MI-DETR: A Strong Baseline for Moving Infrared Small Target Detection with Motion Integration

arXiv:2603.05071 · cs.CV · Submitted 2026-03-05 · Read on arXiv

cs.CV

Submitted: 2026-03-05

Updated: 2026-09-16

Code: https://github.com/nliu-25/MI-DETR

Terminology

• Benchmark — 12× in this paper · explained in 2 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Aggregation — 5× in this paper · explained in 1 episode
• Accuracy — 4× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Optical Flow — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Parvocellular-Magnocellular Interconnection — 1× in this paper
• Recurrent Interpretable Motion Cue Aggregation — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Steering — 1× in this paper · explained in 2 episodes
• University of Chinese Academy of Sciences — 1× in this paper

Sources

• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• Decoupled Weight Decay Regularization

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models