Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 18, 2026

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

Published on: July 14, 2023

Realistic benchmark RBD360 dataset for quality assessment of random user generated 360° videos.

Manav Arun Mehta¹, Pramit Mazumdar¹, Kalyan Chatterjee¹

¹Department of Computer Science & Engineering, Indian Institute of Information Technology Vadodara, Gandhinagar, India.

Scientific Reports

|May 16, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

HoST: integrating Heuristic knowledge with attention-based LSTM networks for Thunderstorm prediction.

Scientific reports·2026

Same author

BC-SwinNet: Swin transformer and CNN with multi-objective optimization for multi-class breast cancer detection using Histopathological images.

Scientific reports·2026

Same author

Explainable artificial-intelligence-based hyperspectral image analysis for leaf disease detection in intercropping system.

Frontiers in plant science·2026

Same author

Generative adversarial networks and hyperparameter-optimized XGBoost for enhanced heart disease prediction.

Scientific reports·2026

Same author

AI-powered detection of pumpkin leaf diseases using DualFusion-CBAM-stochastic for yield protection and precision agriculture.

Frontiers in plant science·2026

Same author

Multimodal attention-driven network with blockchain integrity for reliable kidney stone diagnosis.

Urolithiasis·2026

A new dataset, RBD-360, was created for assessing the quality of user-generated 360° videos. It includes various distortions and viewer discomfort metrics, aiding research in immersive video quality assessment.

Area of Science:

Computer Vision
Multimedia Signal Processing
Human-Computer Interaction

Background:

User-generated 360° video content is rapidly growing due to accessible technology and its immersive quality.
Existing datasets often lack the diverse distortions found in non-professional, real-world scenarios.

Purpose of the Study:

Introduce RBD-360, a novel dataset specifically for evaluating the quality of user-generated 360° videos.
Provide a comprehensive resource for developing and testing video quality assessment models for immersive content.

Main Methods:

Collected diverse source videos across indoor and outdoor environments (day/night).
Generated impaired video sequences using H.264, H.265, and VP9 codecs with varied compression parameters.
Employed Head-Mounted Display (HMD)-based Modified Absolute Category Rating (MACR) and Simulator Sickness Questionnaire (SSQ) for subjective quality and viewer discomfort assessment, following ITU-T P.919.

Keywords:

360° videos Modified ACR Quality of Experience (QoE)User Generated Content (UGC)Video Quality Assessment (VQA)

Related Experiment Videos

Last Updated: May 18, 2026

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

Published on: July 14, 2023

Main Results:

Benchmark quality assessment metrics were implemented and evaluated on the RBD-360 dataset.
The dataset captures various distortions and viewer discomfort, providing a robust testbed for quality models.

Conclusions:

RBD-360 offers a valuable resource for advancing research in user-generated 360° video quality assessment.
The dataset enables the development of more accurate and robust quality prediction models for immersive media.