{"total":58,"rows":[{"id":"2404.09146","title":"Fusion-Mamba for Cross-modality Object Detection","created":"2024-04-14","cited_by_count":67,"area":"ssm"},{"id":"2307.14682","title":"Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World","created":"2023-07-27","cited_by_count":21,"area":null},{"id":"2407.08132","title":"DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing","created":"2024-07-11","cited_by_count":20,"area":"ssm"},{"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":"2507.18173","title":"WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection","created":"2025-07-24","cited_by_count":14,"area":"ssm"},{"id":"2507.16318","title":"M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision","created":"2025-07-22","cited_by_count":8,"area":null},{"id":"2508.06878","title":"Seeing Through the Noise: Improving Infrared Small Target Detection and Segmentation from Noise Suppression Perspective","created":"2025-08-09","cited_by_count":8,"area":null},{"id":"2410.13532","title":"RemoteDet-Mamba: A Hybrid Mamba-CNN Network for Multi-modal Object Detection in Remote Sensing Images","created":"2024-10-17","cited_by_count":7,"area":"ssm"},{"id":"2505.00630","title":"Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook","created":"2025-05-01","cited_by_count":6,"area":"ssm"},{"id":"2510.13620","title":"Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues","created":"2025-10-15","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":"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":"2504.07603","title":"RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions","created":"2025-04-10","cited_by_count":3,"area":null},{"id":"2512.24561","title":"RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2405.18955","title":"RGB-T Object Detection via Group Shuffled Multi-receptive Attention and Multi-modal Supervision","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2412.05969","title":"Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation","created":"2024-12-08","cited_by_count":2,"area":null},{"id":"2505.14043","title":"Selective Structured State Space for Multispectral-fused Small Target Detection","created":"2025-05-20","cited_by_count":2,"area":"ssm"},{"id":"2507.00849","title":"UAVD-Mamba: Deformable Token Fusion Vision Mamba for Multimodal UAV Detection","created":"2025-07-01","cited_by_count":2,"area":"ssm"},{"id":"2508.09533","title":"COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2509.07327","title":"DEPFusion: Dual-Domain Enhancement and Priority-Guided Mamba Fusion for UAV Multispectral Object Detection","created":"2025-09-09","cited_by_count":2,"area":"ssm"},{"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":"2407.16129","title":"FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network","created":"2024-07-23","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":"2603.01758","title":"Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.06920","title":"DLRMamba: Distilling Low-Rank Mamba for Edge Multispectral Fusion Object Detection","created":"2026-03-06","cited_by_count":1,"area":"ssm"},{"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":"2605.13621","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":"2308.01042","title":"WCCNet: Wavelet-context Cooperative Network for Efficient Multispectral Pedestrian Detection","created":"2023-08-02","cited_by_count":0,"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":"2503.06948","title":"Large Language Model Guided Progressive Feature Alignment for Multimodal UAV Object Detection","created":"2025-03-10","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":"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":"2506.23252","title":"DGE-YOLO: Dual-Branch Gathering and Attention for Accurate UAV Object Detection","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2509.16957","title":"MO R-CNN: Multispectral Oriented R-CNN for Object Detection in Remote Sensing Image","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2512.00363","title":"MM-DETR: An Efficient Multimodal Detection Transformer with Mamba-Driven Dual-Granularity Fusion and Frequency-Aware Modality Adapters","created":"2025-11-29","cited_by_count":0,"area":"ssm"},{"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":"2601.02837","title":"Breaking Self-Attention Failure: Rethinking Query Initialization for Infrared Small Target Detection","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2602.00110","title":"Observing Health Outcomes Using Remote Sensing Imagery and Geo-Context Guided Visual Transformer","created":"2026-01-26","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":"2603.17492","title":"UAV-CB: A Complex-Background RGB-T Dataset and Local Frequency Bridge Network for UAV Detection","created":"2026-03-18","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":"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":"2608.04833","title":"RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detection","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.10680","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":"2608.20944","title":"SuppreSensing: Expert-Guided Feature Recalibration and Discrepancy Augmentation for Multimodal Object Detection","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":"2609.18124","title":"Aligned Consensus Teaching for Label-Efficient Oriented Object Detection in Weakly-Aligned Visible-Infrared Imagery","created":"2026-09-16","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},{"id":"2610.05074","title":"ReDiffNet: Differential RGB-Infrared Learning for Low-Light UAV Oriented Vehicle Detection","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}