Get Started
Home
Topics
Search
Library
Research questionHow can infrared-visible object detectors remain reliable when one sensor modality is missing?Infrared and visible sensors provide complementary cues, but their streams may be intermittent or absent, making fixed fusion unreliable. Their heterogeneous feature distributions also make semantic correspondence difficult when both streams are available.
AI
Computer Vision
Image & Video Processing
Machine Learning
Multimodal Models
Latest papersRecent research connected to this question, newest first.Residual Optimal Transport-Based Experts Collaboration Towards Modality-Aware Infrared-Visible Object DetectionThe source studies infrared-visible object detection with adaptive cross-modal or intra-modal expert pathways and residual optimal-transport feature alignment. It reports experiments under complete and missing-modality protocols, including arbitrary modality configurations.research paper · Sep 3, 2026
Related questions
How can existing camera–LiDAR BEV detectors stay reliable under domain shifts and sensor failures without retraining?How can RGB-D salient-object detection remain reliable when depth measurements are missing or corrupted?Can small targeted grayscale patches force chosen semantics in infrared vision-language models across tasks?How can vision-language models maintain visual recognition when modalities are missing and source training data is unavailable?