4 papers · 1 filter
CAT-Free: Multi-View Pedestrian Localization without Calibration, Annotations, or Target-Scene Training via Adaptive Geometric Filtering
Taigo Sakai, Hiroki Kouno, Naoki Kato +1
Multi-camera pedestrian localization is useful for wide-area monitoring in public and commercial spaces. However, deploying these systems often requires considerable setup for each…
GRACE: Geometry- and Ray-Aware Camera-Efficient Multi-View Pedestrian Tracking
Taigo Sakai, Kazuhiro Hotta, Hiroki Kouno +1
Reducing the number of cameras reduces the deployment cost but removes views that correct BEV responses stretched away from true pedestrian positions by projection and short score…
NeuroGuard: Neural Gradient Update Aware of Representation Damage
Taigo Sakai, Kazuhito Hotta
Long-tailed class-incremental learning (LT-CIL) must learn new classes from imbalanced streams while retaining old classes. Existing methods mainly change replay, classifiers, or l…
Dynamic Distillation and Gradient Consistency for Robust Long-Tailed Incremental Learning
Taigo Sakai, Kazuhiro Hotta
The task of Long-tailed Class Incremental Learning (LT-CIL) addresses the sequential learning of new classes from datasets with imbalanced class distributions. This scenario intens…