{"total":18,"rows":[{"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":"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":"2508.04682","title":"TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction","created":"2025-08-06","cited_by_count":9,"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":"2506.19769","title":"A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects","created":"2025-06-24","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":"2408.13980","title":"FusionSAM: Visual Multi-Modal Learning with Segment Anything","created":"2024-08-26","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":"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":"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":"2505.06665","title":"MultiTaskVIF: Segmentation-oriented visible and infrared image fusion via multi-task learning","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2507.20574","title":"LSFDNet: A Single-Stage Fusion and Detection Network for Ships Using SWIR and LWIR","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2509.12710","title":"RIS-FUSION: Rethinking Text-Driven Infrared and Visible Image Fusion from the Perspective of Referring Image Segmentation","created":"2025-09-16","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":"2509.22450","title":"SSVIF: Self-Supervised Segmentation-Oriented Visible and Infrared Image Fusion","created":"2025-09-26","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":"2608.11685","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":"2609.01092","title":"IT-TextFusion: Iterative Text-Image Interaction with Text-Guided Residual Refinement for Degradation-Aware Image Fusion","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}