{"total":152,"rows":[{"id":"2308.02097","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","created":"2023-08-04","cited_by_count":129,"area":null},{"id":"2404.09146","title":"Fusion-Mamba for Cross-modality Object Detection","created":"2024-04-14","cited_by_count":67,"area":"ssm"},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"area":null},{"id":"2204.10704","title":"SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite","created":"2022-04-22","cited_by_count":64,"area":null},{"id":"2306.16175","title":"$\\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection","created":"2023-06-28","cited_by_count":58,"area":null},{"id":"2302.01392","title":"Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion","created":"2023-02-02","cited_by_count":54,"area":"moe"},{"id":"2209.13801","title":"Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection","created":"2022-09-28","cited_by_count":50,"area":null},{"id":"2210.04936","title":"EarthNets: Empowering AI in Earth Observation","created":"2022-10-10","cited_by_count":40,"area":null},{"id":"2204.03245","title":"HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection","created":"2022-04-07","cited_by_count":34,"area":null},{"id":"2308.03256","title":"Learning a Graph Neural Network with Cross Modality Interaction for Image Fusion","created":"2023-08-07","cited_by_count":28,"area":null},{"id":"2406.14482","title":"Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines","created":"2024-06-20","cited_by_count":27,"area":null},{"id":"2507.22412","title":"UAVScenes: A Multi-Modal Dataset for UAVs","created":"2025-07-30","cited_by_count":27,"area":null},{"id":"2308.03979","title":"PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation","created":"2023-08-08","cited_by_count":26,"area":null},{"id":"2412.20665","title":"SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection","created":"2024-12-30","cited_by_count":22,"area":null},{"id":"2503.01187","title":"DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution","created":"2025-03-03","cited_by_count":22,"area":"diffusion"},{"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":"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":"2312.04548","title":"Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?","created":"2023-12-07","cited_by_count":18,"area":null},{"id":"2503.19012","title":"DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding","created":"2025-03-24","cited_by_count":16,"area":"diffusion"},{"id":"2310.19372","title":"RGB-X Object Detection via Scene-Specific Fusion Modules","created":"2023-10-30","cited_by_count":15,"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":"2507.18173","title":"WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection","created":"2025-07-24","cited_by_count":14,"area":"ssm"},{"id":"2408.11958","title":"CARLA Drone: Monocular 3D Object Detection from a Different Perspective","created":"2024-08-21","cited_by_count":12,"area":null},{"id":"2405.07595","title":"Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection","created":"2024-05-13","cited_by_count":11,"area":null},{"id":"2504.12795","title":"EarthGPT-X: A Spatial MLLM for Multi-level Multi-Source Remote Sensing Imagery Understanding with Visual Prompting","created":"2025-04-17","cited_by_count":11,"area":"lr"},{"id":"2406.04647","title":"UVCPNet: A UAV-Vehicle Collaborative Perception Network for 3D Object Detection","created":"2024-06-07","cited_by_count":7,"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":"2502.01467","title":"Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysis","created":"2025-02-03","cited_by_count":7,"area":null},{"id":"2211.16785","title":"SafeSpace MFNet: Precise and Efficient MultiFeature Drone Detection Network","created":"2022-11-30","cited_by_count":6,"area":null},{"id":"2410.14944","title":"Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding","created":"2024-10-19","cited_by_count":6,"area":null},{"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":"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":"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":"2511.22396","title":"Asking like Socrates: Socrates helps VLMs understand remote sensing images","created":"2025-11-27","cited_by_count":6,"area":"lr"},{"id":"2512.09663","title":"IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images with Generative Visual Prompting","created":"2025-12-10","cited_by_count":6,"area":"mllm"},{"id":"2312.08192","title":"PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2401.11582","title":"Thermal Image Calibration and Correction using Unpaired Cycle-Consistent Adversarial Networks","created":"2024-01-21","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":"2409.10080","title":"DAE-Fuse: An Adaptive Discriminative Autoencoder for Multi-Modality Image Fusion","created":"2024-09-16","cited_by_count":5,"area":null},{"id":"2504.20032","title":"More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV","created":"2025-04-28","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":"2603.14336","title":"UAVBench and UAVIT-1M: Benchmarking and Enhancing MLLMs for Low-Altitude UAV Vision-Language Understanding","created":"2026-03-15","cited_by_count":5,"area":"mllm"},{"id":"2305.10882","title":"StawGAN: Structural-Aware Generative Adversarial Networks for Infrared Image Translation","created":"2023-05-18","cited_by_count":4,"area":null},{"id":"2406.06230","title":"UEMM-Air: Make Unmanned Aerial