{"total":197,"rows":[{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2111.00273","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","created":"2021-10-30","cited_by_count":86,"area":null},{"id":"2403.16387","title":"Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion","created":"2024-03-25","cited_by_count":84,"area":null},{"id":"2204.11425","title":"BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix","created":"2022-04-25","cited_by_count":61,"area":null},{"id":"2403.12532","title":"UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All","created":"2024-03-19","cited_by_count":49,"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":"2404.11884","title":"Seeing Motion at Nighttime with an Event Camera","created":"2024-04-18","cited_by_count":34,"area":null},{"id":"2502.19854","title":"One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion","created":"2025-02-27","cited_by_count":32,"area":null},{"id":"2308.11804","title":"Adversarial Illusions in Multi-Modal Embeddings","created":"2023-08-22","cited_by_count":29,"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":"2307.07859","title":"Unified Adversarial Patch for Cross-modal Attacks in the Physical World","created":"2023-07-15","cited_by_count":27,"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":"2312.14209","title":"TextFusion: Unveiling the Power of Textual Semantics for Controllable Image Fusion","created":"2023-12-21","cited_by_count":26,"area":null},{"id":"2412.03240","title":"Task-driven Image Fusion with Learnable Fusion Loss","created":"2024-12-04","cited_by_count":25,"area":null},{"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":"2405.16108","title":"OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All","created":"2024-05-25","cited_by_count":20,"area":null},{"id":"2503.14963","title":"Continual Multimodal Contrastive Learning","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2205.09383","title":"Emergent Visual Sensors for Autonomous Vehicles","created":"2022-05-19","cited_by_count":19,"area":null},{"id":"2403.08997","title":"Caltech Aerial RGB-Thermal Dataset in the Wild","created":"2024-03-13","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":"2404.11016","title":"MaeFuse: Transferring Omni Features with Pretrained Masked Autoencoders for Infrared and Visible Image Fusion via Guided Training","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2405.12944","title":"AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection","created":"2024-05-21","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":"2402.02090","title":"All-weather Multi-Modality Image Fusion: Unified Framework and 100k Benchmark","created":"2024-02-03","cited_by_count":14,"area":null},{"id":"2407.09801","title":"IoT-LM: Large Multisensory Language Models for the Internet of Things","created":"2024-07-13","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":"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":"2408.00969","title":"Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach","created":"2024-08-02","cited_by_count":13,"area":null},{"id":"2403.14053","title":"Leveraging Thermal Modality to Enhance Reconstruction in Low-Light Conditions","created":"2024-03-21","cited_by_count":12,"area":null},{"id":"2305.05970","title":"FusionBooster: A Unified Image Fusion Boosting Paradigm","created":"2023-05-10","cited_by_count":11,"area":null},{"id":"2402.01212","title":"TSJNet: A Multi-modality Target and Semantic Awareness Joint-driven Image Fusion Network","created":"2024-02-02","cited_by_count":10,"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":"2408.15641","title":"MMDRFuse: Distilled Mini-Model with Dynamic Refresh for Multi-Modality Image Fusion","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2410.09831","title":"LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond","created":"2024-10-13","cited_by_count":10,"area":null},{"id":"2411.09387","title":"Instruction-Driven Fusion of Infrared-Visible Images: Tailoring for Diverse Downstream Tasks","created":"2024-11-14","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":"2503.23356","title":"ControlFusion: A Controllable Image Fusion Framework with Language-Vision Degradation Prompts","created":"2025-03-30","cited_by_count":9,"area":null},{"id":"2509.00346","title":"LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables","created":"2025-08-30","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":"2503.23359","title":"VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion","created":"2025-03-30","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":"2203.08581","title":"A Survey on Infrared Image and Video Sets","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2302.00912","title":"Advances and Challenges in Multimodal Remote Sensing Image Registration","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2404.07072","title":"Implicit Multi-Spectral Transformer: An Lightweight and Effective Visible to Infrared Image Translation Model","created":"2024-04-10","cited_by_count":6,"area":null},{"id":"2411.02840","title":"Test-Time Dynamic Image