FaceMoE introduces a MoE transformer with top-k routed specialized FFN experts for resolution-aware feature extraction in low-resolution face recognition, outperforming prior methods on eleven datasets.
arXiv preprint arXiv:2403.12960 (2024) 18 Narayan et al
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
A transformer-based model that jointly processes 2D silhouettes and 3D SMPL features outperforms prior single-modality methods on the BRIAR dataset for gait recognition while also estimating age, BMI, and gender.
FaVChat proposes hierarchical prompt-query guided visual features and Data-Efficient GRPO for efficient training, plus the FaVChat-170K dataset, claiming consistent outperformance over prior VLLMs on facial video tasks.
citing papers explorer
-
FaceMoE: Mixture of Experts for Low-Resolution Face Recognition
FaceMoE introduces a MoE transformer with top-k routed specialized FFN experts for resolution-aware feature extraction in low-resolution face recognition, outperforming prior methods on eleven datasets.
-
Combo-Gait: Unified Transformer Framework for Multi-Modal Gait Recognition and Attribute Analysis
A transformer-based model that jointly processes 2D silhouettes and 3D SMPL features outperforms prior single-modality methods on the BRIAR dataset for gait recognition while also estimating age, BMI, and gender.
-
FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO
FaVChat proposes hierarchical prompt-query guided visual features and Data-Efficient GRPO for efficient training, plus the FaVChat-170K dataset, claiming consistent outperformance over prior VLLMs on facial video tasks.