Weakly-Supervised Autism Severity Assessment in Long Videos

Autism Spectrum Disorder (ASD) is a diverse collection of neurobiological conditions marked by challenges in social communication and reciprocal interactions, as well as repetitive and stereotypical behaviors. Atypical behavior patterns in a long, untrimmed video can serve as biomarkers for children with ASD. In this paper, we propose a video-based weakly-supervised method that takes spatio-temporal features of long videos to learn typical and atypical behaviors for autism detection. On top of that, we propose a shallow TCN-MLP network, which is designed to further categorize the severity score. We evaluate our method on actual evaluation videos of children with autism collected and annotated (for severity score) by clinical professionals. Experimental results demonstrate the effectiveness of behaviors biomarkers that could help clinicians in autism spectrum analysis.

• Publication year

  2024

• Venue

  International Conference on Content-Based Multimedia Indexing

• Publication date

  2024-07-12

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1109/CBMI62980.2024.10859216arXiv 2407.09159
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• OE-CTST: Outlier-Embedded Cross Temporal Scale Transformer for Weakly-supervised Video Anomaly Detection

  2024influential reference
• VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

  2023cited by this paper
• P-Age: Pexels Dataset for Robust Spatio-Temporal Apparent Age Classification

  2023cited by this paper
• Track Anything: Segment Anything Meets Videos

  2023cited by this paper
• DINOv2: Learning Robust Visual Features without Supervision

  2023cited by this paper
• Appearance-Based Gaze Estimation for ASD Diagnosis

  2022cited by this paper
• CLIP-TSA: Clip-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection

  2022cited by this paper
• Video-based Behavior Understanding of Children for Objective Diagnosis of Autism

  2022cited by this paper
• Learning Transferable Visual Models From Natural Language Supervision

  2021cited by this paper
• Deep neural networks for rank-consistent ordinal regression based on conditional probabilities

  2021cited by this paper
• Atypical gaze patterns to facial feature areas in autism spectrum disorders reveal age and culture effects: A meta‐analysis of eye‐tracking studies

  2021cited by this paper
• Gait and Full Body Movement Dataset of Autistic Children Classified by Rough Set Classifier

  2021cited by this paper
• Vision-assisted recognition of stereotype behaviors for early diagnosis of Autism Spectrum Disorders

  2021cited by this paper
• PDAN: Pyramid Dilated Attention Network for Action Detection

  2021cited by this paper
• Autism prevalence increases from 1 in 60 to 1 in 54: CDC

  2020cited by this paper
• Classifying ASD children with LSTM based on raw videos

  2020cited by this paper
• Increased facial asymmetry in autism spectrum conditions is associated with symptom presentation

  2019cited by this paper
• MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation

  2019cited by this paper
• Attention-Based Autism Spectrum Disorder Screening With Privileged Modality

  2019cited by this paper
• Detecting Developmental Delay and Autism Through Machine Learning Models Using Home Videos of Bangladeshi Children: Development and Validation Study

  2019cited by this paper
• Video-Based Early ASD Detection via Temporal Pyramid Networks

  2019cited by this paper
• Real-World Anomaly Detection in Surveillance Videos

  2018cited by this paper
• Video Gesture Analysis for Autism Spectrum Disorder Detection

  2018cited by this paper
• 3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children with Autism

  2018cited by this paper
• The Kinetics Human Action Video Dataset

  2017cited by this paper
• Toward the Autism Motor Signature: Gesture patterns during smart tablet gameplay identify children with autism

  2016cited by this paper
• Decoding Children's Social Behavior

  2013cited by this paper
• Self-Stimulatory Behaviours in the Wild for Autism Diagnosis

  2013cited by this paper
• A computer vision approach for the assessment of autism-related behavioral markers

  2012cited by this paper
• Looking at movies and cartoons: eye-tracking evidence from Williams syndrome and autism.

  2009cited by this paper
• Autism genetics: strategies, challenges, and opportunities

  2008cited by this paper
• MASKING

  2008cited by this paper

• No citing papers are available for this paper.