Face Quality‑Driven Feature Denoising and Fusion for iQIYI‑VID‑2019 Video Person Recognition

The seefun team leveraged face detection scores and quality metrics to denoise and weight‑fuse facial features during training and testing, using a three‑layer MLP with Swish activation and dropout, and achieved a 0.8983 mAP (fourth place) on the iQIYI‑VID‑2019 video person‑recognition challenge.

MLPface quality weightingfeature fusion

0 likes · 10 min read

Face Quality‑Driven Feature Denoising and Fusion for iQIYI‑VID‑2019 Video Person Recognition

iQIYI Technical Product Team

Jul 5, 2019 · Artificial Intelligence

Residual Dense Network with Feature Fusion for Multimodal Video Person Identification (iQIYI-VID-2019)

The authors introduce a feature‑fusion pipeline and a Residual Dense Net that leverages multi‑frame face embeddings to identify persons in iQIYI‑VID‑2019 videos, achieving 0.9035 mAP (second place) with only ≈0.5 GFLOPs and processing the full test set in minutes.

Multimodal Learningfeature fusioniQIYI-VID-2019

0 likes · 11 min read

Residual Dense Network with Feature Fusion for Multimodal Video Person Identification (iQIYI-VID-2019)