Fusion","created":"2024-11-05","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":"2504.10888","title":"CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors","created":"2025-04-15","cited_by_count":6,"area":null},{"id":"2505.24705","title":"RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement","created":"2025-05-30","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":"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":"2405.19202","title":"Vulnerable Road User Detection and Safety Enhancement: A Comprehensive Survey","created":"2024-05-29","cited_by_count":5,"area":null},{"id":"2501.02640","title":"Multispectral Pedestrian Detection with Sparsely Annotated Label","created":"2025-01-05","cited_by_count":5,"area":null},{"id":"2503.16185","title":"MapGlue: Multimodal Remote Sensing Image Matching","created":"2025-03-20","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":"2309.06118","title":"CHITNet: A Complementary to Harmonious Information Transfer Network for Infrared and Visible Image Fusion","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2309.14997","title":"IAIFNet: An Illumination-Aware Infrared and Visible Image Fusion Network","created":"2023-09-26","cited_by_count":4,"area":null},{"id":"2312.01789","title":"Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical world","created":"2023-12-04","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":"2406.05475","title":"HDRT: A Large-Scale Dataset for Infrared-Guided HDR Imaging","created":"2024-06-08","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":"2512.06400","title":"Perceptual Region-Driven Infrared-Visible Co-Fusion for Extreme Scene Enhancement","created":"2025-12-06","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":"2603.03871","title":"Bridging Human Evaluation to Infrared and Visible Image Fusion","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2409.12306","title":"Measuring Sound Symbolism in Audio-visual Models","created":"2024-09-18","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":"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":"2505.04526","title":"DFVO: Learning Darkness-free Visible and Infrared Image Disentanglement and Fusion All at Once","created":"2025-05-07","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":"2508.16881","title":"AWM-Fuse: Multi-Modality Image Fusion for Adverse Weather via Global and Local Text Perception","created":"2025-08-23","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":"2511.22404","title":"UAV-MM3D: A Large-Scale Synthetic Benchmark for 3D Perception of Unmanned Aerial Vehicles with Multi-Modal Data","created":"2025-11-27","cited_by_count":3,"area":null},{"id":"2310.09461","title":"MAC: ModAlity Calibration for Object Detection","created":"2023-10-14","cited_by_count":2,"area":null},{"id":"2310.16212","title":"ShadowSense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection from RGB-Thermal Drone Imagery","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2403.11751","title":"Relational Representation Learning Network for Cross-Spectral Image Patch Matching","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2408.03030","title":"Nighttime Pedestrian Detection Based on Fore-Background Contrast Learning","created":"2024-08-06","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":"2511.09829","title":"Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2603.07667","title":"FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2604.02896","title":"EvaNet: Towards More Efficient and Consistent Infrared and Visible Image Fusion Assessment","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2604.11043","title":"EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2305.12845","title":"Bright Channel Prior Attention for Multispectral Pedestrian Detection","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2305.17376","title":"DePF: A Novel Fusion Approach based on Decomposition Pooling for Infrared and Visible Images","created":"2023-05-27","cited_by_count":1,"area":null},{"id":"2307.06724","title":"Multimodal Object Detection in Remote Sensing","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2311.06217","title":"MultiIoT: Benchmarking Machine Learning for the Internet of Things","created":"2023-11-10","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":"2408.06868","title":"A Comprehensive Survey on Synthetic Infrared Image synthesis","created":"2024-08-13","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":"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":"2504.10871","title":"DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2506.03555","title":"WIFE-Fusion:Wavelet-aware Intra-inter Frequency Enhancement for Multi-model Image Fusion","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2507.06513","title":"What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies","created":"2025-07-09","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":"2510.11456","title":"Coupled Degradation Modeling and Fusion: A VLM-Guided Degradation-Coupled Network for Degradation-Aware Infrared and Visible Image Fusion","created":"2025-10-13","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}],"next_cursor":"100"}