{"total":67,"rows":[{"id":"2403.00326","title":"DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion","created":"2024-03-01","cited_by_count":28,"area":null},{"id":"2403.09323","title":"E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection","created":"2024-03-14","cited_by_count":21,"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":"2505.10931","title":"M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2507.16318","title":"M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision","created":"2025-07-22","cited_by_count":8,"area":null},{"id":"2507.14643","title":"Multispectral State-Space Feature Fusion: Bridging Shared and Cross-Parametric Interactions for Object Detection","created":"2025-07-19","cited_by_count":6,"area":null},{"id":"2408.06123","title":"DPDETR: Decoupled Position Detection Transformer for Infrared-Visible Object Detection","created":"2024-08-12","cited_by_count":5,"area":null},{"id":"2509.23316","title":"C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection","created":"2025-09-27","cited_by_count":5,"area":null},{"id":"2411.12301","title":"Physics-Guided Detector for SAR Airplanes","created":"2024-11-19","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":"2506.16737","title":"Cross-modal Offset-guided Dynamic Alignment and Fusion for Weakly Aligned UAV Object Detection","created":"2025-06-20","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":"2403.15209","title":"MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2506.14696","title":"YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection Framework","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2508.02384","title":"SMART-Ship: A Comprehensive Synchronized Multi-modal Aligned Remote Sensing Targets Dataset and Benchmark for Berthed Ships Analysis","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2505.17911","title":"Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2509.09085","title":"IRDFusion: Iterative Relation-Map Difference guided Feature Fusion for Multispectral Object Detection","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2511.06298","title":"SFFR: Spatial-Frequency Feature Reconstruction for Multispectral Aerial Object Detection","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2511.13607","title":"ICLR: Inter-Chrominance and Luminance Interaction for Natural Color Restoration in Low-Light Image Enhancement","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2512.22447","title":"Towards Robust Optical-SAR Object Detection under Missing Modalities: A Dynamic Quality-Aware Fusion Framework","created":"2025-12-27","cited_by_count":2,"area":null},{"id":"2412.16654","title":"IV-tuning: Parameter-Efficient Transfer Learning for Infrared-Visible Tasks","created":"2024-12-21","cited_by_count":1,"area":null},{"id":"2502.09311","title":"Mitigating the Impact of Prominent Position Shift in Drone-based RGBT Object Detection","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2507.20146","title":"AlignFreeNet: Is Cross-Modal Pre-Alignment Necessary? An End-to-End Alignment-Free Lightweight Network for Visible-Infrared Object Detection","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2508.10445","title":"DOD-SA: Infrared-Visible Decoupled Object Detection with Single-Modality Annotations","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2511.06406","title":"On Modality Incomplete Infrared-Visible Object Detection: An Architecture Compatibility Perspective","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2511.15433","title":"Representation Space Constrained Learning with Modality Decoupling for Multimodal Object Detection","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2601.00598","title":"Modality Dominance-Aware Optimization for Embodied RGB-Infrared Perception","created":"2026-01-02","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":"2605.04675","title":"Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2607.16327","title":"Localization-Infused Vision-Language Semantic Fusion for Text-Guided Medical Image Segmentation","created":"2026-07-15","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":"2407.03872","title":"The Solution for the GAIIC2024 RGB-TIR object detection Challenge","created":"2024-07-04","cited_by_count":0,"area":null},{"id":"2409.00973","title":"IVGF: The Fusion-Guided Infrared and Visible General Framework","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2505.02586","title":"RGBX-DiffusionDet: A Framework for Multi-Modal RGB-X Object Detection Using DiffusionDet","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2505.06937","title":"Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network","created":"2025-05-11","cited_by_count":0,"area":null},{"id":"2505.15137","title":"Multispectral Detection Transformer with Infrared-Centric Feature Fusion","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2506.21018","title":"LASFNet: A Lightweight Attention-Guided Self-Modulation Feature Fusion Network for Multimodal Object Detection","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2512.15971","title":"From Words to Wavelengths: VLMs for Few-Shot Multispectral Object Detection","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2512.18291","title":"PACGNet: Pyramidal Adaptive Cross-Gating Network for Multimodal Object Detection in Aerial Imagery","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2512.18689","title":"Fusion of Multiscale Features Via Centralized Sparse-attention Network for EEG Decoding","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2601.08458","title":"Modality-Decoupled RGB-Thermal Object Detector via Query Fusion","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.14776","title":"M2I2HA: Multi-modal Object Detection Based on Intra- and Inter-Modal Hypergraph Attention","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.06363","title":"Robust Pedestrian Detection with Uncertain Modality","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.06925","title":"Small Target Detection Based on Mask-Enhanced Attention Fusion of Visible and Infrared Remote Sensing Images","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2605.11799","title":"SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.20667","title":"LER-YOLO: Reliability-Aware Expert Routing for Misaligned RGB-Infrared UAV Detection","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.24092","title":"Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.30215","title":"Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.31015","title":"Dual Sparse Aggregation Transformer for Multispectral Object Detection","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.03795","title":"InfraNet: Quality-Aware RGB Guidance for Efficient Infrared Object Detection","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.05153","title":"Geometric Causal Models","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08076","title":"LDFE: Laplacian Decoupled Feature Enhancement Block for Dual-Stream CNN-based RGB-IR Object Detection","created":"2026-07-09","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":"2608.01302","title":"Beyond Symmetric Fusion: Exploiting Task-Dependent Modality Strengths for RGB-Event Small Object Detection","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.02092","title":"Deep Multimodal Fusion Detection through Spatial Mask and Channel Competition","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.03370","title":"DRPFNet: Dual-domain Residual Progressive Fusion Network for RGB-Thermal Object Detection","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.04833","title":"RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.06205","title":"CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detection","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.10680","title":"Bridging Severe Cross-Modal Misalignment: End-to-End Visible-Infrared Object Detection via Explicit Feature-Domain Affine Registration","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.11685","title":"EGM-Det: Entropy-Guided Multimodal Adaptive Fusion for UAV RGB-IR Object Detection","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.15261","title":"Boundary-Aligned Contribution Routing for Robust Optical--SAR Object Detection","created":"2026-08-15","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":"2609.03516","title":"Residual Optimal Transport-Based Experts Collaboration Towards Modality-Aware Infrared-Visible Object Detection","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.12521","title":"Aligned Radiometric RGB-Thermal Fusion for UAV Facade Anomaly Screening","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.18133","title":"Stealthy in Semantics, Antagonistic in Space: Attacking Visible-Infrared Object Detectors via Object-Level Misalignment","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.29125","title":"FoCal: Frequency-Oriented Cross-Modal Interaction and Spectral Calibration for Aerial Visible-Infrared Object Detection","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}