{"total":71,"rows":[{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302,"area":null},{"id":"2304.03752","title":"V3Det: Vast Vocabulary Visual Detection Dataset","created":"2023-04-07","cited_by_count":81,"area":null},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2401.03989","title":"MS-DETR: Efficient DETR Training with Mixed Supervision","created":"2024-01-08","cited_by_count":35,"area":null},{"id":"2404.03507","title":"DQ-DETR: DETR with Dynamic Query for Tiny Object Detection","created":"2024-04-04","cited_by_count":28,"area":null},{"id":"2407.11699","title":"Relation DETR: Exploring Explicit Position Relation Prior for Object Detection","created":"2024-07-16","cited_by_count":28,"area":null},{"id":"2308.15949","title":"Latency-aware Unified Dynamic Networks for Efficient Image Recognition","created":"2023-08-30","cited_by_count":26,"area":null},{"id":"2410.22939","title":"AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection","created":"2024-10-30","cited_by_count":18,"area":null},{"id":"2312.09501","title":"EDA: Evolving and Distinct Anchors for Multimodal Motion Prediction","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2404.17360","title":"UniRGB-IR: A Unified Framework for Visible-Infrared Semantic Tasks via Adapter Tuning","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2401.10731","title":"Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection","created":"2024-01-19","cited_by_count":16,"area":null},{"id":"2409.13366","title":"RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning","created":"2024-09-20","cited_by_count":15,"area":null},{"id":"2409.19833","title":"HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes","created":"2024-09-30","cited_by_count":15,"area":null},{"id":"2410.19635","title":"Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models","created":"2024-10-25","cited_by_count":13,"area":null},{"id":"2311.01025","title":"Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2409.19648","title":"OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images","created":"2024-09-29","cited_by_count":10,"area":null},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10,"area":null},{"id":"2305.07598","title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","created":"2023-05-12","cited_by_count":9,"area":null},{"id":"2309.13242","title":"UniHead: Unifying Multi-Perception for Detection Heads","created":"2023-09-23","cited_by_count":9,"area":null},{"id":"2503.01463","title":"MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2304.04978","title":"StageInteractor: Query-based Object Detector with Cross-stage Interaction","created":"2023-04-11","cited_by_count":8,"area":null},{"id":"2306.07265","title":"detrex: Benchmarking Detection Transformers","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2502.05147","title":"LP-DETR: Layer-wise Progressive Relations for Object Detection","created":"2025-02-07","cited_by_count":8,"area":null},{"id":"2406.03095","title":"EgoSurgery-Tool: A Dataset of Surgical Tool and Hand Detection from Egocentric Open Surgery Videos","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2502.13023","title":"Detection and Geographic Localization of Natural Objects in the Wild: A Case Study on Palms","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2502.14063","title":"PedDet: Adaptive Spectral Optimization for Multimodal Pedestrian Detection","created":"2025-02-19","cited_by_count":6,"area":null},{"id":"2505.05741","title":"Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection","created":"2025-05-09","cited_by_count":6,"area":null},{"id":"2305.00675","title":"End-to-End Lane detection with One-to-Several Transformer","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2504.11999","title":"A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learning","created":"2025-04-16","cited_by_count":5,"area":null},{"id":"2403.19893","title":"PLoc: A New Evaluation Criterion Based on Physical Location for Autonomous Driving Datasets","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2410.12143","title":"Mixture of Scale Experts for Alignment-free RGBT Video Object Detection and A Unified Benchmark","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2411.18288","title":"Optimizing Multispectral Object Detection: A Bag of Tricks and Comprehensive Benchmarks","created":"2024-11-27","cited_by_count":4,"area":null},{"id":"2601.02249","title":"SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detection","created":"2026-01-05","cited_by_count":4,"area":null},{"id":"2603.06917","title":"PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection","created":"2026-03-06","cited_by_count":4,"area":null},{"id":"2306.09165","title":"DEYOv2: Rank Feature with Greedy Matching for End-to-End Object Detection","created":"2023-06-15","cited_by_count":3,"area":null},{"id":"2312.13735","title":"DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2502.07821","title":"Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2512.16818","title":"DenseBEV: Transforming BEV Grid Cells into 3D Objects","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2603.28182","title":"A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2312.00699","title":"Rethinking Detection Based Table Structure Recognition for Visually Rich Document Images","created":"2023-12-01","cited_by_count":1,"area":null},{"id":"2505.23193","title":"Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.19807","title":"DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2509.08738","title":"CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2509.19990","title":"SDE-DET: A Precision Network for Shatian Pomelo Detection in Complex Orchard Environments","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2512.01315","title":"FOD-S2R: A FOD Dataset for Sim2Real Transfer Learning based Object Detection","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2604.11234","title":"Bridging the RGB-IR Gap: Consensus and Discrepancy Modeling for Text-Guided Multispectral Detection","created":"2026-04-13","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":"2605.13621","title":"WD-FQDet: Multispectral Detection Transformer via Wavelet Decomposition and Frequency-aware Query Learning","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.23507","title":"MDS-DETR: DETR with Masked Duplicate Suppressor","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2608.27971","title":"GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2306.10858","title":"Multi-Granularity Hand Action Detection","created":"2023-06-19","cited_by_count":0,"area":null},{"id":"2310.15725","title":"Ranking-based Adaptive Query Generation for DETRs in Crowded Pedestrian Detection","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2312.08268","title":"Efficient Multi-Object Pose Estimation using Multi-Resolution Deformable Attention and Query Aggregation","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2408.09181","title":"PADetBench: Towards Benchmarking Physical Attacks against Object Detection","created":"2024-08-17","cited_by_count":0,"area":null},{"id":"2411.10497","title":"Structure Tensor Representation for Robust Oriented Object Detection","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2504.11779","title":"Multimodal Spatio-temporal Graph Learning for Alignment-free RGBT Video Object Detection","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2505.10825","title":"A High-Performance Thermal Infrared Object Detection Framework with Centralized Regulation","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2508.03243","title":"MVTOP: Multi-View Transformer-based Object Pose-Estimation","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2508.19850","title":"Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2601.09812","title":"LCF3D: A Robust and Real-Time Late-Cascade Fusion Framework for 3D Object Detection in Autonomous Driving","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2603.03788","title":"Small Object Detection in Complex Backgrounds with Multi-Scale Attention and Global Relation Modeling","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.03176","title":"SFFNet: Synergistic Feature Fusion Network With Dual-Domain Edge Enhancement for UAV Image Object Detection","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.13244","title":"4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.24508","title":"FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2607.08191","title":"Dual-Correlation Hypergraph Network for Unaligned RGBT Video Object Detection and A Large-scale Benchmark","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.04766","title":"FUSEP: A Multi-Center Benchmark for Diverse Tasks in Early Pregnancy Fetal Ultrasound Screening","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.21099","title":"A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.30839","title":"Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.15354","title":"End-to-End Cell Detection via Instance-aware Graph Modeling","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.26092","title":"Match One, Learn with Graph: One-to-Graph Query Collaboration with Backward Sharing for Object Detection","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2610.05191","title":"Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}