AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis

Andy Zhou, Samuel Li, Pranav Sriram, Xiang Li, Jiahua Dong, Ansh Sharma, Yuanyi Zhong, Shirui Luo, Maria Jaromin, Volodymyr Kindratenko, Joerg Heintz, Christopher Zallek and 1 more

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal and affective interaction modeling

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
use spatial-temporal region attention with hierarchy loss instead of VGGFace linear probingResNet50 facial classifier · YouTubePD multiclassAUROC: 0.68 -> 0.74Improved
same, binary classificationResNet50 facial classifier · YouTubePD binaryAUROC: 0.86 -> 0.92Improved
same, multiclass top-1 accuracyResNet50 facial classifier · YouTubePD multiclassTop-1 accuracy: 78.20 -> 77.03Hurt
add logit-fusion with landmark and audio modalities to facial videofacial expression model · YouTubePD multiclassF1: 0.23 -> 0.28Improved
use Kinetics-pretrained action recognition backbones instead of VGGFace (ablation)linear-probed video models · YouTubePD multiclassaccuracy: 78.20 -> 45.64Hurt
use AffectNet-8 pretrained backbone instead of VGGFace (ablation)ResNet50 linear probing · YouTubePD binaryF1: 0.56 -> 0.45Hurt
use only temporal attention (no spatial) (ablation)proposed model · YouTubePD binaryTop-1 accuracy: 88.00 -> 77.14Hurt
use only spatial attention (no temporal) (ablation)proposed model · YouTubePD binaryTop-1 accuracy: 88.00 -> 82.86Hurt
fuse modalities by frame concatenation instead of frame voting (ablation)multimodal model · YouTubePD multiclassF1: 0.28 -> 0.21Hurt
replace MAE audio features with wav2vec 2.0 (ablation)audio modality · YouTubePD multiclassF1: 0.16 -> 0.14No clear effect
replace MAE audio features with MFCC (ablation)audio modality · YouTubePD multiclassF1: 0.16 -> 0.11Hurt
leave-one-subject-out split instead of default splitproposed vs VGGFace · YouTubePD multiclassAUROC: 0.66 -> 0.71Improved

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