AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Attribute-Enhanced Face Recognition With Neural Tensor Fusion Networks

Guosheng Hu, Yang Hua, Yang Yuan, Zhihong Zhang, Zheng Lu, Sankha S. Mukherjee, Timothy M. Hospedales, Neil M. Robertson, Yongxin Yang

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 86 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fuse attribute features (AttNet) with GTNNLeanFace · Multi-PIE pose -90 degrecognition rate (%): 72.0 -> 78.3Improved
fuse attribute features (AttNet) with GTNNLBP · Multi-PIE pose -90 degrecognition rate (%): 1.3 -> 16.3Improved
fuse attribute features (AttNet) with GTNNLeanFace · Multi-PIE pose +90 degrecognition rate (%): 61.0 -> 68.0Improved
fuse attribute features (AttNet) with GTNNLBP · Multi-PIE illuminationrecognition rate (%): 57.5 -> 80.3Improved
fuse attribute features (AttNet) with GTNNLBP · Multi-PIE expressionrecognition rate (%): 71.7 -> 77.5Improved
fuse attribute features (AttNet) with GTNNLeanFace · Multi-PIE illuminationrecognition rate (%): 100 -> 100No clear effect
fuse attribute features (AttNet) with GTNNLeanFace · CASIA NIR-VIS 2.0accuracy (%): 97.27 -> 99.94Improved
fuse attribute features (AttNet) with GTNNLeanFace · LFWaccuracy (%): 99.57 -> 99.65Improved
use GTNN instead of LDA fusion (ablation)LeanFace + AttNet · CASIA NIR-VIS 2.0accuracy (%): 98.33 -> 99.94Improved
use feature concatenation instead of no fusion (ablation)LeanFace + AttNet · CASIA NIR-VIS 2.0accuracy (%): 97.27 -> 97.27No clear effect
use score fusion (ablation)LeanFace + AttNet · CASIA NIR-VIS 2.0accuracy (%): 97.27 -> 64.24Hurt
use CCA fusion (ablation)LeanFace + AttNet · LFWaccuracy (%): 99.57 -> 99.23Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy