Tal Barami

Identifying ASD According to Children's Body Movements

Tal Barami, Liora Manelis-Baram, Shalom Elkayam, Omri Azencot, Ilan Dinstein

Autistic children exhibit distinct motor patterns that may enable objective, scalable identification through automated analysis of body movements. We present a deep learning pipeline trained on 580 hours of multi-camera ADOS-2 recordings from 300 children (210 ASD, 90 typically developing). We fine-tuned the PoseC3D action recognition model to classify skeletal movements in 10-second segments and aggregated evidence across segments and cameras to classify individual children. The classifier achieved a mean assessment-level accuracy of 89.0% ± 1.9% with an AUC of 0.94 ± 0.01 and balanced sensitivity and specificity. Integrating data across cameras yielded a 9.4 percentage-point improvement over single-camera classification, demonstrating the value of multiple viewpoints. Temporal and spatial reorganization of skeletal positions decreased accuracy, confirming reliance on coherent spatio-temporal movement patterns. These results demonstrate that computer vision analysis of body movements can reliably identify many autistic children.

Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations

NeurIPS 2025 · 2025

Tal Barami, Nimrod Berman, Ilan Naiman, Amos Haviv Hason, Rotem Ezra, Omri Azencot

Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While real-world data involves multiple interacting semantic factors over time, prior work has mostly focused on simpler two-factor static and dynamic settings, primarily because such settings make data collection easier, thereby overlooking the inherently multi-factor nature of real-world data. We introduce the first standardized benchmark for evaluating multi-factor sequential disentanglement across six diverse datasets spanning video, audio, and time series. Our benchmark includes modular tools for dataset integration, model development, and evaluation metrics tailored to multi-factor analysis. We additionally propose a post-hoc Latent Exploration Stage to automatically align latent dimensions with semantic factors, and introduce a Koopman-inspired model that achieves state-of-the-art results. Moreover, we show that Vision-Language Models can automate dataset annotation and serve as zero-shot disentanglement evaluators, removing the need for manual labels and human intervention. Together, these contributions provide a robust and scalable foundation for advancing multi-factor sequential disentanglement. Our code is available on GitHub, and the datasets and trained models are available on Hugging Face.

Comparing three algorithms of automated facial expression analysis in autistic children: different sensitivities but consistent proportions

Molecular Autism 16(1), 50 · 2025

Liora Manelis, Tal Barami, Michal Ilan, Gal Meiri, Idan Menashe, Elizabeth Soskin, Carmel Sofer, Ilan Dinstein

We analyzed over 5 million video frames from 100 children (72 autistic, 28 controls; ages 2–7) recorded during ADOS-2 assessments. Facial expressions were quantified using three leading analysis tools (iMotions, FaceReader, Py-Feat), enabling objective comparisons across algorithms and groups. Despite substantial variability between tools, all three consistently showed no group differences in the quantity of facial expressions, suggesting that atypical expression use in autism relates more to quality, timing, and social context than to overall frequency.

Automated Analysis of Stereotypical Movements in Videos of Children With Autism Spectrum Disorder

JAMA Network Open · 2024

Tal Barami, Liora Manelis-Baram, Hadas Kaiser, Michal Ilan, Aviv Slobodkin, Ofri Hadashi, Dor Hadad, Omri Azencot, Andrei Sharf, Ilan Dinstein

We developed ASDMotion, the first large-scale open-source tool for detecting and quantifying stereotypical motor movements (SMMs) in children with autism. Trained on over 200 clinical assessments with expert annotations, ASDMotion combines deep learning with pose-based analysis to identify repetitive behaviors such as hand flapping and body rocking. The system achieves over 92% recall and strong alignment with expert ratings, enabling scalable and objective measurement of a core symptom of autism. Beyond its immediate clinical utility, ASDMotion provides a rich dataset and benchmark for advancing automated behavior analysis in naturalistic settings, opening the door to more reliable diagnostics, treatment monitoring, and research on developmental disorders.

Neural Approaches for 3D Pose Estimation from 3D Data

3DBODY.TECH · 2023

Gali Hod, Tal Barami, Michael Kolomenkin

We present two novel, open-source methods for human pose estimation directly from 3D point clouds and meshes, enabling accurate reconstruction of body joints for use in creative, clinical, and interactive applications. Unlike classical approaches, our methods are fully differentiable and designed to integrate seamlessly into modern deep learning pipelines. One approach uses body-part segmentation for skeleton construction; the other directly estimates joint positions using a PointNet++-based neural network.

Sensperience: A Virtual Reality Journey Through Altered Perception

Tal Barami, Liza Fridman, Carmel Lederer, Boaz Krysler

Sensperience is an immersive virtual reality application designed to let users explore and experience a wide range of altered sensory realities. The system combines a VR headset with a Geomagic haptic device, creating a fully interactive, multi-sensory environment that can be entirely controlled and customized by the developer. Users are guided through a series of simulated scenes, each engineered to manipulate and challenge specific human senses — including complete darkness, underwater immersion, vertigo, zero gravity, and interaction with varied textures. The result is a holistic simulation platform providing both visual and tactile feedback, with applications in education, therapy, training, and entertainment.

Playtika

Mentor Graphics

Computer Science & Psychology, Postdoc

Ben-Gurion University of the Negev

Advisor: Prof. Ilan Dinstein

2026 — Present

Computer Science, Ph.D.

Ben-Gurion University of the Negev

Advisors: Prof. Ilan Dinstein, Dr. Omri Azencot

2021 — 2026

Computer Science, M.Sc.

Ben-Gurion University of the Negev

Advisors: Prof. Ilan Dinstein, Prof. Andrei Sharf

2018 — 2021

Software Engineering, B.E.

Ben-Gurion University of the Negev

2014 — 2018