{"total":76,"rows":[{"id":"2111.00273","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","created":"2021-10-30","cited_by_count":86,"area":null},{"id":"2308.07504","title":"ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection","created":"2023-08-15","cited_by_count":76,"area":null},{"id":"2104.02904","title":"Multimodal Object Detection via Probabilistic Ensembling","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2501.10761","title":"Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption","created":"2025-01-18","cited_by_count":46,"area":null},{"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":"2204.09848","title":"Weakly Aligned Feature Fusion for Multimodal Object Detection","created":"2022-04-21","cited_by_count":26,"area":null},{"id":"2205.09383","title":"Emergent Visual Sensors for Autonomous Vehicles","created":"2022-05-19","cited_by_count":19,"area":null},{"id":"2305.16580","title":"TFDet: Target-Aware Fusion for RGB-T Pedestrian Detection","created":"2023-05-26","cited_by_count":18,"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":"2310.19372","title":"RGB-X Object Detection via Scene-Specific Fusion Modules","created":"2023-10-30","cited_by_count":15,"area":null},{"id":"2302.00290","title":"MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization","created":"2023-02-01","cited_by_count":14,"area":null},{"id":"2509.24878","title":"ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation","created":"2025-09-29","cited_by_count":14,"area":null},{"id":"2112.02277","title":"BAANet: Learning Bi-directional Adaptive Attention Gates for Multispectral Pedestrian Detection","created":"2021-12-04","cited_by_count":13,"area":null},{"id":"2403.01300","title":"Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection","created":"2024-03-02","cited_by_count":13,"area":null},{"id":"2407.10125","title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","created":"2024-07-14","cited_by_count":10,"area":null},{"id":"2403.09359","title":"D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection","created":"2024-03-14","cited_by_count":9,"area":null},{"id":"2405.16038","title":"Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection","created":"2024-05-25","cited_by_count":9,"area":null},{"id":"2503.17122","title":"R-LiViT: A LiDAR-Visual-Thermal Dataset Enabling Vulnerable Road User Focused Roadside Perception","created":"2025-03-21","cited_by_count":9,"area":null},{"id":"2310.04662","title":"HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information","created":"2023-10-07","cited_by_count":8,"area":null},{"id":"2401.07801","title":"Pedestrian Detection in Low-Light Conditions: A Comprehensive Survey","created":"2024-01-15","cited_by_count":8,"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":"2412.00622","title":"Visual Modality Prompt for Adapting Vision-Language Object Detectors","created":"2024-12-01","cited_by_count":7,"area":null},{"id":"2307.09027","title":"Online Self-Supervised Thermal Water Segmentation for Aerial Vehicles","created":"2023-07-18","cited_by_count":6,"area":null},{"id":"2408.01037","title":"MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection","created":"2024-08-02","cited_by_count":6,"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":"2404.18849","title":"MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection","created":"2024-04-29","cited_by_count":5,"area":null},{"id":"2405.19202","title":"Vulnerable Road User Detection and Safety Enhancement: A Comprehensive Survey","created":"2024-05-29","cited_by_count":5,"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":"2505.22154","title":"Learning A Robust RGB-Thermal Detector for Extreme Modality Imbalance","created":"2025-05-28","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":"2206.03943","title":"Robust Environment Perception for Automated Driving: A Unified Learning Pipeline for Visual-Infrared Object Detection","created":"2022-06-08","cited_by_count":4,"area":null},{"id":"2404.01492","title":"Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2410.11358","title":"SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detection","created":"2024-10-15","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":"2504.15728","title":"SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems","created":"2025-04-22","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":"2602.19430","title":"TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation","created":"2026-02-23","cited_by_count":4,"area":null},{"id":"2302.08670","title":"Cascaded information enhancement and cross-modal attention feature fusion for multispectral pedestrian detection","created":"2023-02-17","cited_by_count":3,"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":"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":"2106.13603","title":"Partially fake it till you make it: mixing real and fake thermal images for improved object detection","created":"2021-06-25","cited_by_count":2,"area":null},{"id":"2307.06724","title":"Multimodal Object Detection in Remote Sensing","created":"2023-07-13","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":"2507.18925","title":"WiSE-OD: Benchmarking Robustness in Infrared Object Detection","created":"2025-07-25","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":"2511.01435","title":"Contrast-Guided Cross-Modal Distillation for Thermal Object Detection","created":"2025-11-03","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":"2605.15906","title":"A Causally Grounded Taxonomy for Image Degradation Robustness Evaluation","created":"2026-05-15","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":"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":"2505.15137","title":"Multispectral Detection Transformer with Infrared-Centric Feature Fusion","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2506.00365","title":"Feature Fusion and Knowledge-Distilled Multi-Modal Multi-Target Detection","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2506.23353","title":"Layer Decomposition and Morphological Reconstruction for Task-Oriented Infrared Image Enhancement","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2508.02927","title":"Infrared Object Detection with Ultra Small ConvNets: Is ImageNet Pretraining Still Useful?","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2510.03314","title":"From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety","created":"2025-09-30","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":"2601.08458","title":"Modality-Decoupled RGB-Thermal Object Detector via Query Fusion","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.09228","title":"Disentangle Object and Non-object Infrared Features via Language Guidance","created":"2026-01-14","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":"2604.16630","title":"Tri-Modal Fusion Transformers for UAV-based Object Detection","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.20963","title":"Towards UAV Detection in the Real World: A New Multispectral Dataset UAVNet-MS and a New Method","created":"2026-05-20","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":"2607.01871","title":"Descriptor: LYNRED Mobility Dataset Multimodal Detection Subset (LYNRED-MDS)","created":"2026-07-02","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":"2608.10724","title":"InterPruner: Interactive Structured Pruning via Taylor-Implicit Criterion and Language-Prior Modulator for Multimodal Object Detection","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.11595","title":"ProtoHGF-Net: Prototype HyperGraph Fusion with Intra-modal Calibration for RGBT 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":"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}],"next_cursor":null}