An attention-aware transformer aggregates frame-level periocular features from video to outperform naive pooling on the COX dataset with 99.8% TPR at 0.1 FAR.
To train and evaluate our aggregation module, we use the COX Face [12] database, which contains 1k subjects and 3k videos
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Attention-Aware Transformer-Based Aggregation Network for Video Periocular Recognition
An attention-aware transformer aggregates frame-level periocular features from video to outperform naive pooling on the COX dataset with 99.8% TPR at 0.1 FAR.