AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Deep Cybersickness Predictor Based on Brain Signal Analysis for Virtual Reality Contents

Jinwoo Kim, Woojae Kim, Heeseok Oh, Seongmin Lee, Sanghoon Lee

ICCV 2019 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 106 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 cognitive features (transferred from EEG) to the visual predictor (ablation)Visual-cognitive predictor · ETRI-VR video-only cybersickness predictionvalidation accuracy: 68.93 -> 90.48Improved
add cognitive features to the visual predictor (ablation)Visual-cognitive predictor · ETRI-VR video-only cybersickness predictiontest accuracy: 69.03 -> 89.16Improved
use the proposed visual-cognitive predictor instead of Kim et al. [13]Visual-cognitive predictor · ETRI-VR video-only cybersickness predictiontest accuracy: 65.83 -> 89.16Improved
use square kernels replaced by temporal and spectral kernels combinedEEG spectrogram CNN · ETRI-VR EEG spectrogram classificationtest accuracy: 56.89 -> 87.13Improved
add the spectral branch to the temporal-only network (ablation)EEG spectrogram CNN · ETRI-VR EEG spectrogram classificationtest accuracy: 80.57 -> 87.13Improved
add the temporal branch to the spectral-only network (ablation)EEG spectrogram CNN · ETRI-VR EEG spectrogram classificationtest accuracy: 83.74 -> 87.13Improved
lengthen temporal kernel from 1x7 to 1x28 (ablation)Temporal network · ETRI-VR EEG spectrogram classificationtest accuracy: 65.17 -> 80.57Improved
lengthen spectral kernel from 8x1 to 32x1 (ablation)Spectral network · ETRI-VR EEG spectrogram classificationtest accuracy: 83.74 -> 77.74Hurt
use P4 channel only instead of Fp1 (ablation)EEG spectrogram CNN · ETRI-VR EEG single-channel inputtest accuracy: 81.78 -> 86.16Improved
feed video-derived cognitive features instead of EEG representation to stage-1 classifierStage-1 classifier · ETRI-VR cognitive feature transfertest accuracy: 87.13 -> 86.35No clear effect
vary video sampling interval r (ablation)Visual-cognitive predictor · ETRI-VR video-only cybersickness predictionaccuracyNo clear effect

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