id":"2203.00862","title":"SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment","created":"2022-03-02","cited_by_count":0,"area":null},{"id":"2204.01795","title":"Lightweight HDR Camera ISP for Robust Perception in Dynamic Illumination Conditions via Fourier Adversarial Networks","created":"2022-04-04","cited_by_count":0,"area":null},{"id":"2205.12458","title":"A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains","created":"2022-05-25","cited_by_count":0,"area":null},{"id":"2206.11825","title":"YOLOSA: Object detection based on 2D local feature superimposed self-attention","created":"2022-06-23","cited_by_count":0,"area":null},{"id":"2208.01424","title":"Connection Reduction of DenseNet for Image Recognition","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2210.03883","title":"Rethinking the Detection Head Configuration for Traffic Object Detection","created":"2022-10-08","cited_by_count":0,"area":null},{"id":"2210.10998","title":"Semi-supervised object detection based on single-stage detector for thighbone fracture localization","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2301.05957","title":"Towards Spatial Equilibrium Object Detection","created":"2023-01-14","cited_by_count":0,"area":null},{"id":"2302.11095","title":"MM-SFENet: Multi-scale Multi-task Localization and Classification of Bladder Cancer in MRI with Spatial Feature Encoder Network","created":"2023-02-22","cited_by_count":0,"area":null},{"id":"2303.14977","title":"A novel Multi to Single Module for small object detection","created":"2023-03-27","cited_by_count":0,"area":null},{"id":"2304.04963","title":"PlantDet: A benchmark for Plant Detection in the Three-Rivers-Source Region","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2307.16751","title":"High-Performance Fine Defect Detection in Artificial Leather Using Dual Feature Pool Object Detection","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2309.11002","title":"PPD: A New Valet Parking Pedestrian Fisheye Dataset for Autonomous Driving","created":"2023-09-20","cited_by_count":0,"area":null}],"next_cursor":"100"}