3 papers
cs.CV2026
Reading Decoder Trajectories: Training-Free Counterfactual Query-Trajectory Reliability for Small-Object Detection
Zhaoning Shi, Bo Ma
Small-object detection remains challenging because limited pixels cause information loss and suppress the scale knowledge encoded in pretrained detectors. Existing approaches mainl…
cs.CV2026
CODE: Cross-Modal Calibration and Dynamic Suppression for Open World Object Detection
Hao Xu, Zhaoning Shi, Hehe Jin +1
Open World Object Detection (OWOD) built on multimodal foundation models often suffers from semantic ambiguity caused by unidirectional text-to-vision matching, while rigid outlier…
cs.CV2026
Hippocampus-DETR: An Explicit Memory Object Detection Framework Based on Hippocampus Modeling
Zhaoning Shi, Bo Ma, Hao Xu +2
This paper addresses the lack of explicit memory mechanisms in current object detection models and proposes Hippocampus-DETR, a novel detection framework based on biological hippoc…