6 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…
ATLASFusion: Aggregation Tracking with Location-Aware Sparse Fusion for Robust Spatio-Temporal Multi-View Pedestrian Tracking
Keisuke Toida, Taigo Sakai, Takeshi Nakamura +2
For multimedia spatial intelligence through time, multi-view multi-object tracking (MVMOT) suffers from persistent challenges in maintaining consistent object identities across dif…
Growing Deep Neural Network Considering with Similarity between Neurons
Taigo Sakai, Kazuhiro Hotta
Deep learning has excelled in image recognition tasks through neural networks inspired by the human brain. However, the necessity for large models to improve prediction accuracy in…