AI Paper Atlas

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

Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States

Guosheng Hu, Li Liu, Yang Yuan, Zehao Yu, Yang Hua, Zhihong Zhang, Fumin Shen, Ling Shao, Timothy Hospedales, Neil Robertson, Yongxin Yang

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware facial expression recognition · 51 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
add trace-norm soft sharing (LAF) with landmark detection task instead of single-task trainingResNet-34 · LSEMSW mental state recognitionaccuracy (%): 28.39 -> 33.43Improved
add adversarial domain alignment (ADA) to LAF soft sharing (ablation)ResNet-34+LAF · LSEMSW mental state recognitionaccuracy (%): 33.43 -> 36.72Improved
add adversarial domain alignment (ADA) to LAF soft sharing (ablation)ResNet-34+LAF · 300-W full setnormalised mean error (%): 4.67 -> 4.64Improved
use Tucker or TT trace norm instead of LAF (ablation)ResNet-34 soft sharing · LSEMSW mental state recognitionaccuracy (%): 33.43 vs 33.39 vs 33.41No clear effect
replace hard sharing (first 6 layers shared) with automatic soft sharing LAFResNet-34 MTL · LSEMSW mental state recognitionaccuracy (%): 30.07 -> 33.43Improved
share more layers in hard sharing (6 to 32 layers) (ablation)ResNet-34 hard sharing · LSEMSW mental state recognitionaccuracy (%): 30.07 -> 24.69Hurt
replace cross stitch MTL with trace-norm LAF sharingResNet-34 MTL · LSEMSW mental state recognitionaccuracy (%): 30.96 -> 33.43Improved
add ADA to hard sharing RN(6) (ablation)ResNet-34 hard sharing · LSEMSW mental state recognitionaccuracy (%): 30.07 -> 33.97Improved
use l1 loss instead of l2 loss for landmark regression (ablation)RN+LAF+ADA · 300-W full setnormalised mean error (%): 4.76 -> 4.64Improved
fine-tune from LSEMSW pretraining instead of training from scratch (ablation)RN+LAF+ADA · Oulu-Casia NIR&Visaccuracy (%): 76.0 -> 87.1Improved
fine-tune from LSEMSW pretraining instead of training from scratch (ablation)RN+LAF+ADA · CK+accuracy (%): 86.3 -> 96.4Improved
add LAF and ADA to fine-tuned ResNet (ablation)RN (FT) · Oulu-Casia NIR&Visaccuracy (%): 82.9 -> 87.1Improved

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