{"total":15,"rows":[{"id":"2402.02968","title":"Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives","created":"2024-02-05","cited_by_count":23,"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":"2411.18025","title":"Pixel-aligned RGB-NIR Stereo Imaging and Dataset for Robot Vision","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2504.16127","title":"MonoTher-Depth: Enhancing Thermal Depth Estimation via Confidence-Aware Distillation","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2412.16654","title":"IV-tuning: Parameter-Efficient Transfer Learning for Infrared-Visible Tasks","created":"2024-12-21","cited_by_count":1,"area":null},{"id":"2409.00973","title":"IVGF: The Fusion-Guided Infrared and Visible General Framework","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2410.00900","title":"OSSA: Unsupervised One-Shot Style Adaptation","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2505.12715","title":"VLC Fusion: Vision-Language Conditioned Sensor Fusion for Robust Object Detection","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2602.23559","title":"No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.02258","title":"SpectraDINO: Modality-Conditioned Adaptation of RGB Vision Foundation Models Across Infrared Bands","created":"2026-05-04","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":"2607.01871","title":"Descriptor: LYNRED Mobility Dataset Multimodal Detection Subset (LYNRED-MDS)","created":"2026-07-02","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":"2607.08076","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":"2608.25367","title":"RSFusionDet: Underwater RGB-Sonar Multimodal Object Detection","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}