Vehicles Perform More Multi-modal Tasks","created":"2024-06-10","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":"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":"2211.07137","title":"DroneNet: Crowd Density Estimation using Self-ONNs for Drones","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2310.13951","title":"Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMS","created":"2023-10-21","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":"2407.18137","title":"XS-VID: A Large-Scale Benchmark for Small Object Detection and Tracking in Videos","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2412.11582","title":"Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2502.02257","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","created":"2025-02-04","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":"2509.09427","title":"FS-Diff: Semantic guidance and clarity-aware simultaneous multimodal image fusion and super-resolution","created":"2025-09-11","cited_by_count":3,"area":null},{"id":"2401.02606","title":"Exploiting Polarized Material Cues for Robust Car Detection","created":"2024-01-05","cited_by_count":2,"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":"2410.20466","title":"Guidance Disentanglement Network for Optics-Guided Thermal UAV Image Super-Resolution","created":"2024-10-27","cited_by_count":2,"area":null},{"id":"2411.04348","title":"UEVAVD: A Dataset for Developing UAV's Eye View Active Object Detection","created":"2024-11-07","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":"2309.01099","title":"Enhancing Infrared Small Target Detection Robustness with Bi-Level Adversarial Framework","created":"2023-09-03","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":"2409.07024","title":"SCLNet: A Scale-Robust Complementary Learning Network for Object Detection in UAV Images","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2410.13616","title":"Spatiotemporal Object Detection for Improved Aerial Vehicle Detection in Traffic Monitoring","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2411.04697","title":"Dynamic Brightness Adaptation for Robust Multi-modal Image Fusion","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2412.09954","title":"$\\textrm{A}^{\\textrm{2}}$RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2412.10861","title":"Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos","created":"2024-12-14","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":"2503.07950","title":"Decoupled Cross-Modal Alignment Network for Text-RGBT Person Retrieval and A High-Quality Benchmark","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2505.06920","title":"Bi-directional Self-Registration for Misaligned Infrared-Visible Image Fusion","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2506.11175","title":"Teaching in adverse scenes: a statistically feedback-driven threshold and mask adjustment teacher-student framework for object detection in UAV images under adverse scenes","created":"2025-06-12","cited_by_count":1,"area":"distill"},{"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":"2507.20764","title":"ATR-UMMIM: A Benchmark Dataset for UAV-Based Multimodal Image Registration under Complex Imaging Conditions","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2507.23508","title":"Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion","created":"2025-07-31","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":"2509.00497","title":"FLUID: A Fine-Grained Lightweight Urban Signalized-Intersection Dataset of Dense Conflict Trajectories","created":"2025-08-30","cited_by_count":1,"area":null},{"id":"2509.06011","title":"Light-Weight Cross-Modal Enhancement Method with Benchmark Construction for UAV-based Open-Vocabulary Object Detection","created":"2025-09-07","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":"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":"2605.23144","title":"SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.07708","title":"Cross-View Urban Traffic Dataset: Drone-Supervised Ground Truth for Monocular Bird's-Eye View Localization","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.17020","title":"FusionRS: A Large-Scale RGB-Infrared-Style Remote Sensing Dataset for Cross-Modal Vision-Language Learning","created":"2026-06-15","cited_by_count":1,"area":"mllm"},{"id":"2607.09078","title":"Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Method","created":"2026-07-10","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":"2609.01742","title":"Evidential Deep Learning for Multi-Modal Anti-UAV Detection","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2204.04653","title":"Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches","created":"2022-04-10","cited_by_count":0,"area":null},{"id":"2209.02200","title":"Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images","created":"2022-09-06","cited_by_count":0,"area":null},{"id":"2405.03218","title":"Elevator, Escalator, or Neither? Classifying Conveyor State Using Smartphone under Arbitrary Pedestrian Behavior","created":"2024-05-06","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":"2410.06811","title":"Rethinking the Evaluation of Visible and Infrared Image Fusion","created":"2024-10-09","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":"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":"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}],"next_cursor":"100"}